AI Data Analyst Zalando

AI Data Analyst Zalando — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Schema-agnostic databases

Schema-agnostic databases or vocabulary-independent databases aim at supporting users to be abstracted from the representation of the data, supporting the automatic semantic matching between queries and databases. Schema-agnosticism is the property of a database of mapping a query issued with the user terminology and structure, automatically mapping it to the dataset vocabulary. The increase in the size and in the semantic heterogeneity of database schemas bring new requirements for users querying and searching structured data. At this scale it can become unfeasible for data consumers to be familiar with the representation of the data in order to query it. At the center of this discussion is the semantic gap between users and databases, which becomes more central as the scale and complexity of the data grows. == Description == The evolution of data environments towards the consumption of data from multiple data sources and the growth in the schema size, complexity, dynamicity and decentralisation (SCoDD) of schemas increases the complexity of contemporary data management. The SCoDD trend emerges as a central data management concern in Big Data scenarios, where users and applications have a demand for more complete data, produced by independent data sources, under different semantic assumptions and contexts of use, which is the typical scenario for Semantic Web Data applications. The evolution of databases in the direction of heterogeneous data environments strongly impacts the usability, semiotics and semantic assumptions behind existing data accessibility methods such as structured queries, keyword-based search and visual query systems. With schema-less databases containing potentially millions of dynamically changing attributes, it becomes unfeasible for some users to become aware of the 'schema' or vocabulary in order to query the database. At this scale, the effort in understanding the schema in order to build a structured query can become prohibitive. == Schema-agnostic queries == Schema-agnostic queries can be defined as query approaches over structured databases which allow users satisfying complex information needs without the understanding of the representation (schema) of the database. Similarly, Tran et al. defines it as "search approaches, which do not require users to know the schema underlying the data". Approaches such as keyword-based search over databases allow users to query databases without employing structured queries. However, as discussed by Tran et al.: "From these points, users however have to do further navigation and exploration to address complex information needs. Unlike keyword search used on the Web, which focuses on simple needs, the keyword search elaborated here is used to obtain more complex results. Instead of a single set of resources, the goal is to compute complex sets of resources and their relations." The development of approaches to support natural language interfaces (NLI) over databases have aimed towards the goal of schema-agnostic queries. Complementarily, some approaches based on keyword search have targeted keyword-based queries which express more complex information needs. Other approaches have explored the construction of structured queries over databases where schema constraints can be relaxed. All these approaches (natural language, keyword-based search and structured queries) have targeted different degrees of sophistication in addressing the problem of supporting a flexible semantic matching between queries and data, which vary from the completely absence of the semantic concern to more principled semantic models. While the demand for schema-agnosticism has been an implicit requirement across semantic search and natural language query systems over structured data, it is not sufficiently individuated as a concept and as a necessary requirement for contemporary database management systems. Recent works have started to define and model the semantic aspects involved on schema-agnostic queries. === Schema-agnostic structured queries === Consist of schema-agnostic queries following the syntax of a structured standard (for example SQL, SPARQL). The syntax and semantics of operators are maintained, while different terminologies are used. ==== Example 1 ==== SELECT ?y { BillClinton hasDaughter ?x . ?x marriedTo ?y . } which maps to the following SPARQL query in the dataset vocabulary: ==== Example 2 ==== which maps to the following SPARQL query in the dataset vocabulary: === Schema-agnostic keyword queries === Consist of schema-agnostic queries using keyword queries. In this case the syntax and semantics of operators are different from the structured query syntax. ==== Example ==== "Bill Clinton daughter married to" "Books by William Goldman with more than 300 pages" == Semantic complexity == As of 2016 the concept of schema-agnostic queries has been developed primarily in academia. Most of schema-agnostic query systems have been investigated in the context of Natural Language Interfaces over databases or over the Semantic Web. These works explore the application of semantic parsing techniques over large, heterogeneous and schema-less databases. More recently, the individuation of the concept of schema-agnostic query systems and databases have appeared more explicitly within the literature. Freitas et al. provide a probabilistic model on the semantic complexity of mapping schema-agnostic queries.
Read more →
Hybrid machine translation

Hybrid machine translation is a method of machine translation that is characterized by the use of multiple machine translation approaches within a single machine translation system. The motivation for developing hybrid machine translation systems stems from the failure of any single technique to achieve a satisfactory level of accuracy. Many hybrid machine translation systems have been successful in improving the accuracy of the translations, and there are several popular machine translation systems which employ hybrid methods. == Approaches == === Multi-engine === This approach to hybrid machine translation involves running multiple machine translation systems in parallel. The final output is generated by combining the output of all the sub-systems. Most commonly, these systems use statistical and rule-based translation subsystems, but other combinations have been explored. For example, researchers at Carnegie Mellon University have had some success combining example-based, transfer-based, knowledge-based and statistical translation sub-systems into one machine translation system. === Statistical rule generation === This approach involves using statistical data to generate lexical and syntactic rules. The input is then processed with these rules as if it were a rule-based translator. This approach attempts to avoid the difficult and time-consuming task of creating a set of comprehensive, fine-grained linguistic rules by extracting those rules from the training corpus. This approach still suffers from many problems of normal statistical machine translation, namely that the accuracy of the translation will depend heavily on the similarity of the input text to the text of the training corpus. As a result, this technique has had the most success in domain-specific applications, and has the same difficulties with domain adaptation as many statistical machine translation systems. === Multi-Pass === This approach involves serially processing the input multiple times. The most common technique used in multi-pass machine translation systems is to pre-process the input with a rule-based machine translation system. The output of the rule-based pre-processor is passed to a statistical machine translation system, which produces the final output. This technique is used to limit the amount of information a statistical system need consider, significantly reducing the processing power required. It also removes the need for the rule-based system to be a complete translation system for the language, significantly reducing the amount of human effort and labor necessary to build the system. === Confidence-Based === This approach differs from the other hybrid approaches in that in most cases only one translation technology is used. A confidence metric is produced for each translated sentence from which a decision can be made whether to try a secondary translation technology or to proceed with the initial translation output. SMT is also used when common error patterns such as multiple repeat words appear in sequence, as is common with NMT when the attention mechanism is confused.
Read more →
Semantic decomposition (natural language processing)

A semantic decomposition is an algorithm that breaks down the meanings of phrases or concepts into less complex concepts. The result of a semantic decomposition is a representation of meaning. This representation can be used for tasks, such as those related to artificial intelligence or machine learning. Semantic decomposition is common in natural language processing applications. The basic idea of a semantic decomposition is taken from the learning skills of adult humans, where words are explained using other words. It is based on Meaning-text theory. Meaning-text theory is used as a theoretical linguistic framework to describe the meaning of concepts with other concepts. == Background == Given that an AI does not inherently have language, it is unable to think about the meanings behind the words of a language. An artificial notion of meaning needs to be created for a strong AI to emerge. Creating an artificial representation of meaning requires the analysis of what meaning is. Many terms are associated with meaning, including semantics, pragmatics, knowledge and understanding or word sense. Each term describes a particular aspect of meaning, and contributes to a multitude of theories explaining what meaning is. These theories need to be analyzed further to develop an artificial notion of meaning best fit for our current state of knowledge. == Graph representations == Representing meaning as a graph is one of the two ways that both an AI cognition and a linguistic researcher think about meaning (connectionist view). Logicians utilize a formal representation of meaning to build upon the idea of symbolic representation, whereas description logics describe languages and the meaning of symbols. This contention between 'neat' and 'scruffy' techniques has been discussed since the 1970s. Research has so far identified semantic measures and with that word-sense disambiguation (WSD) - the differentiation of meaning of words - as the main problem of language understanding. As an AI-complete environment, WSD is a core problem of natural language understanding. AI approaches that use knowledge-given reasoning creates a notion of meaning combining the state of the art knowledge of natural meaning with the symbolic and connectionist formalization of meaning for AI. The abstract approach is shown in Figure. First, a connectionist knowledge representation is created as a semantic network consisting of concepts and their relations to serve as the basis for the representation of meaning. This graph is built out of different knowledge sources like WordNet, Wiktionary, and BabelNET. The graph is created by lexical decomposition that recursively breaks each concept semantically down into a set of semantic primes. The primes are taken from the theory of Natural Semantic Metalanguage, which has been analyzed for usefulness in formal languages. Upon this graph marker passing is used to create the dynamic part of meaning representing thoughts. The marker passing algorithm, where symbolic information is passed along relations form one concept to another, uses node and edge interpretation to guide its markers. The node and edge interpretation model is the symbolic influence of certain concepts. Future work uses the created representation of meaning to build heuristics and evaluate them through capability matching and agent planning, chatbots or other applications of natural language understanding.
Read more →
Sentence embedding

