The official implementation of VideoScan+, which is a novel online video inference framework that achieves extremely reduced latency and memory usage.
- Ultra-Low Latency: Optimized streaming inference pipeline
- Memory Efficient: Significantly reduced memory footprint compared to traditional approaches
- Online Processing: Real-time video processing capabilities (around 50 serving FPS)
- Easy Integration: Simple integration with existing video processing pipelines
[NEW! 2025.08.05]: VideoScan+ official implementation is released! 🚀🚀🚀
cd VideoScan
pip install -r requirements.txt- Offline Video Inference:
python infer.py- Online Streaming Video Inference:
python stream_infer.pyIf you find this work useful in your research, please consider citing:
@article{li2025videoscan,
title={VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers},
author={Li, Ruanjun and Tan, Yuedong and Shi, Yuanming and Shao, Jiawei},
journal={arXiv preprint arXiv:2503.09387},
year={2025}
}This project is licensed under the Apache 2.0 License.