A Baseline Framework for Part-level Action Parsing and Action Recognition

This technical report introduces our 2nd place solution to Kinetics-TPS Track on Part-level Action Parsing in ICCV DeeperAction Workshop 2021. Our entry is mainly based on YOLOF [1] for instance and part detection, HRNet [7] for human pose estimation, and CSN [8] for video-level action recognition and frame-level part state parsing. We describe technical details for the Kinetics-TPS dataset, together with some experimental results. In the competition, we achieved 61.37% mAP on the test set of Kinetics-TPS.

[1]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Xiangyu Zhang,et al.  You Only Look One-level Feature , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Kaiming He,et al.  Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour , 2017, ArXiv.

[4]  Heng Wang,et al.  Video Classification With Channel-Separated Convolutional Networks , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[5]  Dong Liu,et al.  Deep High-Resolution Representation Learning for Human Pose Estimation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.