Digital image correlation and tracking

Digital image correlation and tracking is an optical method that employs tracking and image registration techniques for accurate 2D and 3D measurements of changes in 2D images or 3D volumes. This method is often used to measure full-field displacement and strains, and it is widely applied in many areas of science and engineering. Compared to strain gauges and extensometers, digital image correlation methods provide finer details about deformation, due to the ability to provide both local and average data. == Overview == Digital image correlation (DIC) techniques have been increasing in popularity, especially in micro- and nano-scale mechanical testing applications due to their relative ease of implementation and use. Advances in computer technology and digital cameras have been the enabling technologies for this method and while white-light optics has been the predominant approach, DIC can be and has been extended to almost any imaging technology. The concept of using cross-correlation to measure shifts in datasets has been known for a long time, and it has been applied to digital images since at least the early 1970s. The present-day applications are almost innumerable, including image analysis, image compression, velocimetry, and strain estimation. Much early work in DIC in the field of mechanics was led by researchers at the University of South Carolina in the early 1980s and has been optimized and improved in recent years. Commonly, DIC relies on finding the maximum of the correlation array between pixel intensity array subsets on two or more corresponding images, which gives the integer translational shift between them. It is also possible to estimate shifts to a finer resolution than the resolution of the original images, which is often called "sub-pixel" registration because the measured shift is smaller than an integer pixel unit. For sub-pixel interpolation of the shift, other methods do not simply maximize the correlation coefficient. An iterative approach can also be used to maximize the interpolated correlation coefficient by using non-linear optimization techniques. The non-linear optimization approach tends to be conceptually simpler and can handle large deformations more accurately, but as with most nonlinear optimization techniques, it is slower. The two-dimensional discrete cross correlation r i j {\displaystyle r_{ij}} can be defined in several ways, one possibility being: r i j = ∑ m ∑ n [ f ( m + i , n + j ) − f ¯ ] [ g ( m , n ) − g ¯ ] ∑ m ∑ n [ f ( m , n ) − f ¯ ] 2 ∑ m ∑ n [ g ( m , n ) − g ¯ ] 2 . {\displaystyle r_{ij}={\frac {\sum _{m}\sum _{n}[f(m+i,n+j)-{\bar {f}}][g(m,n)-{\bar {g}}]}{\sqrt {\sum _{m}\sum _{n}{[f(m,n)-{\bar {f}}]^{2}}\sum _{m}\sum _{n}{[g(m,n)-{\bar {g}}]^{2}}}}}.} Here f(m, n) is the pixel intensity or the gray-scale value at a point (m, n) in the original image, g(m, n) is the gray-scale value at a point (m, n) in the translated image, f ¯ {\displaystyle {\bar {f}}} and g ¯ {\displaystyle {\bar {g}}} are mean values of the intensity matrices f and g respectively. However, in practical applications, the correlation array is usually computed using Fourier-transform methods, since the fast Fourier transform is a much faster method than directly computing the correlation. F = F { f } , G = F { g } . {\displaystyle \mathbf {F} ={\mathcal {F}}\{f\},\quad \mathbf {G} ={\mathcal {F}}\{g\}.} Then taking the complex conjugate of the second result and multiplying the Fourier transforms together elementwise, we obtain the Fourier transform of the correlogram, R {\displaystyle \ R} : R = F ∘ G ∗ , {\displaystyle R=\mathbf {F} \circ \mathbf {G} ^{},} where ∘ {\displaystyle \circ } is the Hadamard product (entry-wise product). It is also fairly common to normalize the magnitudes to unity at this point, which results in a variation called phase correlation. Then the cross-correlation is obtained by applying the inverse Fourier transform: r = F − 1 { R } . {\displaystyle \ r={\mathcal {F}}^{-1}\{R\}.} At this point, the coordinates of the maximum of r i j {\displaystyle r_{ij}} give the integer shift: ( Δ x , Δ y ) = arg ⁡ max ( i , j ) { r } . {\displaystyle (\Delta x,\Delta y)=\arg \max _{(i,j)}\{r\}.