In computer vision, a saliency map is an image that highlights either the region on which people's eyes focus first or the most relevant regions for machine learning models. The goal of a saliency map is to reflect the degree of importance of a pixel to the human visual system or an otherwise opaque ML model. For example, in this image, a person first looks at the fort and light clouds, so they should be highlighted on the saliency map. == Application == === Overview === Saliency maps have applications in a variety of different problems. Some general applications: ==== Human eye ==== Image and video compression: The human eye focuses only on a small region of interest in the frame. Therefore, it is not necessary to compress the entire frame with uniform quality. According to the authors, using a salience map reduces the final size of the video with the same visual perception. Image and video quality assessment: The main task for an image or video quality metric is a high correlation with user opinions. Differences in salient regions are given more importance and thus contribute more to the quality score. Image retargeting: It aims at resizing an image by expanding or shrinking the noninformative regions. Therefore, retargeting algorithms rely on the availability of saliency maps that accurately estimate all the salient image details. Object detection and recognition: Instead of applying a computationally complex algorithm to the whole image, we can use it to the most salient regions of an image most likely to contain an object. the primary visual cortex (V1) appears to be responsible for the saliency map, according to the V1 Saliency Hypothesis. ==== Explainable artificial intelligence ==== Saliency maps are a prominent tool in explainable artificial intelligence, providing visual explanations of the decision-making process of machine learning models, particularly deep neural networks. These maps highlight the regions in input data that are most influential on the model's output, effectively indicating where the model is "looking" when making a prediction. In image classification tasks, for example, saliency maps can identify pixels or regions that contribute most to a specific class decision. Developed for convolutional neural networks, saliency mapping techniques range from simply taking the gradient of the class score with respect to the input data to more complex algorithms, such as integrated gradients and class activation mapping. In transformer architecture, attention mechanisms led to analogous saliency maps, such as attention maps, attention rollouts, and class-discriminative attention maps. === Saliency as a segmentation problem === Saliency estimation may be viewed as an instance of image segmentation. In computer vision, image segmentation is the process of partitioning a digital image into multiple segments (sets of pixels, also known as superpixels). The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics. == Algorithms == === Overview === There are three forms of classic saliency estimation algorithms implemented in OpenCV: Static saliency: Relies on image features and statistics to localize the regions of interest of an image. Motion saliency: Relies on motion in a video, detected by optical flow. Objects that move are considered salient. Objectness: Objectness reflects how likely an image window covers an object. These algorithms generate a set of bounding boxes of where an object may lie in an image. In addition to classic approaches, neural-network-based are also popular. There are examples of neural networks for motion saliency estimation: TASED-Net: It consists of two building blocks. First, the encoder network extracts low-resolution spatiotemporal features, and then the following prediction network decodes the spatially encoded features while aggregating all the temporal information. STRA-Net: It emphasizes two essential issues. First, spatiotemporal features integrated via appearance and optical flow coupling, and then multi-scale saliency learned via attention mechanism. STAViS: It combines spatiotemporal visual and auditory information. This approach employs a single network that learns to localize sound sources and to fuse the two saliencies to obtain a final saliency map. There's a new static saliency in the literature with name visual distortion sensitivity. It is based on the idea that the true edges, i.e. object contours, are more salient than the other complex textured regions. It detects edges in a different way from the classic edge detection algorithms. It uses a fairly small threshold for the gradient magnitudes to consider the mere presence of the gradients. So, it obtains 4 binary maps for vertical, horizontal and two diagonal directions. The morphological closing and opening are applied to the binary images to close the small gaps. To clear the blob-like shapes, it utilizes the distance transform. After all, the connected pixel groups are individual edges (or contours). A threshold of size of connected pixel set is used to determine whether an