home.social

#videoanalysis — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #videoanalysis, aggregated by home.social.

  1. CW: ICE Agent Firing Shots At Renee Good

    Preliminary forensic analysis of January 7, 2026 ICE agent killing of unarmed Renee Nicole Good in Minneapolis.
    Video analyst Michael D. Sellers provides an early examinatiin of recording of shots fired at a 37-year-old mother driving her vehicle on a Minneapolis street near where ICE agents were conducting an operation.

    michaeldsellers.substack.com/p
    #Minneapolis #ReneeNicoleGood #ICE #Shooting
    #VideoAnalysis

  2. 🚀 Gemini 3 Flash pushes LLMs into real-time multimodal territory. Its transformer core and on-device tricks let you analyse video, extract data and answer visual Q&A on the fly. Curious how fast reasoning can get? Dive into the details. #Gemini3Flash #MultimodalReasoning #RealTimeProcessing #VideoAnalysis

    🔗 aidailypost.com/news/gemini-3-

  3. 🚀👏 Oh joy! Ollama's shiny new toy can handle *multimodal* models, as if the world wasn't already drowning in #buzzwords and models that are impossible to distinguish from one another. 😂🤯 Apparently, you can now ask a bajillion-parameter monstrosity what it sees in a video frame—because what we really needed was another way to get ignored by #AI. 🙄🤖
    ollama.com/blog/multimodal-mod #Ollama #Multimodal #VideoAnalysis #AIModels #HackerNews #ngated

  4. #TechNews: #Qwen Releases New #VisionLanguage #LLM Qwen2-VL 🖥️👁️

    After a year of development, #Qwen has released Qwen2-VL, its latest #AI system for interpreting visual and textual information. 🚀

    Key Features of Qwen2-VL:

    1. 🖼️ Image Understanding:

    Qwen2-VL shows performance on #VisualUnderstanding benchmarks including #MathVista, #DocVQA, #RealWorldQA, and #MTVQA.

    2. 🎬 Video Analysis:

    Qwen2-VL can analyze videos over 20 minutes in length. This is achieved through online streaming capabilities, allowing for video-based #QuestionAnswering, #Dialog, and #ContentCreation. #VideoAnalysis

    3. 🤖 Device Integration:

    The #AI can be integrated with #mobile phones, #robots, and other devices. It uses reasoning and decision-making abilities to interpret visual environments and text instructions for device control. #AIAssistants 📱

    4. 🌍 Multilingual Capabilities:

    Qwen2-VL understands text in images across multiple languages. It supports most European languages, Japanese, Korean, Arabic, Vietnamese, among others, in addition to English and Chinese. #MultilingualAI

    This release represents an advancement in #ArtificialIntelligence, combining visual perception and language understanding. 🧠 Potential applications include #education, #healthcare, #robotics, and #contentmoderation.

    github.com/QwenLM/Qwen2-VL

  5. [en] Eyjafjallajökull #eruption: rare observations of #volcanic clouds

    "By comparing characteristics of the #ash cloud ... through the video, the researchers were able to calculate the amount of ash spewed ... #volcano."

    "Demonstrating our lab experiments are realistic is really important, both for making sure we understand how ash #plume|s work ... #forecast ... effectively."

    cam.ac.uk/research/news/video-

    #ResearchHighlights #videoanalysis #volcanology #hazardousash #cambridge #research

  6. A new release of our standalone application, #VideoAnalysis, is freely available! The fresh build runs well on the latest versions of OSX and Windows and is the easiest way to create various visualizations from video files.

    uio.no/ritmo/english/research/

  7. New review articel on #opensource tools for #behavioral #videoanalysis:

    "Open-source tools for behavioral video analysis: Setup, methods, and best practices”, by Kevin Luxem, Jennifer J Sun, Sean P Bradley, Keerthi Krishnan, Eric Yttri, Jan Zimmermann, Talmo D Pereira, and Mark Laubach, 2023, eLife 12:e79305.

    🌎 doi.org/10.7554/eLife.79305