} == Deformation mapping == For deformation mapping, the mapping function that relates the images can be derived from comparing a set of subwindow pairs over the whole images. (Figure 1). The coordinates or grid points (xi, yj) and (xi, yj) are related by the translations that occur between the two images. If the deformation is small and perpendicular to the optical axis of the camera, then the relation between (xi, yj) and (xi, yj) can be approximated by a 2D affine transformation such as: x ∗ = x + u + ∂ u ∂ x Δ x + ∂ u ∂ y Δ y , {\displaystyle x^{}=x+u+{\frac {\partial u}{\partial x}}\Delta x+{\frac {\partial u}{\partial y}}\Delta y,} y ∗ = y + v + ∂ v ∂ x Δ x + ∂ v ∂ y Δ y . {\displaystyle y^{}=y+v+{\frac {\partial v}{\partial x}}\Delta x+{\frac {\partial v}{\partial y}}\Delta y.} Here u and v are translations of the center of the sub-image in the X and Y directions respectively. The distances from the center of the sub-image to the point (x, y) are denoted by Δ x {\displaystyle \Delta x} and Δ y {\displaystyle \Delta y} . Thus, the correlation coefficient rij is a function of displacement components (u, v) and displacement gradients ∂ u ∂ x , ∂ u ∂ y , ∂ v ∂ x , ∂ v ∂ y . {\displaystyle {\frac {\partial u}{\partial x}},{\frac {\partial u}{\partial y}},{\frac {\partial v}{\partial x}},{\frac {\partial v}{\partial y}}.} DIC has proven to be very effective at mapping deformation in macroscopic mechanical testing, where the application of specular markers (e.g. paint, toner powder) or surface finishes from machining and polishing provide the needed contrast to correlate images well. However, these methods for applying surface contrast do not extend to the application of free-standing thin films for several reasons. First, vapor deposition at normal temperatures on semiconductor grade substrates results in mirror-finish quality films with RMS roughnesses that are typically on the order of several nanometers. No subsequent polishing or finishing steps are required, and unless electron imaging techniques are employed that can resolve microstructural features, the films do not possess enough useful surface contrast to adequately correlate images. Typically this challenge can be circumvented by applying paint that results in a random speckle pattern on the surface, although the large and turbulent forces resulting from either spraying or applying paint to the surface of a free-standing thin film are too high and would break the specimens. In addition, the sizes of individual paint particles are on the order of μms, while the film thickness is only several hundred nanometers, which would be analogous to supporting a large boulder on a thin sheet of paper. == Digital volume correlation == Digital Volume Correlation (DVC, and sometimes called Volumetric-DIC) extends the 2D-DIC algorithms into three dimensions to calculate the full-field 3D deformation from a pair of 3D images. This technique is distinct from 3D-DIC, which only calculates the 3D deformation of an exterior surface using conventional optical images. The DVC algorithm is able to track full-field displacement information in the form of voxels instead of pixels. The theory is similar to above except that another dimension is added: the z-dimension. The displacement is calculated from the correlation of 3D subsets of the reference and deformed volumetric images, which is analogous to the correlation of 2D subsets described above. DVC can be performed using volumetric image datasets. These images can be obtained using confocal microscopy, X-ray computed tomography, Magnetic Resonance Imaging or other techniques. Similar to the other DIC techniques, the images must exhibit a distinct, high-contrast 3D "speckle pattern" to ensure accurate displacement measurement. DVC was first developed in 1999 to study the deformation of trabecular bone using X-ray computed tomography images. Since then, applications of DVC have grown to include granular materials, metals, foams, composites and biological materials. To date it has been used with images acquired by MRI imaging, Computer Tomography (CT), micro-CT, confocal microscopy, and lightsheet microscopy. DVC is currently considered to be ideal in the research world for 3D quantification of local displacements, strains, and stress in biological specimens. It is preferred because of the non-invasiveness of the method over traditional experimental methods. Two of the key challenges are improving the speed and reliability of the DVC measurement. The 3D imaging techniques produce noisier images than conventional 2D optical images, which reduces the quality of the displacement measurement. Computational speed is restricted by the file sizes of 3D images, which are significantly larger than 2D images. For example, an

