Y
Yun Zhou
Researcher at University of Science and Technology of China
Publications - 6
Citations - 192
Yun Zhou is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Deep learning & Sensory cue. The author has an hindex of 3, co-authored 6 publications receiving 51 citations.
Papers
More filters
Journal ArticleDOI
Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition
TL;DR: Wang et al. as discussed by the authors proposed a spatial-temporal multi-cue (STMC) network to solve the vision-based sequence learning problem and achieved state-of-the-art performance on three large-scale CSLR benchmarks.
Journal ArticleDOI
Spatial-Temporal Multi-Cue Network for Sign Language Recognition and Translation
TL;DR: A spatial-temporal multi-cue (STMC) network is proposed to solve the vision-based sequence learning problem in video-based sign language understanding and achieves new state-of-the-art performance on all three benchmarks.
Journal ArticleDOI
Relation-Guided Spatial Attention and Temporal Refinement for Video-Based Person Re-Identification
TL;DR: Two relation-guided modules are proposed to learn reinforced feature representations for effective re-identification and enables the individual frames to complement each other in an aggregation manner, leading to robust video-level feature representations.
Journal ArticleDOI
State Representation Learning With Adjacent State Consistency Loss for Deep Reinforcement Learning
TL;DR: This work proposes a new state representation learning scheme with Adjacent State Consistency Loss (ASC Loss), based on the hypothesis that the distance between adjacent states is smaller than that of far apart ones, since scenes in videos generally evolve smoothly.
Proceedings ArticleDOI
State Representation Learning For Effective Deep Reinforcement Learning
TL;DR: This paper exploits ASC loss as an assistant of RL loss in the training phase to boost the state feature learning and conducts evaluation on Atari games and MuJoCo continuous control tasks, which demonstrates that the method is superior to OpenAI baselines.