Computer Vision news and analysis on Web Pulse: 3358 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
FindGenre, an AI-powered audio genre analyzer, uses a CNN trained on spectrograms to identify music genres from uploaded files or YouTube/SoundCloud links. The tool scores tracks in segments and reports confidence levels…
Researchers introduced Temporal Global Policy Optimization (TGPO), a reinforcement learning algorithm that improves temporal awareness in multimodal large language models for egocentric video understanding. TGPO contrast…
A guide explains how creators can use AI video effects tools Runway, Seedance, and Gemini Omni to enhance human-made videos with generative intros, transitions, and visual effects, offering practical workflows for integr…
A guide explains how to create seamless AI-powered location transitions in video using Runway's keyframe system and Seedance 2.0, providing specific prompts and techniques for travel content, cinematic sequences, and soc…
In a head-to-head test of AI video generation, Gemini Omni Flash scored 17.6 to AnimateDiff Turbo's 3.6, demonstrating superior scene construction and prompt obedience across two tasks involving a bakery sign and an umbr…
NATO is building an AI-powered 'Kill Web' along its eastern flank to detect and counter a Russian attack before it begins, according to internal documents obtained by BILD. The system, called the Eastern Flank Deterrence…
Valeo Embedded AI Architect Pullarao Maddu, speaking at the Embedded Vision Summit, warned that latency jitter—not average performance or peak TOPS—is the real enemy in safety-critical edge AI deployments, and that FLOPs…
Meta is testing prototype 'super sensing' smart glasses that could continuously record audio and capture photos every few seconds, with metadata extracted and uploaded for AI queries rather than storing raw footage, acco…
Screenshots from development versions of iRobot's Roomba J7 series, captured in 2020, were leaked online after being shared by gig workers in Venezuela who labeled the data for Scale AI. The images include intimate scene…
Topaz Labs has discontinued its legacy Topaz Video AI at version 7.1.5, shifting to a subscription-only Topaz Video app that continues to receive model updates. The transition raises concerns for editors and ML practitio…
NATO is building the Eastern Flank Deterrence Initiative, an AI-enabled defense network using thousands of sensors, drones, satellites, and uncrewed systems to detect and slow attacks near Russia-facing borders. The syst…
Meta is testing a 'super sensing' mode for its next-generation Ray-Ban smart glasses that keeps cameras and sensors active for hours, enabling continuous AI assistance. CEO Mark Zuckerberg has questioned whether the mand…
Meta is testing AI-powered glasses with 'super sensing' capabilities designed to capture every moment, aiming to enhance user experience through continuous visual recording and analysis.
A developer compiled a list of the top 10 free AI APIs for 2025, including Google Cloud Vision API, Microsoft Azure Cognitive Services, IBM Watson Natural Language Understanding, Amazon Comprehend, TinEye, Google Cloud N…
Mistral launched Robostral Navigate, an 8B-parameter AI model that enables robots to navigate unknown environments using a single RGB camera. The model, trained in simulation and refined with reinforcement learning, achi…
A security researcher discovered that the AI-powered security camera network for India's Project DigiCoal coal mines, developed by DeepSight AI Labs and Accenture, exposed a user list with plaintext passwords via an unau…
Meta announced an update to its Ray-Ban Meta smart glasses that disables the camera if the recording LED is tampered with, aiming to address privacy concerns. However, the company continues to pursue features that collec…
A new interactive feature called 'AI or Not: Architecture' challenges users to distinguish between AI-generated and real architectural images, highlighting the growing sophistication of generative AI in creating photorea…
Mistral released Robostral Navigate, an 8B-parameter navigation model that uses a single RGB camera and plain-language instructions, achieving 76.6% on R2R-CE validation unseen and 79.4% on validation seen. The model out…
Meta announced a mandatory firmware update for its smart glasses that disables the camera if the recording LED is tampered with, addressing one privacy concern. However, other issues remain unresolved, including the diff…