7 papers
DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition
Jiaying Lin, Shiman Wu, Jinfu Liu +2
Millimeter-wave (mmWave) radar provides privacy-preserving sensing and is valuable for human action recognition (HAR). Existing mmWave point cloud datasets are limited in scale and…
Heatmap Pooling Network for Action Recognition from RGB Videos
Mengyuan Liu, Jinfu Liu, Yongkang Jiang +1
Human action recognition (HAR) in videos has garnered widespread attention due to the rich information in RGB videos. Nevertheless, existing methods for extracting deep features fr…
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition
Jinfu Liu, Chen Chen, Mengyuan Liu
Skeleton-based action recognition has garnered significant attention due to the utilization of concise and resilient skeletons. Nevertheless, the absence of detailed body informati…
SemiPL: A Semi-supervised Method for Event Sound Source Localization
Yue Li, Baiqiao Yin, Jinfu Liu +3
In recent years, Event Sound Source Localization has been widely applied in various fields. Recent works typically relying on the contrastive learning framework show impressive per…
HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition
Jinfu Liu, Baiqiao Yin, Jiaying Lin +3
Skeleton-based action recognition has gained considerable traction thanks to its utilization of succinct and robust skeletal representations. Nonetheless, current methodologies oft…
SFMViT: SlowFast Meet ViT in Chaotic World
Jiaying Lin, Jiajun Wen, Mengyuan Liu +3
The task of spatiotemporal action localization in chaotic scenes is a challenging task toward advanced video understanding. Paving the way with high-quality video feature extractio…
Explore Human Parsing Modality for Action Recognition
Jinfu Liu, Runwei Ding, Yuhang Wen +4
Multimodal-based action recognition methods have achieved high success using pose and RGB modality. However, skeletons sequences lack appearance depiction and RGB images suffer irr…