Computer Vision

MarkTechPost published a tutorial on building a VideoAgent-style multi-agent system for video editing tasks, including intent parsing, graph planning, and tool routing. The system integrates FFmpeg, Whisper transcription…

A team of developers built DJ ROOTS, a real-time collaborative DJ platform that lets everyone in a room vote on songs using a room code. The platform uses Supabase Realtime for instant updates and Google MediaPipe for to…

A developer proposes a paradigm shift in deepfake defense, moving from reactive detection to proactive authenticity verification through a system that creates and validates cryptographic 'digital twins' of individuals ba…

Amazon has invested in TwelveLabs' $100 million Series B round and secured a commercial deal making AWS the startup's preferred cloud partner, with next-generation models launching first on Amazon's Trainium chips rather…

Meta's camera-equipped AI Glasses have sparked such a strong backlash over privacy violations and non-consensual recordings that some owners now avoid wearing them in public, according to Engadget. Influencers, mostly me…

Meta has launched three controversial AI features in less than a month, including a now-retracted WhatsApp tool that used Instagram profile photos to generate new images, a facial recognition system for its smart glasses…

AI glasses from Meta, including Ray-Ban Meta and Oakley Meta models, can serve as a hands-free travel assistant for sightseeing, offering features such as landmark identification, translation, directions, calls, and mess…

Roboflow published a tutorial on automating surface defect detection using a custom RF-DETR object detection model and Roboflow Workflows, enabling quality teams to instantly classify product health and route defective i…

Adobe's Photoshop now includes generative AI tools powered by its Firefly model that are well-suited for beginner-level photo editing, according to a CNET guide. The tools include AI image generation, generative fill, ex…

Meta's AI image detector, previewed alongside its Muse Image generator, failed to identify 55% of its own AI-generated images after they were cropped, according to a Reuters test. The detector relies on Meta's Content Se…

Singer Lorde publicly denounced smart glasses during a festival performance, saying 'f*ck the glasses' and citing privacy concerns about hidden cameras, while Tyler the Creator also criticized Ray-Ban Meta AI glasses on …

Samsung will launch AI smart glasses in autumn 2026, developed with Google and designed by Gentle Monster and Warby Parker, to compete with Meta's Ray-Ban glasses. The Android XR-powered glasses will feature dual front-f…

Anthropic's vision-language model misidentified a video of a rotary automatic weapon firing as a screen recording of a terminal running code, demonstrating object hallucination where the model's output is governed by tra…

A roundup of top AI papers on Hugging Face highlights four major themes: real-time interactive video generation with Vidu S1, scientific reasoning on molecular structures via SciReasoner, a critique of video benchmarks b…

A developer relies on two free browser-based image tools that require no installation: an online image compressor that processes files locally to avoid uploads, and ClarifyPix, which runs AI in-browser for upscaling, deb…

Grocery Outlet in San Francisco's Mission District is using AI facial recognition software from SAFR at RealNetworks to match customers against a watchlist of people who have previously caused harm, with the system sendi…

A new training-free approach called TCLA (Training-Free Class-Level Adaptation) enhances medical vision-language models' performance on out-of-distribution data by correcting inference logits with a few support samples, …

A new study reveals that the true energy burden of Vision-Language Models lies not in visual processing but in the generation of output tokens, with each output token consuming 11 to 39 times more wall-clock time than ea…

VGGT, a 3D reconstruction model, uses its internal layer L17 to differentiate co-visible image pairs without explicit supervision, solving a key challenge in 3D vision. Building on this, Co-VGGT adds a lightweight 7.5M-p…

Researchers have developed a parameter-efficient AI framework based on CLIP models that enhances animal re-identification by adapting to visual shifts over time, using continuous metadata conditioning to eliminate the ne…