In natural language processing, a sentence embedding is a representation of a sentence as a vector of numbers which encodes meaningful semantic information. State of the art embeddings are based on the learned hidden layer representation of dedicated sentence transformer models. BERT pioneered an approach involving the use of a dedicated [CLS] token prepended to the beginning of each sentence inputted into the model; the final hidden state vector of this token encodes information about the sentence and can be fine-tuned for use in sentence classification tasks. In practice however, BERT's sentence embedding with the [CLS] token achieves poor performance, often worse than simply averaging non-contextual word embeddings. SBERT later achieved superior sentence embedding performance by fine tuning BERT's [CLS] token embeddings through the usage of a siamese neural network architecture on the SNLI dataset. Other approaches are loosely based on the idea of distributional semantics applied to sentences. Skip-Thought trains an encoder-decoder structure for the task of neighboring sentences predictions; this has been shown to achieve worse performance than approaches such as InferSent or SBERT. An alternative direction is to aggregate word embeddings, such as those returned by Word2vec, into sentence embeddings. The most straightforward approach is to simply compute the average of word vectors, known as continuous bag-of-words (CBOW). However, more elaborate solutions based on word vector quantization have also been proposed. One such approach is the vector of locally aggregated word embeddings (VLAWE), which demonstrated performance improvements in downstream text classification tasks. == Applications == In recent years, sentence embedding has seen a growing level of interest due to its applications in natural language queryable knowledge bases through the usage of vector indexing for semantic search. LangChain for instance utilizes sentence transformers for purposes of indexing documents. In particular, an indexing is generated by generating embeddings for chunks of documents and storing (document chunk, embedding) tuples. Then given a query in natural language, the embedding for the query can be generated. A top k similarity search algorithm is then used between the query embedding and the document chunk embeddings to retrieve the most relevant document chunks as context information for question answering tasks. This approach is also known formally as retrieval-augmented generation. Though not as predominant as BERTScore, sentence embeddings are commonly used for sentence similarity evaluation which sees common use for the task of optimizing a Large language model's generation parameters is often performed via comparing candidate sentences against reference sentences. By using the cosine-similarity of the sentence embeddings of candidate and reference sentences as the evaluation function, a grid-search algorithm can be utilized to automate hyperparameter optimization. == Evaluation == A way of testing sentence encodings is to apply them on Sentences Involving Compositional Knowledge (SICK) corpus for both entailment (SICK-E) and relatedness (SICK-R). In the best results are obtained using a BiLSTM network trained on the Stanford Natural Language Inference (SNLI) Corpus. The Pearson correlation coefficient for SICK-R is 0.885 and the result for SICK-E is 86.3. A slight improvement over previous scores is presented in: SICK-R: 0.888 and SICK-E: 87.8 using a concatenation of bidirectional Gated recurrent unit.
Read more →
Multiple buffering

In computer science, multiple buffering is the use of more than one buffer to hold a block of data, so that a "reader" will see a complete (though perhaps old) version of the data instead of a partially updated version of the data being created by a "writer". It is very commonly used for computer display images. It is also used to avoid the need to use dual-ported RAM (DPRAM) when the readers and writers are different devices. == Description == === Double buffering Petri net === The Petri net in the illustration shows double buffering. Transitions W1 and W2 represent writing to buffer 1 and 2 respectively while R1 and R2 represent reading from buffer 1 and 2 respectively. At the beginning, only the transition W1 is enabled. After W1 fires, R1 and W2 are both enabled and can proceed in parallel. When they finish, R2 and W1 proceed in parallel and so on. After the initial transient where W1 fires alone, this system is periodic and the transitions are enabled – always in pairs (R1 with W2 and R2 with W1 respectively). == Double buffering in computer graphics == In computer graphics, double buffering is a technique for drawing graphics that shows less stutter, tearing, and other artifacts. It is difficult for a program to draw a display so that pixels do not change more than once. For instance, when updating a page of text, it is much easier to clear the entire page and then draw the letters than to somehow erase only the pixels that are used in old letters but not in new ones. However, this intermediate image is seen by the user as flickering. In addition, computer monitors constantly redraw the visible video page (traditionally at around 60 times a second), so even a perfect update may be visible momentarily as a horizontal divider between the "new" image and the un-redrawn "old" image, known as tearing. === Software double buffering === A software implementation of double buffering has all drawing operations store their results in some region of system RAM; any such region is often called a "back buffer". When all drawing operations are considered complete, the whole region (or only the changed portion) is copied into the video RAM (the "front buffer"); this copying is usually synchronized with the monitor's raster beam in order to avoid tearing. Software implementations of double buffering necessarily require more memory and CPU time than single buffering because of the system memory allocated for the back buffer, the time for the copy operation, and the time waiting for synchronization. Compositing window managers often combine the "copying" operation with "compositing" used to position windows, transform them with scale or warping effects, and make portions transparent. Thus, the "front buffer" may contain only the composite image seen on the screen, while there is a different "back buffer" for every window containing the non-composited image of the entire window contents. === Page flipping === In the page-flip method, instead of copying the data, both buffers are capable of being displayed. At any one time, one buffer is actively being displayed by the monitor, while the other, background buffer is being drawn. When the background buffer is complete, the roles of the two are switched. The page-flip is typically accomplished by modifying a hardware register in the video display controller—the value of a pointer to the beginning of the display data in the video memory. The page-flip is much faster than copying the data and can guarantee that tearing will not be seen as long as the pages are switched over during the monitor's vertical blanking interval—the blank period when no video data is being drawn. The currently active and visible buffer is called the front buffer, while the background page is called the back buffer. == Triple buffering == In computer graphics, triple buffering is similar to double buffering but can provide improved performance. In double buffering, the program must wait until the finished drawing is copied or swapped before starting the next drawing. This waiting period could be several milliseconds during which neither buffer can be touched. In triple buffering, the program has two back buffers and can immediately start drawing in the one that is not involved in such copying. The third buffer, the front buffer, is read by the graphics card to display the image on the monitor. Once the image has been sent to the monitor, the front buffer is flipped with (or copied from) the back buffer holding the most recent complete image. Since one of the back buffers is always complete, the graphics card never has to wait for the software to complete. Consequently, the software and the graphics card are completely independent and can run at their own pace. Finally, the displayed image was started without waiting for synchronization and thus with minimum lag. Due to the software algorithm not polling the graphics hardware for monitor refresh events, the algorithm may continuously draw additional frames as fast as the hardware can render them. For frames that are completed much faster than interval between refreshes, it is possible to replace a back buffers' frames with newer iterations multiple times before copying. This means frames may be written to the back buffer that are never used at all before being overwritten by successive frames. Nvidia has implemented this method under the name "Fast Sync". An alternative method sometimes referred to as triple buffering is a swap chain three buffers long. After the program has drawn both back buffers, it waits until the first one is placed on the screen, before drawing another back buffer (i.e. it is a 3-long first in, first out queue). Most Windows games seem to refer to this method when enabling triple buffering. == Quad buffering == The term quad buffering is the use of double buffering for each of the left and right eye images in stereoscopic implementations, thus four buffers total (if triple buffering was used then there would be six buffers). The command to swap or copy the buffer typically applies to both pairs at once, so at no time does one eye see an older image than the other eye. Quad buffering requires special support in the graphics card drivers which is disabled for most consumer cards. AMD's Radeon HD 6000 Series and newer support it. 3D standards like OpenGL and Direct3D support quad buffering. == Double buffering for DMA == The term double buffering is used for copying data between two buffers for direct memory access (DMA) transfers, not for enhancing performance, but to meet specific addressing requirements of a device (particularly 32-bit devices on systems with wider addressing provided via Physical Address Extension). Windows device drivers are a place where the term "double buffering" is likely to be used. Linux and BSD source code calls these "bounce buffers". Some programmers try to avoid this kind of double buffering with zero-copy techniques. == Other uses == Double buffering is also used as a technique to facilitate interlacing or deinterlacing of video signals.
Read more →
Neural radiance field

