46 citations · 61 across the 6 of their papers we have counts for
6 papers
Mining Contextual Information Beyond Image for Semantic Segmentation
Zhenchao Jin, Tao Gong, Dongdong Yu +4
This paper studies the context aggregation problem in semantic image segmentation. The existing researches focus on improving the pixel representations by aggregating the contextua…
Improving Generalization in Reinforcement Learning with Mixture Regularization
Kaixin Wang, Bingyi Kang, Jie Shao +1
Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments. To improve their…
Temporal Context Aggregation for Video Retrieval with Contrastive Learning
Jie Shao, Xin Wen, Bingchen Zhao +1
The current research focus on Content-Based Video Retrieval requires higher-level video representation describing the long-range semantic dependencies of relevant incidents, events…
Towards Good Practices for Video Object Segmentation
Dongdong Yu, Kai Su, Hengkai Guo +6
Semi-supervised video object segmentation is an interesting yet challenging task in machine learning. In this work, we conduct a series of refinements with the propagation-based vi…
Qiniu Submission to ActivityNet Challenge 2018
Xiaoteng Zhang, Yixin Bao, Feiyun Zhang +7
In this paper, we introduce our submissions for the tasks of trimmed activity recognition (Kinetics) and trimmed event recognition (Moments in Time) for Activitynet Challenge 2018.…
Learning to Point and Count
Jie Shao, Dequan Wang, Xiangyang Xue +1
This paper proposes the problem of point-and-count as a test case to break the what-and-where deadlock. Different from the traditional detection problem, the goal is to discover ke…