Computer Vision news and analysis on Web Pulse: 3323 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers from Emory University and the Georgia Institute of Technology deployed an AI-powered facial recognition device called CapuchinAI in Costa Rica's Taboga Forest Reserve, where 16 capuchin monkeys interacted wit…
Houston Methodist researchers published the first peer-reviewed evidence that ambient AI in the operating room is associated with a 7% rise in surgical case volume, about 25 additional cases per month, in a high-acuity c…
A new dissertation from an unnamed researcher introduces bio-inspired active vision systems that use foveal-peripheral sampling and learned saccades to improve efficiency and robustness in deep neural networks. The syste…
A dissertation from a researcher at an unnamed institution proposes modular parameter-efficient continual learning for Vision Transformers, organizing adaptation into small role-matched corrections rather than full-model…
The Botslab W510 4K AI Security Camera System 2-Camera Kit is available for $220.58, a 31% discount off its $319 RRP, using promo code AA18 at Botslab. The kit includes two wire-free 4K/8MP cameras with solar panels, a h…
A Hacker News reader with 50,000+ bookmarks shared a curated list of S-Tier interactive and animated resources for learning computer science, math, algorithms, systems building, networking, graphics, hardware, and AI top…
A new analysis argues that organ-specific foundation models, trained exclusively on histopathology images from a single organ, may outperform universal models for computational pathology tasks. The author, writing in a t…
Ikerlan, a Spanish-Basque technology center, has developed the BEGI project, a single-lens, passive, neuromorphic 4D sensor that mimics an insect eye to capture 3D depth and track motion using just one optic, aiming to a…
Apple's iOS 27 introduces AI-powered photo editing tools in the Photos app, including Reframe, Extend, and Clean Up, which were tested by a user on an iPhone 17 Pro Max. The Reframe tool showed mixed results, accurately …
Remover.work, an AI-powered tool, removes unwanted objects, backgrounds, subtitles, watermarks, and logos from videos and images, offering the first 5 seconds of video processing free at source resolution with no waterma…
Amazon has reduced the Tapo D205 2K Video Doorbell from £54.99 to £34.47 in a limited-time deal, offering 2K 3MP video, AI person detection, and no subscription required for storage. The doorbell has a 4.3-star rating on…
Rebellions, a Korean neural processing unit (NPU) designer, will supply its ATOM-Max Servers to public surveillance control centers operated by the South Gyeongsang Provincial Government and Ulsan Metropolitan City, mark…
Hong Kong's Labour Department has begun testing an infrared thermal-imaging drone to detect illegal smoking at construction sites, with plans to add artificial intelligence to identify smoking workers. Since the total si…
Researchers propose a human-in-the-loop deep learning framework for color reconstruction of historical lenticular films, addressing failures of automated methods on curved lenticules, low-contrast, or badly captured regi…
A new arXiv preprint (2608.02830v1) reveals that many-shot in-context learning can cause a sharp accuracy drop, termed 'in-context collapse,' in vision-language models (VLMs), with some models falling below chance while …
Researchers propose CURV, a curriculum learning framework that improves chart question answering by reformulating it as multi-step visual grounded reasoning, achieving up to 20.50% improvements over baselines and up to 1…
Alibaba Group's Qwen team introduced Qwen-3D, a geometry-aware large multimodal model that compresses visual information using multi-view geometric cues and 3D Rotary Positional Embeddings, enabling efficient long-horizo…
Researchers propose Structured All-Mask Prediction and its instantiation STAMPlus to resolve the segmentation trilemma in multimodal large language model (MLLM)-based segmentation, achieving state-of-the-art performance …
Researchers developed a unified 2D lesion analysis framework integrating LLM-based reasoning, detection, segmentation, and report generation, achieving mAP50 of 70.1%, Dice score of 62.6%, and BLEU_1 of 64.3% on DeepLesi…
Researchers propose CHASE (Classification with Hierarchical Analysis and Structured Enforcement), a single-stage framework that uses a clinically driven three-level taxonomy of 9 anatomical regions, 17 sub-regions, and 2…