A neural radiance field (NeRF) is a neural field for reconstructing a three-dimensional representation of a scene from two-dimensional images. The NeRF model enables downstream applications of novel view synthesis, scene geometry reconstruction, and obtaining the reflectance properties of the scene. Additional scene properties such as camera poses may also be jointly learned. First introduced in 2020, it has since gained significant attention for its potential applications in computer graphics and content creation. == Algorithm == The NeRF algorithm represents a scene as a radiance field parametrized by a deep neural network (DNN). The network predicts a volume density and view-dependent emitted radiance given the spatial location ( x , y , z ) {\displaystyle (x,y,z)} and viewing direction in Euler angles ( θ , Φ ) {\displaystyle (\theta ,\Phi )} of the camera. By sampling many points along camera rays, traditional volume rendering techniques can produce an image. === Data collection === A NeRF needs to be retrained for each unique scene. The first step is to collect images of the scene from different angles and their respective camera pose. These images are standard 2D images and do not require a specialized camera or software. Any camera is able to generate datasets, provided the settings and capture method meet the requirements for SfM (Structure from Motion). This requires tracking of the camera position and orientation, often through some combination of SLAM, GPS, or inertial estimation. Researchers often use synthetic data to evaluate NeRF and related techniques. For such data, images (rendered through traditional non-learned methods) and respective camera poses are reproducible and error-free. === Training === For each sparse viewpoint (image and camera pose) provided, camera rays are marched through the scene, generating a set of 3D points with a given radiance direction (into the camera). For these points, volume density and emitted radiance are predicted using the multi-layer perceptron (MLP). An image is then generated through classical volume rendering. Because this process is fully differentiable, the error between the predicted image and the original image can be minimized with gradient descent over multiple viewpoints, encouraging the MLP to develop a coherent model of the scene. == Variations and improvements == Early versions of NeRF were slow to optimize and required that all input views were taken with the same camera in the same lighting conditions. These performed best when limited to orbiting around individual objects, such as a drum set, plants or small toys. Since the original paper in 2020, many improvements have been made to the NeRF algorithm, with variations for special use cases. === Fourier feature mapping === In 2020, shortly after the release of NeRF, the addition of Fourier Feature Mapping improved training speed and image accuracy. Deep neural networks struggle to learn high frequency functions in low dimensional domains; a phenomenon known as spectral bias. To overcome this shortcoming, points are mapped to a higher dimensional feature space before being fed into the MLP. γ ( v ) = [ a 1 cos ⁡ ( 2 π B 1 T v ) a 1 sin ⁡ ( 2 π B 1 T v ) ⋮ a m cos ⁡ ( 2 π B m T v ) a m sin ⁡ ( 2 π B m T v ) ] {\displaystyle \gamma (\mathrm {v} )={\begin{bmatrix}a_{1}\cos(2{\pi }{\mathrm {B} }_{1}^{T}\mathrm {v} )\\a_{1}\sin(2\pi {\mathrm {B} }_{1}^{T}\mathrm {v} )\\\vdots \\a_{m}\cos(2{\pi }{\mathrm {B} }_{m}^{T}\mathrm {v} )\\a_{m}\sin(2{\pi }{\mathrm {B} }_{m}^{T}\mathrm {v} )\end{bmatrix}}} Where v {\displaystyle \mathrm {v} } is the input point, B i {\displaystyle \mathrm {B} _{i}} are the frequency vectors, and a i {\displaystyle a_{i}} are coefficients. This allows for rapid convergence to high frequency functions, such as pixels in a detailed image. === Bundle-adjusting neural radiance fields === One limitation of NeRFs is the requirement of knowing accurate camera poses to train the model. Often times, pose estimation methods are not completely accurate, nor is the camera pose even possible to know. These imperfections result in artifacts and suboptimal convergence. So, a method was developed to optimize the camera pose along with the volumetric function itself. Called Bundle-Adjusting Neural Radiance Field (BARF), the technique uses a dynamic low-pass filter (DLPF) to go from coarse to fine adjustment, minimizing error by finding the geometric transformation to the desired image. This corrects imperfect camera poses and greatly improves the quality of NeRF renders. === Multiscale representation === Conventional NeRFs struggle to represent detail at all viewing distances, producing blurry images up close and overly aliased images from distant views. In 2021, researchers introduced a technique to improve the sharpness of details at different viewing scales known as mip-NeRF (comes from mipmap). Rather than sampling a single ray per pixel, the technique fits a gaussian to the conical frustum cast by the camera. This improvement effectively anti-aliases across all viewing scales. mip-NeRF also reduces overall image error and is faster to converge at about half the size of ray-based NeRF. === Learned initializations === In 2021, researchers applied meta-learning to assign initial weights to the MLP. This rapidly speeds up convergence by effectively giving the network a head start in gradient descent. Meta-learning also allowed the MLP to learn an underlying representation of certain scene types. For example, given a dataset of famous tourist landmarks, an initialized NeRF could partially reconstruct a scene given one image. === NeRF in the wild === Conventional NeRFs are vulnerable to slight variations in input images (objects, lighting) often resulting in ghosting and artifacts. As a result, NeRFs struggle to represent dynamic scenes, such as bustling city streets with changes in lighting and dynamic objects. In 2021, researchers at Google developed a new method for accounting for these variations, named NeRF in the Wild (NeRF-W). This method splits the neural network (MLP) into three separate models. The main MLP is retained to encode the static volumetric radiance. However, it operates in sequence with a separate MLP for appearance embedding (changes in lighting, camera properties) and an MLP for transient embedding (changes in scene objects). This allows the NeRF to be trained on diverse photo collections, such as those taken by mobile phones at different times of day. === Relighting === In 2021, researchers added more outputs to the MLP at the heart of NeRFs. The output now included: volume density, surface normal, material parameters, distance to the first surface intersection (in any direction), and visibility of the external environment in any direction. The inclusion of these new parameters lets the MLP learn material properties, rather than pure radiance values. This facilitates a more complex rendering pipeline, calculating direct and global illumination, specular highlights, and shadows. As a result, the NeRF can render the scene under any lighting conditions with no re-training. === Plenoctrees === Although NeRFs had reached high levels of fidelity, their costly compute time made them useless for many applications requiring real-time rendering, such as VR/AR and interactive content. Introduced in 2021, Plenoctrees (plenoptic octrees) enabled real-time rendering of pre-trained NeRFs through division of the volumetric radiance function into an octree. Rather than assigning a radiance direction into the camera, viewing direction is taken out of the network input and spherical radiance is predicted for each region. This makes rendering over 3000x faster than conventional NeRFs. === Sparse Neural Radiance Grid === Similar to Plenoctrees, this method enabled real-time rendering of pretrained NeRFs. To avoid querying the large MLP for each point, this method bakes NeRFs into Sparse Neural Radiance Grids (SNeRG). A SNeRG is a sparse voxel grid containing opacity and color, with learned feature vectors to encode view-dependent information. A lightweight, more efficient MLP is then used to produce view-dependent residuals to modify the color and opacity. To enable this compressive baking, small changes to the NeRF architecture were made, such as running the MLP once per pixel rather than for each point along the ray. These improvements make SNeRG extremely efficient, outperforming Plenoctrees. === Instant NeRFs === In 2022, researchers at Nvidia enabled real-time training of NeRFs through a technique known as Instant Neural Graphics Primitives. An innovative input encoding reduces computation, enabling real-time training of a NeRF, an improvement orders of magnitude above previous methods. The speedup stems from the use of spatial hash functions, which have O ( 1 ) {\displaystyle O(1)} access times, and parallelized architectures which run fast on modern GPUs. == Related techniques == === Plenoxels === Plen
Read more →
Kdan Mobile