Contextual AI

Contextual AI is an enterprise software company based in Mountain View, California. It develops a platform for building specialized Retrieval-Augmented Generation (RAG) agents for enterprise use. The company was founded in 2023 by Douwe Kiela and Amanpreet Singh, both former AI researchers at Facebook AI Research (FAIR) and Hugging Face. Douwe Kiela previously led the Meta research team that introduced the Retrieval-Augmented Generation (RAG) approach in 2020. Contextual AI focuses on enterprise generative AI applications using RAG 2.0 technology, with deployments primarily in the technology, banking, finance and media sectors. == History == In June 2023, Contextual AI announced it had raised $20 million in a seed funding round led by Bain Capital Ventures (BCV), with participation from Lightspeed Venture Partners, Greycroft, SV Angel, and several angel investors. In August 2024, the company raised $80 million in a Series A funding round led by Greycroft, with participation from previous investors including Bain Capital Ventures, Lightspeed, and Conviction Partners. The round also included new backers such as Bezos Expeditions, NVentures (Nvidia), HSBC Ventures, and Snowflake Ventures. == Features == Retrieval-Augmented Generation (RAG) is an artificial intelligence framework that integrates information retrieval with text generation to improve the performance of large language models (LLMs) on complex, knowledge-intensive tasks. It was introduced in 2020 by researchers at Meta AI, including Douwe Kiela, Patrick Lewis and others, in their paper Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. RAG enables language models to access and incorporate external information, such as proprietary databases or real-time web content, at query time, instead of relying solely on pre-trained, internal, static knowledge. This architecture addresses common limitations of standard LLMs, including hallucination, outdated information, and lack of attribution to source materials. RAG systems retrieve relevant context through a variety of techniques - including vector search, keyword search, text-to-SQL - and feeds this context into the language model to generate responses. The approach improves factual accuracy, supports domain-specific customization, enables citation of sources, and allows for more updated information without retraining the model itself. General Availability. In January 2025, Contextual AI announced the general availability of its enterprise platform for building specialized RAG agents. Early adopters included Qualcomm, which used the platform for their Customer Engineering team needs. Grounded Language Model. In March 2025, the company introduced a Grounded Language Model (GLM) for factual accuracy in enterprise AI applications. Reranker. In March 2025, Contextual AI released an instruction-following reranker that allows users to influence the ranking of retrieved documents through natural language instructions, such as prioritizing recent files, specific formats, or content from designated sources. == Applications == Contextual AI's platform has been adopted across a range of industries, including finance, technology, media and professional services. Clients include Fortune 500 companies such as Qualcomm and HSBC.

International Conference on Language Resources and Evaluation

The International Conference on Language Resources and Evaluation is an international conference organised by the ELRA Language Resources Association every other year (on even years) with the support of institutions and organisations involved in Natural language processing. The series of LREC conferences was launched in Granada in 1998. == History of conferences == The survey of the LREC conferences over the period 1998-2013 was presented during the 2014 conference in Reykjavik as a closing session. It appears that the number of papers and signatures is increasing over time. The average number of authors per paper is higher as well. The percentage of new authors is between 68% and 78%. The distribution between male (65%) and female (35%) authors is stable over time. The most frequent technical term is "annotation", then comes "part-of-speech". == The LRE Map == The LRE Map was introduced at LREC 2010 and is now a regular feature of the LREC submission process for both the conference papers and the workshop papers. At the submission stage, the authors are asked to provide some basic information about all the resources (in a broad sense, i.e. including tools, standards and evaluation packages), either used or created, described in their papers. All these descriptors are then gathered in a global matrix called the LRE Map. This feature has been extended to several other conferences.

