Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Polyphony: Diffusion-based Dual-Hand Action Segmentation with Alternating Vision Transformer and Semantic Conditioning
Hao Zheng, Hu Wang, Tiantian Zheng +2
Dual-hand action segmentation, densely predicting actions for both hands from untrimmed videos, is essential for understanding complex bimanual activities. However, it poses severa…
cs.CV2026★ 5 cited
Deep Multimodal Learning with Missing Modality: A Survey
Renjie Wu, Hu Wang, Hsiang-Ting Chen +1
During multimodal model training and testing, certain data modalities may be absent due to sensor limitations, cost constraints, privacy concerns, or data loss, negatively affectin…
cs.CV2024
Segment Beyond View: Handling Partially Missing Modality for Audio-Visual Semantic Segmentation
Renjie Wu, Hu Wang, Feras Dayoub +1
Augmented Reality (AR) devices, emerging as prominent mobile interaction platforms, face challenges in user safety, particularly concerning oncoming vehicles. While some solutions…