Kdan Mobile Software Limited is a software application development company based in Tainan City, Taiwan. Kdan also has branches in Taipei, Changsha, Irvine, California, Japan, and South Korea. The company was founded in 2009 by Kenny Su, the company's CEO. == History == Kdan Mobile was founded in 2009 by Kenny Su (蘇柏州) and develops an application for PDF documents. Su previously worked at the Industrial Technology Research Institute (ITRI) . In 2018, the company completed its Series B round of fundraising, in which it raised 16 million USD in total. Four global firms, Dattoz Partners (South Korea), WI Harper Group (U.S.), Taiwania Capital (Taiwan), and Golden Asia Fund Mitsubishi UFJ Capital (Japan), made up the Series B investment. Kdan previously raised 5 million USD in its Series A round in 2018.
Read more →
LanguageWare

LanguageWare is a natural language processing (NLP) technology developed by IBM, which allows applications to process natural language text. It comprises a set of Java libraries that provide a range of NLP functions: language identification, text segmentation/tokenization, normalization, entity and relationship extraction, and semantic analysis and disambiguation. The analysis engine uses a finite-state machine approach at multiple levels, which aids its performance characteristics while maintaining a reasonably small footprint. The behaviour of the system is driven by a set of configurable lexico-semantic resources which describe the characteristics and domain of the processed language. A default set of resources comes as part of LanguageWare and these describe the native language characteristics, such as morphology, and the basic vocabulary for the language. Supplemental resources have been created that capture additional vocabularies, terminologies, rules and grammars, which may be generic to the language or specific to one or more domains. A set of Eclipse-based customization tooling, LanguageWare Resource Workbench, is available on IBM's alphaWorks site, and allows domain knowledge to be compiled into these resources and thereby incorporated into the analysis process. LanguageWare can be deployed as a set of UIMA-compliant annotators, Eclipse plug-ins or Web Services.
Read more →
Opponent process

The opponent process is a hypothesis of color vision that states that the human visual system interprets information about color by processing signals from the three types of photoreceptor cells in an antagonistic manner. The three types of cones are called L, M, and S. The names stand for "Long wavelength sensitive,” "middle wavelength sensitive," and "short wavelength sensitive." The opponent-process theory implicates three opponent channels: L versus M, S versus (L+M), and a luminance channel (+ versus -). These cone-opponent mechanisms were at one time thought to be the neural substrate for a psychological theory called Hering's Opponent Colors Theory, which calls for three psychologically important opponent color processes: red versus green, blue versus yellow, and black versus white (luminance). The Opponent Colors Theory is named for the German physiologist Ewald Hering who proposed the idea in the late 19th century. However, it has been argued that Hering’s Opponent Colors Theory lacks adequate phenomenological and empirical support, and may not be a necessary feature of normal human color experience. Correspondingly, considerable physiological and behavioral evidence proves that the physiological cone opponent mechanisms do not constitute the neurobiological basis for Hering's Opponent Colors Theory. == Color theory == === Complementary colors === When staring at a bright color for a while (e.g. red), then looking away at a white field, an afterimage is perceived, such that the original color will evoke its complementary color (cyan, in the case of red input). When complementary colors are combined or mixed, they "cancel each other out" and become neutral (white or gray). That is, complementary colors are never perceived as a mixture; there is no "greenish red" or "yellowish blue", despite claims to the contrary. The strongest color contrast that a color can have is its complementary color. Complementary colors may also be called "opposite colors" and they were originally considered the primary evidence in support of Hering's Opponent Colors Theory. There are two fatal problems with this evidence. First, the complement of red is not green, as called for by Hering's theory; it is bluish-green. And second, there exists a complementary color for every color, so there is nothing special about the set of complementary pairs picked out by Hering's theory. === Unique hues === The colors that define the extremes for each opponent channel are called unique hues, as opposed to composite (mixed) hues. Ewald Hering first defined the unique hues as red, green, blue, and yellow, and based them on the concept that these colors could not be simultaneously perceived. For example, a color cannot appear both red and green. These definitions have been experimentally refined and are represented today by average hue angles of 353° (carmine red), 128° (cobalt green), 228° (cobalt blue), 58° (yellow). The unique hues are a defining feature of many psychological color spaces, but there is substantial evidence showing that the unique hues are not hard wired in the nervous system, contrary to the stipulations of Hering's Opponent Colors Theory. Unique hues can differ between individuals and are often used in psychophysical research to measure variations in color perception due to color-vision deficiencies or color adaptation. While there is considerable inter-subject variability when defining unique hues experimentally, an individual's unique hues are very consistent, to within a few nanometers of wavelength. == Physiological basis == === Relation to LMS color space === The trichromatic theory is in conflict with Hering's Opponent Colors Theory, although it is compatible with a physiological opponent process that compares the outputs of the different classes of cone types. The poles of these cone opponent mechanisms do not correspond to the unique hues of Hering's Opponent Colors Theory and unlike the unique hues, have no privilege in color perception. Most humans have three different cone cells in their retinas that facilitate trichromatic color vision. Colors are determined by the proportional excitation of these three cone types, i.e. their quantum catch. The levels of excitation of each cone type are the parameters that define LMS color space. To calculate the opponent process tristimulus values from the LMS color space, the cone excitations must be compared: The luminous (achromatic) opponent channel is a weighted sum of all three cone cells (plus the rod cells in some conditions). The red–green opponent channel is equal to the difference of the L- and M-cones. The blue–yellow opponent channel is equal to the difference of the S-cone and the average/weighted sum of the L- and M-cones. Most mammals have no L cone (the primate L cone arose from a gene duplication of the M cone opsin gene). These mammals still show two kinds of opponent channels in their retinal ganglion cells: the achromatic channel and the blue-yellow opponency channel. === Cone opponent mechanisms are encoded in the retina === The output of different types of cones are compared by cells in the retina including retina bipolar cells (which compare signals from L and M cones) and bistratified retinal ganglion cells (which compare S cone signals with L and M cone signals). The output of bipolar cells is relayed to the visual cortex by the retinal ganglion cells (RGCs) by way of a thalamic relay station called the lateral geniculate nucleus (LGN) of the thalamus. Much of the scientific knowledge of retinal ganglion cell physiology was obtained by neural recordings of cells in the LGN. The cone-opponent mechanisms in the retina and LGN represent a fundamental physiological opponent process but do not represent the unique hues (or Hering's Opponent Colors Theory). For example, the colors that best elicit responses of the bistratified S-(L+M)-opponent neurons are best described as purplish (or lavender) and lime-green, not "blue" and "yellow". The neurons are sometimes referred to as "blue–yellow" neurons, but this is a historical artifact dating to the time when it was thought that Hering's Opponent Colors Theory was hardwired by the retina and the mismatch between the colors to which they are optimally tuned and Hering's Opponent Colors was overlooked. Cone opponent mechanisms exist in the retinas of many mammals, including monkeys, mice, and cats. In primates, the LGN contains three major classes of layers: Magnocellular layers (M, large-cell) – responsible largely for the luminance channel Parvocellular layers (P, small-cell) – responsible largely for red–green opponency Koniocellular layers (K) – responsible largely for blue–yellow opponency, poor spatial resolution, long latency Other mammals such as cats also have three cell types denoted as X (magno), Y (parvo), and W (konio). The W type is beyond most doubt homologous to the primate K type. There are some subtle differences between the M and X types as well as the Y and P types to make the correspondence unclear. === Advantage === Transmitting information in opponent-channel color space could be advantageous over transmitting it in LMS color space ("raw" signals from each cone type). There is some overlap in the wavelengths of light to which the three types of cones (L for long-wave, M for medium-wave, and S for short-wave light) respond, so it is more efficient for the visual system (from a perspective of dynamic range) to record differences between the responses of cones, rather than each type of cone's individual response. Hurvich and Jameson argued that the use of opponent-channel color space would increase color contrast, making the information easier to process by later stages of vision. === Color blindness === Color blindness can be classified by the cone cell that is affected (protan, deutan, tritan) or by the opponent channel that is affected (red–green or blue–yellow). In either case, the channel can either be inactive (in the case of dichromacy) or have a lower dynamic range (in the case of anomalous trichromacy). For example, individuals with deuteranopia see little difference between the red and green unique hues. == History == Johann Wolfgang von Goethe first studied the physiological effect of opposed colors in his Theory of Colours in 1810. Goethe arranged his color wheel symmetrically "for the colours diametrically opposed to each other in this diagram are those which reciprocally evoke each other in the eye. Thus, yellow demands purple; orange, blue; red, green; and vice versa: Thus again all intermediate gradations reciprocally evoke each other." Ewald Hering proposed opponent color theory in 1892. He thought that the colors red, yellow, green, and blue are special in that any other color can be described as a mix of them, and that they exist in opposite pairs. That is, either red or green is perceived and never greenish-red: Even though yellow is a mixture of red and green in the RGB color theory, humans
Read more →
Weak supervision