image block contains a perceivable edge (salient region) or not. === Example implementation === First, we should calculate the distance of each pixel to the rest of pixels in the same frame: S A L S ( I k ) = ∑ i = 1 N | I k − I i | {\displaystyle \mathrm {SALS} (I_{k})=\sum _{i=1}^{N}|I_{k}-I_{i}|} I i {\displaystyle I_{i}} is the value of pixel i {\displaystyle i} , in the range of [0,255]. The following equation is the expanded form of this equation. SALS(Ik) = |Ik - I1| + |Ik - I2| + ... + |Ik - IN| Where N is the total number of pixels in the current frame. Then we can further restructure our formula. We put the value that has same I together. SALS(Ik) = Σ Fn × |Ik - In| Where Fn is the frequency of In. And the value of n belongs to [0,255]. The frequencies is expressed in the form of histogram, and the computational time of histogram is O ( N ) {\displaystyle O(N)} time complexity. ==== Time complexity ==== This saliency map algorithm has O ( N ) {\displaystyle O(N)} time complexity. Since the computational time of histogram is O ( N ) {\displaystyle O(N)} time complexity which N is the number of pixel's number of a frame. Besides, the minus part and multiply part of this equation need 256 times operation. Consequently, the time complexity of this algorithm is O ( N + 256 ) {\displaystyle O(N+256)} which equals to O ( N ) {\displaystyle O(N)} . ==== Pseudocode ==== All of the following code is pseudo MATLAB code. First, read data from video sequences. After we read data, we do superpixel process to each frame. Spnum1 and Spnum2 represent the pixel number of current frame and previous pixel. Then we calculate the color distance of each pixel, this process we call it contract function. After this two process, we will get a saliency map, and then store all of these maps into a new FileFolder. ==== Difference in algorithms ==== The major difference between function one and two is the difference of contract function. If spnum1 and spnum2 both represent the current frame's pixel number, then this contract function is for the first saliency function. If spnum1 is the current frame's pixel number and spnum2 represent the previous frame's pixel number, then this contract function is for second saliency function. If we use the second contract function which using the pixel of the same frame to get center distance to get a saliency map, then we apply this saliency function to each frame and use current frame's saliency map minus previous frame's saliency map to get a new image which is the new saliency result of the third saliency function. == Datasets == The saliency dataset usually contains human eye movements on some image sequences. It is valuable for new saliency algorithm creation or benchmarking the existing one. The most valuable dataset parameters are spatial resolution, size, and eye-tracking equipment. Here is part of the large datasets table from MIT/Tübingen Saliency Benchmark datasets, for example. To collect a saliency dataset, image or video sequences and eye-tracking equipment must be prepared, and observers must be invited. Observers must have normal or corrected to normal vision and must be at the same distance from the screen. At the beginning of each recording session, the eye-tracker recalibrates. To do this, the observer fixates their gaze on the screen center. The session is then started, and saliency data are collected by showing sequences and recording eye gazes. The eye-tracking device is a high-speed camera, capable of recording eye movements at least 250 fr
Operational image
An operational image, also known as operative image, is an image that serves a functional, rather than aesthetic, purpose. Operational images are not intended to be viewed by people as representations of the real world; they are created to be used as instruments in performing some task or operation, often by machine automation. Operational images are used in a wide variety of applications, such as weapons targeting and guidance systems, and assisting surgeons performing robot-assisted surgery. The term "operational image" was first coined in 2000 by German filmmaker Harun Farocki in the first part of his three-part audiovisual installation, Eye/Machine. Farocki's installation included operational images used by militaries, such as weapons guidance and targeting systems. Eye/Machine featured images shown to the public by the United States military from the cameras used by laser-guided missiles in the Gulf War. Farocki defined operational images as "Images without a social goal, not for edification, not for reflection," and that they "do not represent an object, but rather are part of an operation." According to Volker Pantenburg, operational images are more accurately characterized as "visualizations of data". He describes operational images as a "working image" or an image that "performs work". Operational images are ubiquitous in modern society, used for a variety of military and non-military applications, such as inspecting sewer piping, and assisting surgeons performing robotic surgery.
