6 papers
STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval
Miaoge Li, Dongsheng Wang, Zening Sun +3
Training-free zero-shot composed image retrieval models are recently gaining increasing research interest due to their generalizability and flexibility in unseen multimodal retriev…
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…