2 papers
cs.LG2026
OVA-IB: One vs All Information Bottleneck for Multi-Modal Alignment
Tianchao Li, Shujian Yu, Xinrui Zu +4
Contrastive learning is effective for aligning paired views or modalities, but alignment beyond two modalities remains non-trivial and comparatively underexplored. Pairwise CLIP-st…
cs.CV2024
Sonicmesh: Enhancing 3D Human Mesh Reconstruction in Vision-Impaired Environments With Acoustic Signals
Xiaoxuan Liang, Wuyang Zhang, Hong Zhou +6
3D Human Mesh Reconstruction (HMR) from 2D RGB images faces challenges in environments with poor lighting, privacy concerns, or occlusions. These weaknesses of RGB imaging can be c…