PaddlePaddle/PaddleVideo
A video understanding toolkit built on PaddlePaddle for action recognition, temporal action detection, and skeleton-based human activity analysis.
Not currently ranked — collecting fresh signals.
star history
PaddleVideo provides video understanding models and tools for action recognition, temporal action localization, and skeleton-based activity detection. It includes implementations of popular architectures like SlowFast, ST-GCN, TSM, and TSN, along with the project’s PP-TSM and PP-TSMv2 lightweight action recognition models. The toolkit supports video data annotation and covers datasets like Kinetics-400, AVA, ActivityNet, and YouTube-8M.
Frequently asked
- What is PaddlePaddle/PaddleVideo?
- A video understanding toolkit built on PaddlePaddle for action recognition, temporal action detection, and skeleton-based human activity analysis.
- Is PaddleVideo open source?
- Yes — PaddlePaddle/PaddleVideo is open source, released under the Apache-2.0 license.
- What language is PaddleVideo written in?
- PaddlePaddle/PaddleVideo is primarily written in Python.
- How popular is PaddleVideo?
- PaddlePaddle/PaddleVideo has 1.7k stars on GitHub.
- Where can I find PaddleVideo?
- PaddlePaddle/PaddleVideo is on GitHub at https://github.com/PaddlePaddle/PaddleVideo.