IJCAI Award for Research Excellence
The IJCAI Award for Research Excellence is a biannual award before given at the IJCAI conference to researcher in artificial intelligence as a recognition of excellence of their career. Beginning in 2016, the conference is held annually and so is the award. == Laureates == The recipients of this award have been: John McCarthy (1985) Allen Newell (1989) Marvin Minsky (1991) Raymond Reiter (1993) Herbert A. Simon (1995) Aravind Joshi (1997) Judea Pearl (1999) Donald Michie (2001) Nils Nilsson (2003) Geoffrey E. Hinton (2005) Alan Bundy (2007) Victor R. Lesser (2009) Robert Kowalski (2011) Hector Levesque (2013) Barbara Grosz (2015) for her pioneering research in Natural Language Processing and in theories and applications of Multiagent Collaboration. Michael I. Jordan (2016) for his groundbreaking and impactful research in both the theory and application of statistical machine learning. Andrew Barto (2017) for his pioneering work in the theory of reinforcement learning. Jitendra Malik (2018) Yoav Shoham (2019) Eugene Freuder (2020) Richard S. Sutton (2021) Stuart J. Russell (2022) Sarit Kraus (2023) for her pioneering work of the study of interactions among self-interested agents, creating the field of automated negotiation, and developing methods for coalition formation and teamwork, both as formal models and real-world implementations. == Winners of also Turing Award == John McCarthy (1971) Allen Newell (1975) Marvin Minsky (1969) Herbert A. Simon (1975) Judea Pearl (2011) Geoffrey Hinton (2018) Andrew Barto (2024) Richard S. Sutton (2024)
Flux (text-to-image model)
Flux (also known as FLUX.1 and FLUX.2) is a text-to-image model developed by Black Forest Labs (BFL), based in Freiburg im Breisgau, Germany. Black Forest Labs was founded by former employees of Stability AI. As with other text-to-image models, Flux generates images from natural language descriptions, called prompts. == History == Black Forest Labs (BFL) was founded in 2024 by Robin Rombach, Andreas Blattmann, and Patrick Esser, former employees of Stability AI. All three founders had previously researched the artificial intelligence image generation at LMU Munich as research assistants under Björn Ommer. They published their research results on image generation in 2022, which resulted in creation of Stable Diffusion. Investors in BFL included venture capital firm Andreessen Horowitz, Brendan Iribe, Michael Ovitz, Garry Tan, and Vladlen Koltun. The company received an initial investment of US$31 million. In August 2024, Flux was integrated into the Grok chatbot developed by xAI and made available as part of premium feature on X (formerly Twitter). Grok later switched to its own text-to-image model Aurora in December 2024. On 18 November 2024, Mistral AI announced that its Le Chat chatbot had integrated Flux Pro as its image generation model. On 21 November 2024, BFL announced the release of Flux.1 Tools, a suite of editing tools designed to be used on top of existing Flux models. The tools consisting of Flux.1 Fill for inpainting and outpainting, Flux.1 Depth for control based on extracted depth map of input images and prompts, Flux.1 Canny for control based on extracted canny edges of input images and prompts, and Flux.1 Redux for mixing existing input images and prompts. Each tools are available in both Pro and Dev models. In January 2025, BFL announced a partnership with Nvidia for inclusion of Flux models as foundation models for Nvidia's Blackwell microarchitecture. The company also announced the release of Flux Pro Finetuning API, designed for customisation and fine-tuning of Flux-generated images and a partnership with German media company Hubert Burda Media for usage of Flux Pro as part of content creation. On 29 May 2025, BFL announced Flux.1 Kontext, a suite of models that enable in-context image generation and editing, allowing users to prompt with both text and images. Alongside this, BFL Playground, an interface for testing Flux models was released. On 31 July 2025, BFL announced Flux.1 Krea Dev, a model developed in collaboration with Krea AI that trained to achieve better performance, more varied aesthetics, and better realism compared to existing text-to-image models. In September 2025, Adobe Inc. announced that Photoshop (beta) users can use Flux.1 Kontext Pro as a model for its generative fill tool. BFL collaborated with Meta on Vibes, a video-generation app. On 25 November 2025, BFL announced the release of Flux.2 model series, consisting of Pro, Flex, Dev, and Apache 2.0-licensed Klein (meaning Little or Small in German language) models along with Flux.2 variational autoencoder which also released as open-source software under Apache 2.0 licence. This series claimed improvements for image reference, photorealism, typography, and prompt understanding. == Models == Flux is a series of text-to-image models. The models are based on rectified flow transformer blocks scaled to 12 billion parameters. Flux.1 models were released under different licences with Schnell (meaning Fast or Quick in German language) released as open-source software under Apache License, Dev released as source-available software under a non-commercial licence (users can obtain a self-serving commercial licence for Dev from BFL), and Pro released as proprietary software and only available as API that can be licensed by third-party users. Users retained the ownership of resulting output regardless of models used. An improved flagship model, Flux 1.1 Pro was released on 2 