5 papers
Towards Robust and Realistic Human Pose Estimation via WiFi Signals
Yang Chen, Jingcai Guo
Robust WiFi-based human pose estimation (HPE) is a challenging task that bridges discrete and subtle WiFi signals to human skeletons. We revisit this problem and reveal two critica…
Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition
Yang Chen, Miaoge Li, Zhijie Rao +3
Recognizing unseen skeleton action categories remains highly challenging due to the absence of corresponding skeletal priors. Existing approaches generally follow an ``align-then-c…
Semantic-guided LoRA Parameters Generation
Miaoge Li, Yang Chen, Zhijie Rao +2
Low-Rank Adaptation (LoRA) has demonstrated strong generalization capabilities across a variety of tasks for efficiently fine-tuning AI models, especially on resource-constrained e…
Exploring Transferable Homogeneous Groups for Compositional Zero-Shot Learning
Zhijie Rao, Jingcai Guo, Miaoge Li +1
Conditional dependency present one of the trickiest problems in Compositional Zero-Shot Learning, leading to significant property variations of the same state (object) across diffe…
Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
Yang Chen, Jingcai Guo, Song Guo +1
Zero-shot skeleton action recognition is a non-trivial task that requires robust unseen generalization with prior knowledge from only seen classes and shared semantics. Existing me…