6 papers
Zero-Shot Skeleton-Based Action Anticipation
Hongsong Wang, Pengbo Yan, Yang Zhang +1
Action anticipation (AA) aims to recognize ongoing human or humanoids actions from partial observations, enabling robots to predict intentions before the actions are completed. Alt…
Virtual Category-Guided Continual Generalized Category Discovery
Jiahui Xiong, Qiuxia Lai, Hongsong Wang
Continual Generalized Category Discovery (C-GCD) aims to incrementally identify novel categories from sequential unlabeled data while preserving recognition of known classes, which…
Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images
Bo Zhou, Qiuxia Lai, Zeren Sun +3
Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied AI. However, learning such…
Temporal Consistency-Aware Text-to-Motion Generation
Hongsong Wang, Wenjing Yan, Qiuxia Lai +1
Text-to-Motion (T2M) generation aims to synthesize realistic human motion sequences from natural language descriptions. While two-stage frameworks leveraging discrete motion repres…
A Conditional Probability Framework for Compositional Zero-shot Learning
Peng Wu, Qiuxia Lai, Hao Fang +4
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen combinations of known objects and attributes by leveraging knowledge from previously seen compositions. Traditional…
PAMD: Plausibility-Aware Motion Diffusion Model for Long Dance Generation
Hongsong Wang, Yin Zhu, Qiuxia Lai +3
Computational dance generation is crucial in many areas, such as art, human-computer interaction, virtual reality, and digital entertainment, particularly for generating coherent a…