Weak supervision (also known as semi-supervised learning) is a paradigm in machine learning, the relevance and notability of which increased with the advent of large language models due to the large amount of data required to train them. It is characterized by using a combination of a small amount of human-labeled data (exclusively used in more expensive and time-consuming supervised learning paradigm), followed by a large amount of unlabeled data (used exclusively in unsupervised learning paradigm). In other words, the desired output values are provided only for a subset of the training data. The remaining data is unlabeled or imprecisely labeled. Intuitively, it can be seen as an exam and labeled data as sample problems that the teacher solves for the class as an aid in solving another set of problems. In the transductive setting, these unsolved problems act as exam questions. In the inductive setting, they become practice problems of the sort that will make up the exam. == Problem == The acquisition of labeled data for a learning problem often requires a skilled human agent (e.g. to transcribe an audio segment) or a physical experiment (e.g. determining the 3D structure of a protein or determining whether there is oil at a particular location). The cost associated with the labeling process thus may render large, fully labeled training sets infeasible, whereas acquisition of unlabeled data is relatively inexpensive. In such situations, semi-supervised learning can be of great practical value. Semi-supervised learning is also of theoretical interest in machine learning and as a model for human learning. == Technique == More formally, semi-supervised learning assumes a set of l {\displaystyle l} independently identically distributed examples x 1 , … , x l ∈ X {\displaystyle x_{1},\dots ,x_{l}\in X} with corresponding labels y 1 , … , y l ∈ Y {\displaystyle y_{1},\dots ,y_{l}\in Y} and u {\displaystyle u} unlabeled examples x l + 1 , … , x l + u ∈ X {\displaystyle x_{l+1},\dots ,x_{l+u}\in X} are processed. Semi-supervised learning combines this information to surpass the classification performance that can be obtained either by discarding the unlabeled data and doing supervised learning or by discarding the labels and doing unsupervised learning. Semi-supervised learning may refer to either transductive learning or inductive learning. The goal of transductive learning is to infer the correct labels for the given unlabeled data x l + 1 , … , x l + u {\displaystyle x_{l+1},\dots ,x_{l+u}} only. The goal of inductive learning is to infer the correct mapping from X {\displaystyle X} to Y {\displaystyle Y} . It is unnecessary (and, according to Vapnik's principle, imprudent) to perform transductive learning by way of inferring a classification rule over the entire input space; however, in practice, algorithms formally designed for transduction or induction are often used interchangeably. == Assumptions == In order to make any use of unlabeled data, some relationship to the underlying distribution of data must exist. Semi-supervised learning algorithms make use of at least one of the following assumptions: === Continuity / smoothness assumption === Points that are close to each other are more likely to share a label. This is also generally assumed in supervised learning and yields a preference for geometrically simple decision boundaries. In the case of semi-supervised learning, the smoothness assumption additionally yields a preference for decision boundaries in low-density regions, so few points are close to each other but in different classes. === Cluster assumption === The data tend to form discrete clusters, and points in the same cluster are more likely to share a label (although data that shares a label may spread across multiple clusters). This is a special case of the smoothness assumption and gives rise to feature learning with clustering algorithms. === Manifold assumption === The data lie approximately on a manifold of much lower dimension than the input space. In this case learning the manifold using both the labeled and unlabeled data can avoid the curse of dimensionality. Then learning can proceed using distances and densities defined on the manifold. The manifold assumption is practical when high-dimensional data are generated by some process that may be hard to model directly, but which has only a few degrees of freedom. For instance, human voice is controlled by a few vocal folds, and images of various facial expressions are controlled by a few muscles. In these cases, it is better to consider distances and smoothness in the natural space of the generating problem, rather than in the space of all possible acoustic waves or images, respectively. == History == The heuristic approach of self-training (also known as self-learning or self-labeling) is historically the oldest approach to semi-supervised learning, with examples of applications starting in the 1960s. The transductive learning framework was formally introduced by Vladimir Vapnik in the 1970s. Interest in inductive learning using generative models also began in the 1970s. A probably approximately correct learning bound for semi-supervised learning of a Gaussian mixture was demonstrated by Ratsaby and Venkatesh in 1995. == Methods == === Generative models === Generative approaches to statistical learning first seek to estimate p ( x | y ) {\displaystyle p(x|y)} , the distribution of data points belonging to each class. The probability p ( y | x ) {\displaystyle p(y|x)} that a given point x {\displaystyle x} has label y {\displaystyle y} is then proportional to p ( x | y ) p ( y ) {\displaystyle p(x|y)p(y)} by Bayes' rule. Semi-supervised learning with generative models can be viewed either as an extension of supervised learning (classification plus information about p ( x ) {\displaystyle p(x)} ) or as an extension of unsupervised learning (clustering plus some labels). Generative models assume that the distributions take some particular form p ( x | y , θ ) {\displaystyle p(x|y,\theta )} parameterized by the vector θ {\displaystyle \theta } . If these assumptions are incorrect, the unlabeled data may actually decrease the accuracy of the solution relative to what would have been obtained from labeled data alone. However, if the assumptions are correct, then the unlabeled data necessarily improves performance. The unlabeled data are distributed according to a mixture of individual-class distributions. In order to learn the mixture distribution from the unlabeled data, it must be identifiable, that is, different parameters must yield different summed distributions. Gaussian mixture distributions are identifiable and commonly used for generative models. The parameterized joint distribution can be written as p ( x , y | θ ) = p ( y | θ ) p ( x | y , θ ) {\displaystyle p(x,y|\theta )=p(y|\theta )p(x|y,\theta )} by using the chain rule. Each parameter vector θ {\displaystyle \theta } is associated with a decision function f θ ( x ) = argmax y p ( y | x , θ ) {\displaystyle f_{\theta }(x)={\underset {y}{\operatorname {argmax} }}\ p(y|x,\theta )} . The parameter is then chosen based on fit to both the labeled and unlabeled data, weighted by λ {\displaystyle \lambda } : argmax Θ ( log ⁡ p ( { x i , y i } i = 1 l | θ ) + λ log ⁡ p ( { x i } i = l + 1 l + u | θ ) ) {\displaystyle {\underset {\Theta }{\operatorname {argmax} }}\left(\log p(\{x_{i},y_{i}\}_{i=1}^{l}|\theta )+\lambda \log p(\{x_{i}\}_{i=l+1}^{l+u}|\theta )\right)} === Low-density separation === Another major class of methods attempts to place boundaries in regions with few data points (labeled or unlabeled). One of the most commonly used algorithms is the transductive support vector machine, or TSVM (which, despite its name, may be used for inductive learning as well). Whereas support vector machines for supervised learning seek a decision boundary with maximal margin over the labeled data, the goal of TSVM is a labeling of the unlabeled data such that the decision boundary has maximal margin over all of the data. In addition to the standard hinge loss ( 1 − y f ( x ) ) + {\displaystyle (1-yf(x))_{+}} for labeled data, a loss function ( 1 − | f ( x ) | ) + {\displaystyle (1-|f(x)|)_{+}} is introduced over the unlabeled data by letting y = sign ⁡ f ( x ) {\displaystyle y=\operatorname {sign} {f(x)}} . TSVM then selects f ∗ ( x ) = h ∗ ( x ) + b {\displaystyle f^{}(x)=h^{}(x)+b} from a reproducing kernel Hilbert space H {\displaystyle {\mathcal {H}}} by minimizing the regularized empirical risk: f ∗ = argmin f ( ∑ i = 1 l ( 1 − y i f ( x i ) ) + + λ 1 ‖ h ‖ H 2 + λ 2 ∑ i = l + 1 l + u ( 1 − | f ( x i ) | ) + ) {\displaystyle f^{}={\underset {f}{\operatorname {argmin} }}\left(\displaystyle \sum _{i=1}^{l}(1-y_{i}f(x_{i}))_{+}+\lambda _{1}\|h\|_{\mathcal {H}}^{2}+\lambda _{2}\sum _{i=l+1}^{l+u}(1-|f(x_{i})|)_{+}\right)} An exact solution is intractable due to the non-convex term ( 1 − | f ( x ) | ) + {\displayst
Read more →
Ontology learning