October 2024. Two additional modes were added on 6 November, Ultra which can generate image at four times higher resolution and up to 4 megapixel without affecting generation speed and Raw which can generate hyper-realistic image in the style of candid photography. Flux.1 Kontext is a series with in-context image generation and editing capabilities. It is available in Max, Pro, and Dev models. Max is the highest quality model and can be used to iteratively modify an existing image by using prompt while Pro is optimized to balance quality and speed of generation. Dev is an open-weight model released under non-commercial license, same as Flux.1 Dev. Flux.2 models are based on latent flow matching architecture with Mistral AI's Mistral-3 model (24 billion parameters) for its vision-language model. As with Flux.1, Flux.2 models were also released under different licences with Klein released as open-source software under Apache License, Dev released as source-available software under a non-commercial licence (users can obtain a self-serving commercial licence from BFL), and both Flex and Pro released as proprietary software and only available as API. The models can be used either online or locally by using generative AI user interfaces such as ComfyUI, Recraft Studio and Stable Diffusion WebUI Forge (a fork of Automatic1111 WebUI). Related to Flux is a text-to-video model by Black Forest Labs, under development as of February 2026. == Reception == According to a test performed by Ars Technica, the outputs generated by Flux.1 Dev and Flux.1 Pro are comparable with DALL-E 3 in terms of prompt fidelity, with the photorealism closely matched Midjourney 6 and generated human hands with more consistency over previous models such as Stable Diffusion XL. Flux has been criticised for its very realistic generated images. According to media reports, depictions ranged from an image of Donald Trump posing with guns to disturbing scenes, which triggered discussions about ethical implications of Flux models. After the release of the model, social media platform X was flooded with Flux-generated images. Black Forest Labs has not provided exact details of the data used to train the model. Ars Technica suspected that Flux is based on a large, unauthorised collection of images scraped from the internet, a controversial practice with potential legal consequences. According to a test performed by Japanese technology news website Gigazine for Flux.1 Kontext, the model series has a good understanding of the English language and can easily transfer style of the image from photorealistic into anime-style according to prompts given by the user; however, its ability to understand Japanese is quite poor. == Availability == In addition to the official BFL Playground on its website, the Flux models are also widely available through various third-party platforms for creative and professional use. These include repositories on platforms like Hugging Face and Replicate. == Further readings == FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space (29 May 2025) FLUX.2: Analyzing and Enhancing the Latent Space of FLUX – Representation Comparison (25 November 2025)
Tip and cue
Tip and cue, sometimes referred to as tip and que, tipping and cueing, or tipping and queing, is a method for satellite imagery and reconnaissance satellites to automatically coordinate tracking of objects across different satellites in real or near real-time. This technique ensures continuous tracking of targets as they move across different regions by handing them off between satellites, sharing satellite imagery and collateral across discrete satellites. The coordination between various satellites and their complementary sensors allows for more accurate and efficient data collection. This system is particularly useful in scenarios requiring real-time monitoring and rapid response; the method significantly improves situational awareness and operational effectiveness. Tip and cue techniques involve integrating various sensor systems, each playing a specific role in the tracking process. As a target moves, it is handed off from one satellite to another, ensuring continuous monitoring. This coordination optimizes data collection and analysis, enhancing overall tracking accuracy. The real-time information gathered by these satellites is critical for decision-making in various applications, including defense and surveillance. By leveraging multiple satellites and their sensors, it provides broader coverage and more reliable tracking, and the continuous handoff between satellites ensures there are no gaps in monitoring, essential for high-stakes applications. The real-time data provided by this system allows for timely and informed decisions, improving response times and outcomes. Tip and cue methodologies are a part of geospatial intelligence, or GEOINT. Robert Cardillo, a former director of the National Geospatial-Intelligence Agency, highlighted the importance of tip and cue methods to their data collection efforts in 2015. == Historical Development == The concept of tip and cue in satellite monitoring has its origins in early military applications designed to enhance missile detection and tracking systems. During the Cold War, advancements in infrared sensing technologies laid the groundwork for more sophisticated tip and cue techniques. The integration of different sensor types, such as radar and optical sensors, in the 1990s expanded the capabilities of tip and cue systems beyond military applications. These