Text-to-image personalization

Text-to-Image personalization is a task in deep learning for computer graphics that augments pre-trained text-to-image generative models. In this task, a generative model that was trained on large-scale data (usually a foundation model), is adapted such that it can generate images of novel, user-provided concepts. These concepts are typically unseen during training, and may represent specific objects (such as the user's pet) or more abstract categories (new artistic style or object relations). Text-to-Image personalization methods typically bind the novel (personal) concept to new words in the vocabulary of the model. These words can then be used in future prompts to invoke the concept for subject-driven generation, inpainting, style transfer and even to correct biases in the model. To do so, models either optimize word-embeddings, fine-tune the generative model itself, or employ a mixture of both approaches. == Technology == Text-to-Image personalization was first proposed during August 2022 by two concurrent works, Textual Inversion and DreamBooth. In both cases, a user provides a few images (typically 3–5) of a concept, like their own dog, together with a coarse descriptor of the concept class (like the word "dog"). The model then learns to represent the subject through a reconstruction based objective, where prompts referring to the subject are expected to reconstruct images from the training set. In Textual Inversion, the personalized concepts are introduced into the text-to-image model by adding new words to the vocabulary of the model. Typical text-to-image models represent words (and sometimes parts-of-words) as tokens, or indices in a predefined dictionary. During generation, an input prompt is converted into such tokens, each of which is converted into a ‘word-embedding’: a continuous vector representation which is learned for each token as part of the model's training. Textual Inversion proposes to optimize a new word-embedding vector for representing the novel concept. This new embedding vector can then be assigned to a user-chosen string, and invoked whenever the user's prompt contains this string. In DreamBooth, rather than optimizing a new word vector, the full generative model itself is fine-tuned. The user first selects an existing token, typically one which rarely appears in prompts. The subject itself is then represented by a string containing this token, followed by a coarse descriptor of the subject's class. A prompt describing the subject will then take the form: "A photo of " (e.g. "a photo of sks cat" when learning to represent a specific cat). The text-to-image model is then tuned so that prompts of this form will generate images of the subject. == Textual Inversion == The key idea in Textual Inversion is to add a new term to the vocabulary of the diffusion model that corresponds to the new (personalized) concept. Textual Inversion operates by inverting the concepts into new pseudo-words within the textual embedding space of a pre-trained text-to-image model. These pseudo-words can be injected into new scenes using simple natural language descriptions, allowing for simple and intuitive modifications. The method allows a user to leverage multi-modal information — using a text-driven interface for ease of editing, but providing visual cues when approaching the limits of natural language. The resulting model is extremely light-weight per concept: only 1K long, but succeeds to encode detailed visual properties of the concept. == Extensions == Several approaches were proposed to refine and improve over the original methods. These include the following. Low-rank Adaptation (LoRA) - an adapter-based technique for efficient finetuning of models. In the case of text-to-image models, LoRA is typically used to modify the cross-attention layers of a diffusion model. Perfusion - a low rank update method that also locks the activations of the key matrix in the diffusion model's cross attention layers to the concept's coarse class. Extended Textual Inversion - a technique that learns an individual word embedding for each layer in the diffusion model's denoising network. Encoder-based methods that use another neural network to quickly personalize a model == Challenges and limitations == Text-to-image personalization methods must contend with several challenges. At their core is the goal of achieving high-fidelity to the personal concept while maintaining high alignment between novel prompts containing the subject, and the generated images (typically referred to as ‘editability’). Another challenge that personalization methods must contend with is memory requirements. Initial implementations of personalization methods required more than 20 Gigabytes of GPU memory, and more recent approaches have reported requirements of more than 40 Gigabytes. However, optimizations such as Flash Attention have since reduced this requirement considerably. Approaches that tune the entire generative model may also create checkpoints that are several gigabytes in size, making it difficult to share or store many models. Embedding based approaches require only a few kilobytes, but typically struggle to preserve identity while maintaining editability. More recent approaches have proposed hybrid tuning goals which optimize both an embedding and a subset of network weights. These can reduce storage requirements to as little as 100 Kilobytes while achieving quality comparable to full tuning methods. Finally, optimization processes can be lengthy, requiring several minutes of tuning for each novel concept. Encoder and quick-tuning methods aim to reduce this to seconds or less.

