155 citations · 420 across the 30 of their papers we have counts for
7 papers · 1 filter
Suppressing Mislabeled Data via Grouping and Self-Attention
Xiaojiang Peng, Kai Wang, Zhaoyang Zeng +3
Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. To suppressing the impact of mislabeled data, this pape…
Effective Action Recognition with Embedded Key Point Shifts
Haozhi Cao, Yuecong Xu, Jianfei Yang +3
Temporal feature extraction is an essential technique in video-based action recognition. Key points have been utilized in skeleton-based action recognition methods but they require…
PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition
Yuecong Xu, Haozhi Cao, Jianfei Yang +3
Long-range spatiotemporal dependencies capturing plays an essential role in improving video features for action recognition. The non-local block inspired by the non-local means is…
ARID: A New Dataset for Recognizing Action in the Dark
Yuecong Xu, Jianfei Yang, Haozhi Cao +3
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 the action recogn…
Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition
Yuecong Xu, Jianfei Yang, Kezhi Mao +2
Temporal feature extraction is an important issue in video-based action recognition. Optical flow is a popular method to extract temporal feature, which produces excellent performa…
Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training
Jianfei Yang, Han Zou, Yuxun Zhou +1
Domain adaptation tackles the problem of transferring knowledge from a label-rich source domain to a label-scarce or even unlabeled target domain. Recently domain-adversarial train…