no code implementations • 8 Aug 2023 • Jiahang Zhang, Lilang Lin, Jiaying Liu
Moreover, combining these two paradigms in a naive manner leaves the synergy between them untapped and can lead to interference in training.
no code implementations • CVPR 2023 • Lilang Lin, Jiahang Zhang, Jiaying Liu
However, these methods treat the motion and static parts equally, and lack an adaptive design for different parts, which has a negative impact on the accuracy of action recognition.
Ranked #82 on Skeleton Based Action Recognition on NTU RGB+D
1 code implementation • 24 Nov 2022 • Jiahang Zhang, Lilang Lin, Jiaying Liu
In this paper, we investigate the potential of adopting strong augmentations and propose a general hierarchical consistent contrastive learning framework (HiCLR) for skeleton-based action recognition.
no code implementations • 4 Jul 2022 • Jiahang Zhang, Lilang Lin, Zejia Fan, Wenjing Wang, Jiaying Liu
We first present a newdataset S5Mars for Semi-SuperviSed learning on Mars Semantic Segmentation, which contains 6K high-resolution images and is sparsely annotated based on confidence, ensuring the high quality of labels.
no code implementations • 5 Jun 2022 • Wenjing Wang, Lilang Lin, Zejia Fan, Jiaying Liu
For segmentation, we extend supervised inter-class contrastive learning into an element-wise mode and use online pseudo labels for supervision on unlabeled areas.
1 code implementation • 12 Oct 2020 • Lilang Lin, Sijie Song, Wenhan Yan, Jiaying Liu
To realize this goal, we integrate motion prediction, jigsaw puzzle recognition, and contrastive learning to learn skeleton features from different aspects.