[NEWS!] We will host HACS Temporal Action Localization Challenge at CVPR'21 International Challenge on Activity Recognition Workshop. You are welcome to participate in our action localization challenge. The challenge guideline is HERE, and the evaluation server is open now!
This project introduces a novel video dataset, named HACS (Human Action Clips and Segments). It consists of two kinds of manual annotations. HACS Clips contains 1.55M 2-second clip annotations; HACS Segments has complete action segments (from action start to end) on 50K videos. The large-scale dataset is effective for pretraining action recognition and localization models, and also serves as a new benchmark for temporal action localization. (*SLAC dataset is now part of HACS dataset.)
HACS Clips includes:
HACS Segments includes:
HACS annotation pipeline:
Each row shows the sampled clips from one video, their corresponding start and end times (start, end), and the annotations (Positive or Negative).
Play the videos to check segment annotations, which are shown in the timelines below.
If you find our work helpful, please cite the following paper:
@article{zhao2019hacs,
title={HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization},
author={Zhao, Hang and Yan, Zhicheng and Torresani, Lorenzo and Torralba, Antonio},
journal={arXiv preprint arXiv:1712.09374},
year={2019}
}
