Cycle-Contrast for Self-Supervised Video Representation Learning

NIPS 2020(2020)

引用 51|浏览202
暂无评分
摘要
We present Cycle-Contrastive Learning (CCL), a novel self-supervised method for learning video representation. Following a nature that there is a belong and inclusion relation of video and its frames, CCL is designed to find correspondences across frames and videos considering the contrastive representation in their domains respectively. It is different from recent approaches that merely learn correspondences across frames or clips. In our method, the frame and video representations are learned from a single network based on an R3D architecture, with a shared non-linear transformation for embedding both frame and video features before the cycle-contrastive loss. We demonstrate that the video representation learned by CCL can be transferred well to downstream tasks of video understanding, outperforming previous methods in nearest neighbour retrieval and action recognition tasks on UCF101, HMDB51 and MMAct.
更多
查看译文
关键词
learning,representation,video,cycle-contrast,self-supervised
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要