advancements have made tip and cue techniques essential for various civilian uses, including disaster monitoring and environmental surveillance. Significant progress was made with the advent of high-speed data processing and communication technologies in the early 2000s, further refining the method. Advanced algorithms and data fusion techniques have been introduced to better integrate information from multiple sensors. Machine learning technologies now play a crucial role in improving detection and prediction capabilities, allowing for more adaptive and efficient tracking. Richmond and Brennan of Lockheed Martin, presenting to the annual technical conference of the Maui Space Surveillance Complex (formerly the Air Force Maui Optical Station (AMOS)), discussed the algorithms needed for 'tip and cue', to facilitate "multi-phenomenology data fusion." The Space Surveillance Telescope (SST) at Naval Communication Station Harold E. Holt in Australia, operated by the United States Space Force and designed by the Massachusetts Institute of Technology Lincoln Laboratory, was reported by the Defense Advanced Research Projects Agency (DARPA) to be a leader in creating and improving tip and cue techniques, from a large library of orbital object data. == Technical overview == Tip and cue systems utilize a network of at least two satellites equipped with complementary sensor technologies to track moving objects in real-time. The method involves detecting a target with a primary sensor, such as an infrared or photographic sensor, which then cues secondary sensors on the same or other satellites for more detailed monitoring. This handoff process between discrete systems ensures continuous tracking as the target moves across different areas, leveraging each systems strengths. Data collected by these systems and sensors are rapidly processed and shared among the network, enhancing situational awareness. This coordination optimizes resource usage and improves the accuracy of tracking moving objects over large areas. The primary sensors detect initial targets based on specific signatures, such as heat or movement, and then cue secondary sensors to gather more precise data. This ensures that each sensor operates within its optimal range, maintaining high tracking accuracy and reliability. The integration of various sensor types, including optical, radar, and infrared, allows the system to function effectively under different conditions and environments. Real-time data processing and communication between satellites and ground stations are crucial for timely and accurate target tracking. Satellites using tip and cue processes may use either passive or active scanning methodoloigies. These systems may also leverage both orbital and ground-based ELINT (electronic signals intelligence). == Known use cases == Tip and cue systems have been extensively utilized in military applications, particularly for missile detection and defense. These systems enable early detection of missile launches using infrared sensors, which then cue other sensors to track the missile's trajectory more accurately. In environmental monitoring, tip and cue techniques help track natural disasters such as wildfires and hurricanes by coordinating various satellite sensors for comprehensive data collection and analysis. Surveillance and reconnaissance operations also benefit from tip and cue systems, which provide continuous and precise tracking of moving objects, enhancing situational awareness. Additionally, these systems are used in maritime surveillance to monitor ship movements and detect illegal activities such as smuggling and piracy. Tip and cue systems are used in disaster management. For instance, during wildfires, infrared sensors can detect heat signatures, prompting other sensors to gather detailed imagery and data on fire spread and intensity. This coordinated approach allows for real-time monitoring and rapid response, crucial for mitigating damage and saving lives. Similarly, in hurricane tracking, satellites equipped with various sensors can monitor storm development and progression, providing timely information for emergency management agencies. The integration of multiple sensor types ensures accurate and comprehensive coverage of these dynamic and fast-changing events. In maritime surveillance, or maritime domain awareness (MDA), tip and cue systems enhance the detection and monitoring of vessel movements, contributing to maritime security. By coordinating satellite sensors, these systems can track ships over vast ocean areas, identifying potential threats or illegal activities such as smuggling, piracy, and illegal fishing. The ability to maintain continuous surveillance and share data in real-time with maritime authorities improves response times and enforcement capabilities. This application of tip and cue systems not only aids in law enforcement but also supports environmental conservation efforts by monitoring protected marine areas. Automatic Identification System (AIS) is one of the most important sources of data for the MDA agencies. AIS is used in order for ships to know each other's whereabouts, they transmit a signal from ship to ship and to shore. Lately, the system has been developed into satellite system, so called satellite AIS, which makes the system more effective. All ocean-going vessels above 300 tons, are supposed to use and transmit via AIS according to the International Maritime Organization. The satellite constellations help facilitate this with tip and cue methodologies.
