Agentic video understanding
Agentic video understanding is an approach to video analysis in which a reasoning model chooses which parts of a video to inspect for a particular question.
Explore Computer Vision through related topics and the articles other pages reference most.
Articles that also belong to these categories. Counts cover all of Computer Vision.
Showing 1-22 of 22 articles
Agentic video understanding is an approach to video analysis in which a reasoning model chooses which parts of a video to inspect for a particular question.
CLIP, short for Contrastive Language-Image Pre-training, is a family of neural networks developed by OpenAI researchers to learn a shared representation of images and natural-language descriptions.
CLIP Score (also written CLIPScore or CLIP-S) is a reference-free automatic evaluation metric that measures how well a text caption matches an image, computed as the rescaled cosine similarity of the image and…
Chartography is a benchmark for professional chart understanding created by Surge AI.
A computer-use agent (CUA) is a category of AI agent in artificial intelligence that performs tasks by directly operating a general-purpose computer's graphical user interface (GUI) the way a human does, by…
DeepSeek-OCR is an open-source optical character recognition (OCR) and document-understanding system released by DeepSeek on 20 October 2025 that pioneers a contexts optical compression paradigm: it encodes…
Donut (Document understanding transformer) is an OCR-free visual document understanding model introduced by researchers at NAVER CLOVA in the paper "OCR-free Document Understanding Transformer," first posted…
EgoSchema is a diagnostic benchmark for evaluating very long-form video language understanding, introduced by Karttikeya Mangalam, Raiymbek Akshulakov, and Jitendra Malik at UC Berkeley.
Elorian (legal name Elorian AI, Inc.) is an artificial intelligence research and product lab in Palo Alto, California, that builds models meant to reason directly over images and video rather than first…
Fox is an evaluation suite for fine-grained, multi-page document understanding by large vision-language models.
Glimpse is a multimodal AI model from Elorian, a Palo Alto startup led by former Google DeepMind researcher Andrew Dai.
MMMU-Pro is a rigorous benchmark for evaluating multimodal AI systems on college-level, expert questions that genuinely require seeing an image, built as a harder and more robust version of the original MMMU…
Perception Encoder (PE) is a family of vision and vision-language encoders from Meta AI's Fundamental AI Research (FAIR) group, released in April 2025
Robostral Navigate is an 8-billion-parameter vision language model developed by Mistral AI for instruction-following robot navigation.
SigLIP (Sigmoid Loss for Language-Image Pre-training) is a family of vision-language encoders developed by researchers at Google DeepMind that pre-trains image and text encoders by treating each image-text…
Video-MME (Video Multi-Modal Evaluation) is a benchmark for testing how well multimodal large language models (MLLMs) understand video, built from 900 manually selected videos totaling 254 hours and 2,700…
A vision encoder is the neural network component that turns an image into a sequence of numerical vectors that other models can consume.
Vision-language models (VLMs) are artificial intelligence models that learn relationships between visual data and natural language.
Visual question answering models are AI systems that take an image and a natural language question about that image and return a natural language answer.
Visual question answering (VQA) is the task of producing a natural-language answer to a natural-language question about an image.
WeVisOne-VL (WeChat Vision All-in-One) is a vision-language model family developed by the WeChat Vision team at Tencent.
ZeroBench is a visual reasoning benchmark built to be effectively impossible for current frontier large multimodal models, which score 0.0% on its main questions.