Ontology learning (ontology extraction, ontology augmentation generation, ontology generation, or ontology acquisition) is the automatic or semi-automatic creation of ontologies, including extracting the corresponding domain's terms and the relationships between the concepts that these terms represent from a corpus of natural language text, and encoding them with an ontology language for easy retrieval. As building ontologies manually is extremely labor-intensive and time-consuming, there is great motivation to automate the process. Typically, the process starts by extracting terms and concepts or noun phrases from plain text using linguistic processors such as part-of-speech tagging and phrase chunking. Then statistical or symbolic techniques are used to extract relation signatures, often based on pattern-based or definition-based hypernym extraction techniques. == Procedure == Ontology learning (OL) is used to (semi-)automatically extract whole ontologies from natural language text. The process is usually split into the following eight tasks, which are not all necessarily applied in every ontology learning system. === Domain terminology extraction === During the domain terminology extraction step, domain-specific terms are extracted, which are used in the following step (concept discovery) to derive concepts. Relevant terms can be determined, e.g., by calculation of the TF/IDF values or by application of the C-value / NC-value method. The resulting list of terms has to be filtered by a domain expert. In the subsequent step, similarly to coreference resolution in information extraction, the OL system determines synonyms, because they share the same meaning and therefore correspond to the same concept. The most common methods therefore are clustering and the application of statistical similarity measures. === Concept discovery === In the concept discovery step, terms are grouped to meaning bearing units, which correspond to an abstraction of the world and therefore to concepts. The grouped terms are these domain-specific terms and their synonyms, which were identified in the domain terminology extraction step. === Concept hierarchy derivation === In the concept hierarchy derivation step, the OL system tries to arrange the extracted concepts in a taxonomic structure. This is mostly achieved with unsupervised hierarchical clustering methods. Because the result of such methods is often noisy, a supervision step, e.g., user evaluation, is added. A further method for the derivation of a concept hierarchy exists in the usage of several patterns that should indicate a sub- or supersumption relationship. Patterns like “X, that is a Y” or “X is a Y” indicate that X is a subclass of Y. Such pattern can be analyzed efficiently, but they often occur too infrequently to extract enough sub- or supersumption relationships. Instead, bootstrapping methods are developed, which learn these patterns automatically and therefore ensure broader coverage. === Learning of non-taxonomic relations === In the learning of non-taxonomic relations step, relationships are extracted that do not express any sub- or supersumption. Such relationships are, e.g., works-for or located-in. There are two common approaches to solve this subtask. The first is based upon the extraction of anonymous associations, which are named appropriately in a second step. The second approach extracts verbs, which indicate a relationship between entities, represented by the surrounding words. The result of both approaches need to be evaluated by an ontologist to ensure accuracy. === Rule discovery === During rule discovery, axioms (formal description of concepts) are generated for the extracted concepts. This can be achieved, e.g., by analyzing the syntactic structure of a natural language definition and the application of transformation rules on the resulting dependency tree. The result of this process is a list of axioms, which, afterwards, is comprehended to a concept description. This output is then evaluated by an ontologist. === Ontology population === At this step, the ontology is augmented with instances of concepts and properties. For the augmentation with instances of concepts, methods based on the matching of lexico-syntactic patterns are used. Instances of properties are added through the application of bootstrapping methods, which collect relation tuples. === Concept hierarchy extension === In this step, the OL system tries to extend the taxonomic structure of an existing ontology with further concepts. This can be performed in a supervised manner with a trained classifier or in an unsupervised manner via the application of similarity measures. === Frame and Event detection === During frame/event detection, the OL system tries to extract complex relationships from text, e.g., who departed from where to what place and when. Approaches range from applying SVM with kernel methods to semantic role labeling (SRL) to deep semantic parsing techniques. == Tools == Dog4Dag (Dresden Ontology Generator for Directed Acyclic Graphs) is an ontology generation plugin for Protégé 4.1 and OBOEdit 2.1. It allows for term generation, sibling generation, definition generation, and relationship induction. Integrated into Protégé 4.1 and OBO-Edit 2.1, DOG4DAG allows ontology extension for all common ontology formats (e.g., OWL and OBO). Limited largely to EBI and Bio Portal lookup service extensions.
Read more →
Document mosaicing

