5 papers
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
Panqi Yang, Haodong Jing, Jiahao Chao +5
Unified visual tokenization faces a fundamental trade-off between high-fidelity pixel reconstruction (spatial equivariance) and semantic abstraction (conceptual invariance). We att…
UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space
Panqi Yang, Haodong Jing, Nanning Zheng +1
In the field of human-object interaction (HOI), detection and generation are two dual tasks that have traditionally been addressed separately, hindering the development of comprehe…
PlaneHEC: Efficient Hand-Eye Calibration for Multi-view Robotic Arm via Any Point Cloud Plane Detection
Ye Wang, Haodong Jing, Yang Liao +2
Hand-eye calibration is an important task in vision-guided robotic systems and is crucial for determining the transformation matrix between the camera coordinate system and the rob…
EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning
Xiao Zhang, Yongqiang Ma, Haodong Jing +1
Compositional Zero-Shot Learning (CZSL) investigates compositional generalization capacity to recognize unknown state-object pairs based on learned primitive concepts. Existing CZS…
See Through Their Minds: Learning Transferable Neural Representation from Cross-Subject fMRI
Yulong Liu, Yongqiang Ma, Guibo Zhu +2
Deciphering visual content from functional Magnetic Resonance Imaging (fMRI) helps illuminate the human vision system. However, the scarcity of fMRI data and noise hamper brain dec…