4 papers · 1 filter
Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition
Yulin Wang, Haoji Zhang, Yang Yue +4
This paper presents a comprehensive exploration of the phenomenon of data redundancy in video understanding, with the aim to improve computational efficiency. Our investigation com…
Bridging the Divide: Reconsidering Softmax and Linear Attention
Dongchen Han, Yifan Pu, Zhuofan Xia +6
Widely adopted in modern Vision Transformer designs, Softmax attention can effectively capture long-range visual information; however, it incurs excessive computational cost when d…
Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models
Jiayi Guo, Xingqian Xu, Yifan Pu +6
Recently, diffusion models have made remarkable progress in text-to-image (T2I) generation, synthesizing images with high fidelity and diverse contents. Despite this advancement, l…
End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning
Jinrong Zhang, Wujun Wen, Shenglan Liu +3
The streaming temporal action segmentation (STAS) task, a supplementary task of temporal action segmentation (TAS), has not received adequate attention in the field of video unders…