Improved Techniques for Quantizing Deep Networks with Adaptive Bit-WidthsXimeng SunRameswar Pandaet al.2024WACV 2024
AU-Aware Dynamic 3D Face Reconstruction from Videos with TransformerChenyi KuangJeffrey O. Kephartet al.2024WACV 2024
PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene DataRoei HerzigOfir Abramovichet al.2024WACV 2024
Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You WhereZhi-Yi ChinChieh-Ming Jianget al.2024WACV 2024
Incorporating Physics Principles for Precise Human Motion PredictionYufei ZhangJeffrey O. Kephartet al.2024WACV 2024