Timezone: »
This work concerns self-supervised video representation learning (SSVRL), one topic that has received much attention recently. Since videos are storage-intensive and contain a rich source of visual content, models designed for SSVRL are expected to be storage- and computation-efficient, as well as effective. However, most existing methods only focus on one of the two objectives, failing to consider both at the same time. In this work, for the first time, the seemingly contradictory goals are simultaneously achieved by exploiting compressed videos and capturing mutual information between two input streams. Specifically, a novel Motion Vector based Cross Guidance Contrastive learning approach (MVCGC) is proposed. For storage and computation efficiency, we choose to directly decode RGB frames and motion vectors (that resemble low-resolution optical flows) from compressed videos on-the-fly. To enhance the representation ability of the motion vectors, hence the effectiveness of our method, we design a cross guidance contrastive learning algorithm based on multi-instance InfoNCE loss, where motion vectors can take supervision signals from RGB frames and vice versa. Comprehensive experiments on two downstream tasks show that our MVCGC yields new state-of-the-art while being significantly more efficient than its competitors.
Author Information
Yuqi Huo (Renmin University of China)
Mingyu Ding (The University of Hong Kong)
Haoyu Lu (Renmin University of China)
Nanyi Fei (Renmin University of China)
Zhiwu Lu (Renmin University of China)
Ji-Rong Wen (Renmin University of China)
Ping Luo (The University of Hong Kong)
More from the Same Authors
-
2021 : An Empirical Investigation of Representation Learning for Imitation »
Cynthia Chen · Sam Toyer · Cody Wild · Scott Emmons · Ian Fischer · Kuang-Huei Lee · Neel Alex · Steven Wang · Ping Luo · Stuart Russell · Pieter Abbeel · Rohin Shah -
2021 Poster: Rethinking the Pruning Criteria for Convolutional Neural Network »
Zhongzhan Huang · Wenqi Shao · Xinjiang Wang · Liang Lin · Ping Luo -
2021 Poster: Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language »
Mingyu Ding · Zhenfang Chen · Tao Du · Ping Luo · Josh Tenenbaum · Chuang Gan -
2021 Poster: Model-Based Reinforcement Learning via Imagination with Derived Memory »
Yao Mu · Yuzheng Zhuang · Bin Wang · Guangxiang Zhu · Wulong Liu · Jianyu Chen · Ping Luo · Shengbo Li · Chongjie Zhang · Jianye Hao -
2021 Poster: Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning »
Chongjian GE · Youwei Liang · YIBING SONG · Jianbo Jiao · Jue Wang · Ping Luo -
2021 Poster: SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers »
Enze Xie · Wenhai Wang · Zhiding Yu · Anima Anandkumar · Jose M. Alvarez · Ping Luo -
2020 Poster: Scalable Graph Neural Networks via Bidirectional Propagation »
Ming Chen · Zhewei Wei · Bolin Ding · Yaliang Li · Ye Yuan · Xiaoyong Du · Ji-Rong Wen -
2018 Poster: Domain-Invariant Projection Learning for Zero-Shot Recognition »
An Zhao · Mingyu Ding · Jiechao Guan · Zhiwu Lu · Tao Xiang · Ji-Rong Wen