Actions ~ Transformations
CVPR(2016)
摘要
What defines an action like "kicking ball"? We argue that the true meaning of an action lies in the change or transformation an action brings to the environment. In this paper, we propose a novel representation for actions by modeling an action as a transformation which changes the state of the environment before the action happens (precondition) to the state after the action (effect). Motivated by recent advancements of video representation using deep learning, we design a Siamese network which models the action as a transformation on a high-level feature space. We show that our model gives improvements on standard action recognition datasets including UCF101 and HMDB51. More importantly, our approach is able to generalize beyond learned action categories and shows significant performance improvement on cross-category generalization on our new ACT dataset.
更多查看译文
关键词
action representation,action transformation,video representation,deep learning,siamese network,high-level feature space,action recognition,cross-category generalization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络