Action Recognition in the Dark Dataset (ARID Dataset)
A Benchmark Dataset for Action Recognition in Dark Videos
Abstract
The task of action recognition in dark videos is useful in various scenarios, e.g., night surveillance and self-driving at night. Though progress has been made in action recognition task for videos in normal illumination, few have studied action recognition in the dark. This is partly due to the lack of sufficient datasets for such a task. In this paper, we explored the task of action recognition in dark videos. We bridge the gap of the lack of data for this task by collecting a new dataset: the Action Recognition in the Dark (ARID) dataset. It consists of over 3,780 video clips with 11 action categories. To the best of our knowledge, it is the first dataset focused on human actions in dark videos. To gain further understanding of our ARID dataset, we analyze the ARID dataset in detail and showed its necessity over synthetic dark videos. Additionally, we benchmark the performance of several current action recognition models on our dataset and explored potential methods for increasing their performances. Our results show that current action recognition models and frame enhancement methods may not be effective solutions for the task of action recognition in dark videos.
Basic Statistics
The distribution of clips among the 11 classes is as follows:
Comparisons with HMDB51(-dark)
We compare our ARID dataset statistically with HMDB51/HMDB51-dark, with the results and sampled frame as shown:
Benchmark Results
Here we present some benchmark results of previous action recognition models: (Across three splits)
| Method | Top-1 Accuracy | Top-5 Accuracy |
|---|---|---|
| VGG-Two Stream | 32.08% | 90.76% |
| TSN | 57.96% | 94.17% |
| C3D | 40.34% | 94.17% |
| I3D-RGB | 54.68% | 97.69% |
| I3D-Two Stream | 72.78% | 99.39% |
| 3D-ResNet (50) | 71.08% | 99.39% |
Papers and Download
- We are co-organizing the 4th UG2+ Workshop with our ARID dataset, to be held in conjunction with CVPR2021. For more information about this workshop, click here Major update is introduced. [NEW!]
- To learn more about our ARID dataset, please click Here for our paper!
- To download the dataset, please write to xuyu0014@e.ntu.edu.sg and yang0478@e.ntu.edu.sg for the download link. Thank you! [Update!]
- Usage of our dataset is licensed under the MIT License, you may view the license here [Update!]
- If you find our work helpful, you may cite our work at:
@article{xu2020arid, title={ARID: A New Dataset for Recognizing Action in the Dark}, author={Xu, Yuecong and Yang, Jianfei and Cao, Haozhi and Mao, Kezhi and Yin, Jianxiong and See, Simon}, journal={arXiv preprint arXiv:2006.03876}, year={2020} } - We provide a sample code to initiate, please check here
- The pretrained models can be found here, please put them at “./network/pretrained” folder