yunlong10/Awesome-LLMs-for-Video-Understanding resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

3273 stars · 150 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A curated awesome-list accompanying the survey paper 'Video Understanding with Large Language Models' (IEEE TCSVT). It catalogs papers, code, datasets, and benchmarks for video-LLMs (Vid-LLMs).

Use cases

• find papers on video understanding with large language models
• discover datasets for training video LLMs
• find benchmarks for evaluating video-language models
• survey the taxonomy of Vid-LLM architectures
• keep up with the latest research in video-language models
• find code implementations of video understanding models

When to choose

• you need a curated, regularly updated index of Vid-LLM research, datasets, and benchmarks
• you are starting research on video understanding with LLMs and want a survey-backed entry point

When to avoid

• you need runnable software rather than a paper/dataset catalog
• you need a non-multimodal LLM resource or general computer vision references outside video-language models

Facets

learning-resource · maturity active

documentation machine-learning video-processing nlp deep-learning computer-vision large-language-models tutorials awesome-lists cross-platform awesome-list survey video-llms multimodal research-papers datasets benchmarks video

Member repositories

For agents

markdown · JSON · MCP: product_card(name="yunlong10/Awesome-LLMs-for-Video-Understanding")