Computer Vision news and analysis on Web Pulse: 3331 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers propose CausAdv, a causal framework for detecting adversarial examples in convolutional neural networks (CNNs) by learning causal and non-causal features and quantifying counterfactual information (CI) per fi…
Researchers developed the Language-guided Segmentation-assisted Diagnostic Transformer (LSDT) model, which uses zero-shot segmentation and multi-modal slice fusion to classify prostate cancer into four clinically meaning…
A new classification-guided large vision-language model (LVLM) framework for visual information extraction (VIE) from documents achieves 86.43% F1-score in zero-shot inference on a real-world bidding dataset with 16 cert…
Researchers introduced KANEx, the first framework leveraging Kolmogorov-Arnold Networks (KANs) to ground Vision-Language Model (VLM) reasoning for medical explainability, achieving a 10% improvement in visual localizatio…
Researchers propose an automated framework using Vision-Language Models to verify actions in cognitive remediation tasks for schizophrenia patients, aiming to replace subjective manual observation by clinicians. The syst…
Researchers propose CADER (Confidence-Aware Dynamic Evidence Reasoning), a training-free framework for adaptive long-video reasoning that uses a logit-margin signal to let high-confidence examples exit early and activate…
Researchers introduce TOM-GS, an editable video representation that uses regular 3D Gaussians with a continuous temporal opacity formulation, avoiding complex deformations. The method outperforms prior editable video rep…
Researchers introduce C-VCE, a diffusion framework that builds a classifier directly into the generative model via a concept bottleneck layer to produce visual counterfactual explanations without relying on external nois…
AI-powered cameras on bridges over Seoul's Han River are detecting potential suicide attempts and alerting first responders in a country with one of the world's highest suicide rates, according to Seoul officials. The sy…
A new diagnostic framework called Spatial-IQ, introduced by researchers using NVIDIA Isaac Sim, decomposes object counting in stacked 3D structures into 9 perceptual and cognitive sub-tasks to evaluate spatial reasoning …
Codeifai (ASX:CDE) Executive Director and COO Martin Ross said the company is transitioning to a self-service SaaS model and scaling customer adoption to capitalize on the GS1 Sunrise 2027 mandate, which requires all ret…
Meta introduced Facebook Verified on 24 July 2026, a free badge that requires users to submit a short video selfie to prove they are human, but the announcement does not disclose where the video is stored, how long it is…
Indian activists are challenging Prime Minister Narendra Modi's government over AI-powered surveillance used at the largest youth protest in decades, with student activist Aishe Ghosh asking the Delhi High Court to decla…
FeyNoBg, a high-precision background removal model developed by Feyn Inc., achieves top-tier scores across eight benchmarks by expanding the third stage of its BiRefNet-based feature extractor from 18 to 24 blocks using …
Mealyu, an AI-powered nutrition and fitness coach, launches with features including photo-based meal analysis, proactive coaching, goal prediction, and personalized workout sessions. The app offers a free tier with limit…
Apple is reportedly debating whether to include a camera in its upcoming smart glasses, with one prototype omitting the camera entirely and another including it but disabling photo and video capture, according to Bloombe…
Feyn Labs released FeyNoBg, a 263M-parameter background-removal model that leads on four of eight standard benchmarks and stays within 2% of the leader on the rest, but the weights are licensed CC-BY-NC-4.0, limiting com…
The National Institute of Standards and Technology launched the AI Technology Evaluation platform on Monday, a voluntary testbed that provides blind data for safely evaluating AI models across quantum science, genomics, …
RevelRaw, a native macOS RAW editor, reads the scene in a photograph using Apple's on-device AI and ranks 40+ curated presets to match, all offline with no cloud or account. The app supports 24 RAW formats from Canon, Ni…
U.S. cities including Brownsville, Texas, and Las Vegas are expanding use of AI-powered cameras and sensors for public safety and traffic management, provided by SHI International, raising privacy concerns from advocates…