#long-video-understanding Repositories
Discover 7 active open source GitHub repositories tagged with #long-video-understanding, accumulating 8,859 total stars (averaging 1,265 stars per project). Leading this topic is HKUDS/VideoRAG with 3,528 stars.
7 repositories total
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
Official code for Goldfish model for long video understanding and MiniGPT4-video for short video understanding
[ICLR2026] VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
Frequently Asked Questions
What is the most popular #long-video-understanding repository on GitHub?
The top ranked open source #long-video-understanding project on GitHub is HKUDS/VideoRAG with 3,528 stars. [KDD'2026] "VideoRAG: Chat with Your Videos"
Which programming languages are most used in #long-video-understanding repositories?
Among the top ranked #long-video-understanding projects on GitHub, the most common programming languages are Python, C++.
How is the #long-video-understanding repository ranking calculated?
We track 7 active open source repositories tagged with #long-video-understanding (500+ stars), totaling 8,859 stars with an average of 1,265 stars per repository. Rankings update daily from the GitHub API.