Psychology in cybersecurity
The psychology of cybersecurity (often intersecting with usable security and cyberpsychology) is an interdisciplinary field studying how human behavior, cognitive biases, and social dynamics influence information security. While traditional cybersecurity focuses on hardware and software vulnerabilities, this discipline addresses the "human factor," which is exploited in cyberattacks. Psychology in cybersecurity draws from cognitive psychology and human–computer interaction. == History and evolution == The challenge of human behavior in computing was noted as early as the 1960s with multi-user mainframes like the Compatible Time-Sharing System (CTSS). In 1966, a software error on CTSS caused the system's master password file to be displayed to every user upon login—one of the earliest documented security incidents attributable to a combination of system design and human factors. These behaviors gained broader significance in the 1990s as the Internet became widely accessible. High-profile incidents involving figures like Kevin Mitnick demonstrated how human trust could be exploited through social engineering such as pretexting over the phone. == Cognitive and behavioral factors == Much of the psychology of cybersecurity focuses on decision-making under stress or uncertainty. Researchers apply frameworks like dual process theory to explain why humans fall for phishing or business email compromise. Threat actors design malicious communications to trigger fast, emotional "System 1" thinking—using urgency, authority, or panic, which prompts users to click a link or wire funds before their analytical "System 2" can assess the situation's legitimacy. Industry research has consistently documented the effectiveness of these techniques at scale, pointing to several recurring psychological phenomena that influence daily security practices: Cognitive biases: The optimism bias leads users to believe they are unlikely to be targeted by cybercriminals, resulting in lax password practices or delayed software updates. The availability heuristic causes individuals to focus on highly publicized, sophisticated threats while ignoring common, statistically probable risks like credential reuse. Social influence: Attackers leverage established principles of persuasion, such as those categorized by Robert Cialdini. Impersonating a CEO leverages the psychological trigger of authority, while fake tech support scams use reciprocity (offering to fix a problem before asking for network credentials). == Neurological and pre-cognitive factors == Functional magnetic resonance imaging (fMRI) studies show that neural activation in visual and attentional regions decreases with repeated exposure to the same stimulus, a phenomenon termed repetition suppression. Experiments have confirmed this effect in the context of security warnings: static warning designs produce declines in user attention and adherence. Information processing research on phishing indicates that affective cues, such as artificial urgency or fear, increase cognitive load and elicit automatic heuristic processing, reducing the likelihood of analytical evaluation and facilitating compliance with malicious requests. == Security fatigue and organizational dynamics == Aggressive cybersecurity postures can sometimes lead to mental and emotional exhaustion, a phenomenon known as security fatigue. === Alert fatigue === One example is alert fatigue, which most frequently affects both end-users and security operations center analysts. Continuous exposure to browser warnings or antivirus pop-ups, particularly those that are false positives, conditions users to dismiss alerts automatically due to the volume of notifications rather than their repetitive appearance (see § Neurological and pre-cognitive factors). The scale of this problem is significant in enterprise: SOC teams in large organizations receive thousands of alerts daily, and a survey published in ACM Computer Surveys found that analysts spend over 25% of their time handling false positives, meaning that malicious indicators can be buried in the noise. === Password fatigue === Similarly, password fatigue is the feeling experienced by many people who are required to remember an excessive number of passwords as part of their daily routine, such as to log in to a computer at work. Users cope with the memory burden by making predictable, iterative changes to their passwords (such as updating "Password01!" to "Password02!"), which decreases password security.
Monkey and banana problem
The monkey and banana problem is a famous toy problem in artificial intelligence, particularly in logic programming and planning. It has been framed as: A monkey is in a room containing a box and a bunch of bananas. The bananas are hanging from the ceiling out of reach of the monkey. How can the monkey obtain the bananas? The situation is used as a toy problem for computer science and can be solved with an expert system such as CLIPS. The example set of rules that CLIPS provides is somewhat fragile, in that, naive changes to the rulebase that might seem to a human of average intelligence to make common sense can cause the engine to fail to get the monkey to reach the banana. Other examples exist using Rules Based System (RBS), including a project implemented in Python.