Application performance engineering

Application performance engineering is a method to develop and test application performance in various settings, including mobile computing, the cloud, and conventional information technology (IT). == Methodology == According to the American National Institute of Standards and Technology, nearly four out of every five dollars spent on the total cost of ownership of an application is directly attributable to finding and fixing issues post-deployment. A full one-third of this cost could be avoided with better software testing. Application performance engineering attempts to test software before it is published. While practices vary among organizations, the method attempts to emulate the real-world conditions that software in development will confront, including network deployment and access by mobile devices. Techniques include network virtualization.

Avid Symphony

Avid Symphony is non-linear editing software aimed at professionals in the film and television industry. It is available for Microsoft Windows PCs and Apple Macintosh platforms. Symphony is Avid's high end SD/HD finishing platform for long form work, such as documentary and episodic TV. Its interface is based on the same look and feature set as the Media Composer and Xpress systems, but contains the highest level of features and resolution including secondary color correction, uncompressed HD, and higher real-time performance. == Release history == Symphony is the software component of a tightly integrated package that includes specific hardware audio/video interfaces, storage, and the computer, also sold by Avid. Its release history is therefore tightly related to the release of new Avid interface hardware: Symphony was introduced to the market in 1998. It was based on Avid's Meridien hardware, supporting SD only, and was available first only for the PC and later for the Macintosh platforms. Its last release was 5.0.5 which supported Windows 2000 and Mac OS X v10.2. The next major upgrade was Symphony Nitris in 2005, with a redesigned software and integration with the Nitris DNA hardware (PCI-X). It supported 8 bit and 10 bit SD and HD resolutions in both compressed and uncompressed forms, the MXF format and DNxHD codec, and ran only on Windows PC platforms. Symphony Nitris DX, released in 2008, added support for a range of HD codecs, including HDV, XDCAM-HD, DVCPRO HD, and AVC-I, and brought back Mac OS support for OS X 10.5, as well as Windows Vista. Since the introduction of Symphony 6, it can be used in software-only mode (where a Nitris or Nitris DX BOB used to be required), and at the same time, like Media Composer, Symphony was opened up with "Open I/O", allowing users to have Symphony use their third party hardware from companies like AJA, Matrox, BlueFish, Blackmagic Design and MOTU. The last remaining features that differentiate it from Media Composer are Advanced Color Correction (channels, secondary color correction,), Relational Color Correction (corrections based on common clip name, tape name, program track) and Universal HD Mastering (only with Nitris DX hardware). The latter allows cross-conversions of 23.976p or 24p projects sequences to most any other format during Digital Cut. In 2013, Avid announced it would no longer offer Symphony a standalone product. Starting version 7, Symphony will be sold as an option to Media Composer. This optional package (sold at a premium) will contain all the traditional Symphony-only features to any Media Composer install. == Use in movies == The Celibacy, Director: Horacio Bocaranda Avid Media Composer 6 and Avid Symphony 6 Nitris DX American Hardcore, Director: Paul Rachman Avid Xpress Pro and Symphony Summercamp!, Director: Spike Lee Avid Xpress Pro and Symphony When the Levees Broke Avid Media Composer and Symphony Nitris Superman Returns Edited with Mac-based Film Composer XL, but HD screenings prepped with Symphony

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.