Document mosaicing is a process that stitches multiple, overlapping snapshot images of a document together to produce one large, high resolution composite. The document is slid under a stationary, over-the-desk camera by hand until all parts of the document are snapshotted by the camera's field of view. As the document slid under the camera, all motion of the document is coarsely tracked by the vision system. The document is periodically snapshotted such that the successive snapshots are overlap by about 50%. The system then finds the overlapped pairs and stitches them together repeatedly until all pairs are stitched together as one piece of document. The document mosaicing can be divided into four main processes. Tracking Feature detecting Correspondences establishing Images mosaicing. == Tracking (simple correlation process) == In this process, the motion of the document slid under the camera is coarsely tracked by the system. Tracking is performed by a process called simple correlation process. In the first frame of snapshots, a small patch is extracted from the center of the image as a correlation template. The correlation process is performed in the four times size of the patch area of the next frame. The motion of the paper is indicated by the peak in the correlation function. The peak in the correlation function indicates the motion of the paper. The template is resampled from this frame and the tracking continues until the template reaches the edge of the document. After the template reaches the edge of the document, another snapshot is taken and the tracking process performs repeatedly until the whole document is imaged. The snapshots are stored in an ordered list to facilitate pairing the overlapped images in later processes. == Feature detecting for efficient matching == Feature detection is the process of finding the transformation that aligns one image with another. There are two main approaches for feature detection. Feature-based approach : Motion parameters are estimated from point correspondences. This approach is suitable for the case that there is plenty supply of stable and detectable features. Featureless approach : When the motion between the two images is small, the motion parameters are estimated using optical flow. On the other hand, when the motion between the two images is large, the motion parameters are estimated using generalised cross-correlation. However, this approach requires a computationally expensive resources. Each image is segmented into a hierarchy of columns, lines, and words to match the organised sets of features across images. Skew angle estimation and columns, lines and words finding are the examples of feature detection operations. === Skew angle estimation === Firstly, the angle that the rows of text make with the image raster lines (skew angle) is estimated. It is assumed to lie in the range of ±20°. A small patch of text in the image is selected randomly and then rotated in the range of ±20° until the variance of the pixel intensities of the patch summed along the raster lines is maximised. To ensure that the found skew angle is accurate, the document mosaic system performs calculation at many image patches and derive the final estimation by finding the average of the individual angles weighted by the variance of the pixel intensities of each patch. === Columns, lines and words finding === In this operation, the de-skewed document is intuitively segmented into a hierarchy of columns, lines and words. The sensitivity to illumination and page coloration of the de-skewed document can be removed by applying a Sobel operator to the de-skewed image and thresholding the output to obtain the binary gradient, de-skewed image. The operation can be roughly separated into 3 steps: column segmentation, line segmentation and word segmentation. Columns are easily segmented from the binary gradient, de-skewed images by summing pixels vertically. Baselines of each row are segmented in the same way as the column segmentation process but horizontally. Finally, individual words are segmented by applying the vertical process at each segmented row. These segmentations are important because the document mosaic is created by matching the lower right corners of words in overlapping images pair. Moreover, the segmentation operation can organize the list of images in the context of a hierarchy of rows and column reliably. The segmentation operation involves a considerable amount of summing in the binary gradient, de-skewed images, which done by construct a matrix of partial sums whose elements are given by p i y = ∑ u = 1 i ∑ v = 1 j b u v {\displaystyle p_{iy}=\sum _{u=1}^{i}\sum _{v=1}^{j}b_{uv}} The matrix of partial sums is calculated in one pass through the binary gradient, de-skewed image. ∑ u = u 1 u 2 ∑ v = v 1 v 2 b u v = p u 2 v 2 + p u 1 v 1 − p u 1 v 2 − p u 2 v 1 {\displaystyle \sum _{u=u_{1}}^{u_{2}}\sum _{v=v_{1}}^{v_{2}}b_{uv}=p_{u_{2}v_{2}}+p_{u_{1}v_{1}}-p_{u_{1}v_{2}}-p_{u_{2}v_{1}}} == Correspondences establishing == The two images are now organized in hierarchy of linked lists in following structure : image=list of columns row=list of words column=list of row word=length (in pixels) At the bottom of the structure, the length of each word is recorded for establishing correspondence between two images to reduce to search only the corresponding structures for the groups of words with the matching lengths. === Seed match finding === A seed match finding is done by comparing each row in image1 with each row in image2. The two rows are then compared to each other by every word. If the length (in pixel) of the two words (one from image1 and one from image2) and their immediate neighbours agree with each other within a predefined tolerance threshold (5 pixels, for example), then they are assumed to match. The row of each image is assumed a match if there are three or more word matches between the two rows. The seed match finding operation is terminated when two pairs of consecutive row match are found. === Match list building === After finishing a seed match finding operation, the next process is to build the match list to generate the correspondences points of the two images. The process is done by searching the matching pairs of rows away from the seed row. == Images mosaicing == Given the list of corresponding points of the two images, finding the transformation of the overlapping portion of the images is the next process. Assuming a pinhole camera model, the transformation between pixels (u,v) of image 1 and pixels (u0, v0) of image 2 is demonstrated by a plane-to-plane projectivity. [ s u ′ s v ′ s ] = [ p 11 p 12 p 13 p 21 p 22 p 23 p 31 p 32 1 ] [ u v 1 ] E q .1 {\displaystyle \left[{\begin{array}{c}su'\\sv'\\s\end{array}}\right]=\left[{\begin{array}{ccc}p_{11}&p_{12}&p_{13}\\p_{21}&p_{22}&p_{23}\\p_{31}&p_{32}&1\end{array}}\right]\left[{\begin{array}{c}u\\v\\1\end{array}}\right]\qquad Eq.1} The parameters of the projectivity is found from four pairs of matching points. RANSAC regression technique is used to reject outlying matches and estimate the projectivity from the remaining good matches. The projectivity is fine-tuned using correlation at the corners of the overlapping portion to obtain four correspondences to sub-pixel accuracy. Therefore, image1 is then transformed into image2's coordinate system using Eq.1. The typical result of the process is shown in Figure 5. === Many images coping === Finally, the whole page composition is built up by mapping all the images into the coordinate system of an "anchor" image, which is normally the one nearest the page center. The transformations to the anchor frame are calculated by concatenating the pair-wise transformations found earlier. The raw document mosaic is shown in Figure 6. However, there might be a problem of non-consecutive images that are overlap. This problem can be solved by performing Hierarchical sub-mosaics. As shown in Figure 7, image1 and image2 are registered, as are image3 and image4, creating two sub-mosaics. These two sub-mosaics are later stitched together in another mosaicing process. == Applied areas == There are various areas that the technique of document mosaicing can be applied to such as : Text segmentation of images of documents Document Recognition Interaction with paper on the digital desk Video mosaics for virtual environments Image registration techniques == Relevant research papers == Huang, T.S.; Netravali, A.N. (1994). "Motion and structure from feature correspondences: A review". Proceedings of the IEEE. 82 (2): 252–268. doi:10.1109/5.265351. D.G. Lowe. [1] Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, Boston, 1985. Irani, M.; Peleg, S. (1991). "Improving resolution by image registration". CVGIP: Graphical Models and Image Processing. 53 (3): 231–239. doi:10.1016/1049-9652(91)90045-L. S2CID 4834546. Shivakumara, P.; Kumar, G. Hemantha; Guru, D. S.; Nagabhushan, P. (2006). "
Read more →
Egocentric vision

Egocentric vision or first-person vision is a sub-field of computer vision that entails analyzing images and videos captured by a wearable camera, which is typically worn on the head or on the chest and naturally approximates the visual field of the camera wearer. Consequently, visual data capture the part of the scene on which the user focuses to carry out the task at hand and offer a valuable perspective to understand the user's activities and their context in a naturalistic setting. The wearable camera looking forwards is often supplemented with a camera looking inward at the user's eye and able to measure a user's eye gaze, which is useful to reveal attention and to better understand the user's activity and intentions. == History == The idea of using a wearable camera to gather visual data from a first-person perspective dates back to the 70s, when Steve Mann invented "Digital Eye Glass", a device that, when worn, causes the human eye itself to effectively become both an electronic camera and a television display. Subsequently, wearable cameras were used for health-related applications in the context of Humanistic Intelligence and Wearable AI. Egocentric vision is best done from the point-of-eye, but may also be done by way of a neck-worn camera when eyeglasses would be in-the-way. This neck-worn variant was popularized by way of the Microsoft SenseCam in 2006 for experimental health research works. The interest of the computer vision community into the egocentric paradigm has been arising slowly entering the 2010s and it is rapidly growing in recent years, boosted by both the impressive advances in the field of wearable technology and by the increasing number of potential applications. The prototypical first-person vision system described by Kanade and Hebert, in 2012 is composed by three basic components: a localization component able to estimate the surrounding, a recognition component able to identify object and people, and an activity recognition component, able to provide information about the current activity of the user. Together, these three components provide a complete situational awareness of the user, which in turn can be used to provide assistance to the user or to the caregiver. Following this idea, the first computational techniques for egocentric analysis focused on hand-related activity recognition and social interaction analysis. Also, given the unconstrained nature of the video and the huge amount of data generated, temporal segmentation and summarization were among the first problems addressed. After almost ten years of egocentric vision (2007–2017), the field is still undergoing diversification. Emerging research topics include: Social saliency estimation Multi-agent egocentric vision systems Privacy preserving techniques and applications Attention-based activity analysis Social interaction analysis Hand pose analysis Ego graphical User Interfaces (EUI) Understanding social dynamics and attention Revisiting robotic vision and machine vision as egocentric sensing Activity forecasting Gaze prediction == Technical challenges == Today's wearable cameras are small and lightweight digital recording devices that can acquire images and videos automatically, without the user intervention, with different resolutions and frame rates, and from a first-person point of view. Therefore, wearable cameras are naturally primed to gather visual information from our everyday interactions since they offer an intimate perspective of the visual field of the camera wearer. Depending on the frame rate, it is common to distinguish between photo-cameras (also called lifelogging cameras) and video-cameras. The former (e.g., Narrative Clip and Microsoft SenseCam), are commonly worn on the chest, and are characterized by a very low frame rate (up to 2fpm) that allows to capture images over a long period of time without the need of recharging the battery. Consequently, they offer considerable potential for inferring knowledge about e.g. behaviour patterns, habits or lifestyle of the user. However, due to the low frame-rate and the free motion of the camera, temporally adjacent images typically present abrupt appearance changes so that motion features cannot be reliably estimated. The latter (e.g., Google Glass, GoPro), are commonly mounted on the head, and capture conventional video (around 35fps) that allows to capture fine temporal details of interactions. Consequently, they offer potential for in-depth analysis of daily or special activities. However, since the camera is moving with the wearer head, it becomes more difficult to estimate the global motion of the wearer and in the case of abrupt movements, the images can result blurred. In both cases, since the camera is worn in a naturalistic setting, visual data present a huge variability in terms of illumination conditions and object appearance. Moreover, the camera wearer is not visible in the image and what he/she is doing has to be inferred from the information in the visual field of the camera, implying that important information about the wearer, such for instance as pose or facial expression estimation, is not available. == Applications == A collection of studies published in a special theme issue of the American Journal of Preventive Medicine has demonstrated the potential of lifelogs captured through wearable cameras from a number of viewpoints. In particular, it has been shown that used as a tool for understanding and tracking lifestyle behaviour, lifelogs would enable the prevention of noncommunicable diseases associated to unhealthy trends and risky profiles (such as obesity and depression). In addition, used as a tool of re-memory cognitive training, lifelogs would enable the prevention of cognitive and functional decline in elderly people. More recently, egocentric cameras have been used to study human and animal cognition, human-human social interaction, human-robot interaction, human expertise in complex tasks. Other applications include navigation/assistive technologies for the blind, monitoring and assistance of industrial workflows, and augmented reality interfaces.
Read more →
Auralization

Auralization is a procedure designed to model and simulate the experience of acoustic phenomena rendered as a soundfield in a virtualized space. This is useful in configuring the soundscape of architectural structures, concert venues, and public spaces, as well as in making coherent sound environments within virtual immersion systems. == History == The English term auralization was used for the first time by Kleiner et al. in an article in the journal of the AES en 1991. The increase of computational power allowed the development of the first acoustic simulation software towards the end of the 1960s. == Principles == Auralizations are experienced through systems rendering virtual acoustic models made by convolving or mixing acoustic events recorded 'dry' (or in an anechoic chamber) projected within a virtual model of an acoustic space, the characteristics of which are determined by means of sampling its impulse response (IR). Once this h ( t ) {\displaystyle h(t)} has been determined, the simulation of the resulting soundfield s ( t ) {\displaystyle s(t)} in the target environment is obtained by convolution: r ( t ) = h ( t ) ∗ s ( t ) {\displaystyle r(t)=h(t)s(t)} The resulting sound r ( t ) {\displaystyle r(t)} is heard as it would if emitted in that acoustic space. == Binaurality == For auralizations to be perceived as realistic, it is critical to emulate the human hearing in terms of position and orientation of the listener's head with respect to the sources of sound. For IR data to be convolved convincingly, the acoustic events are captured using a dummy head where two microphones are positioned on each side of the head to record an emulation of sound arriving at the locations of human ears, or using an ambisonics microphone array and mixed down for binaurality. Head-related transfer functions (HRTF) datasets can be used to simplify the process insofar as a monaural IR can be measured or simulated, then audio content is convolved with its target acoustic space. In rendering the experience, the transfer function corresponding to the orientation of the head is applied to simulate the corresponding spatial emanation of sound.
Read more →
Logic form

Logic forms are simple, first-order logic knowledge representations of natural language sentences formed by the conjunction of concept predicates related through shared arguments. Each noun, verb, adjective, adverb, pronoun, preposition and conjunction generates a predicate. Logic forms can be decorated with word senses to disambiguate the semantics of the word. There are two types of predicates: events are marked with e, and entities are marked with x. The shared arguments connect the subjects and objects of verbs and prepositions together. Example input/output might look like this: Input: The Earth provides the food we eat every day. Output: Earth:n_#1(x1) provide:v_#2(e1, x1, x2) food:n_#1(x2) we(x3) eat:v_#1(e2, x3, x2; x4) day:n_#1(x4) Logic forms are used in some natural language processing techniques, such as question answering, as well as in inference both for database systems and QA systems.
Read more →