Hao Zhou

Hao Zhou

Auto-generated profile, based on publicly available information

Hao Zhou

Baidu Inc, Beijing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 February 2021 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
HZHao Zhou
Hao Zhou
WZWengang Zhou
Wengang Zhou
YZYun Zhou
Yun Zhou
HLHouqiang Li
Houqiang Li
Despite the recent success of deep learning in video-related tasks, deep models typically focus on the most discriminative features, ignoring other potentially non-trivial and informative contents. Such characteristic heavily constrains their capability to learn implicit visual grammars in sign videos behind the collaboration of different visual cues (i.e., hand shape, facial expression and body posture). To this end, we approach video-based sign language understanding with multi-cue learning and propose a spatial-temporal multi-cue (STMC) network to solve the vision-based sequence learning problem. Our STMC network consists of a spatial multi-cue (SMC) module and a temporal multi-cue (TMC) module. The SMC module learns to spatial representation of different cues with a self-contained pose estimation branch. The TMC module models temporal corrections from intra-cue and inter-cue perspectives to explore the collaboration of multiple cues. A joint optimization strategy and a segmented attention mechanism are designed to make the best of multi-cue sources for SL recognition and translation. To validate the effectiveness, we perform experiments on three large-scale sign language benchmarks: PHOENIX-2014, CSL and PHOENIX-2014-T. Experimental results demonstrate that the proposed method achieves new state-of-the-art performance on all three benchmarks.

1 January 2025
Verified
Conference Paper
Open access
PDF file
XHXiaohu Huang
Xiaohu Huang
HZHao Zhou
Hao Zhou
KHKai Han
Kai Han
Xiaohu Huang, Hao Zhou, Kai Han. Findings of the Association for Computational Linguistics: ACL 2025. 2025.

5 April 2023 in Journal of Cleaner Production
Verified
Journal Article
Closed access
ZHZujian Huang
Zujian Huang
HZHao Zhou
Hao Zhou
HTHao Tang
Hao Tang
YZYang Zhao
Yang Zhao
BLBorong Lin
Borong Lin

23 April 2024 in Environmental Impact Assessment Review
Verified
Journal Article
Closed access
ZHZujian Huang
Zujian Huang
HTHao Tang
Hao Tang
YWYuhe Wen
Yuhe Wen
WSWenbo Sun
Wenbo Sun
HZHao Zhou
Hao Zhou
BLBorong Lin
Borong Lin

3 June 2025 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
ZZZhengqi Zhao
Zhengqi Zhao
XHXiaohu Huang
Xiaohu Huang
HZHao Zhou
Hao Zhou
KYKun Yao
Kun Yao
EDErrui Ding
Errui Ding
FBFeng Bin
Feng Bin

8 February 2020 in arXiv
Verified
Preprint
Open access
PDF file
HZHao Zhou
Hao Zhou
WZWengang Zhou
Wengang Zhou
YZYun Zhou
Yun Zhou
HLHouqiang Li
Houqiang Li
Despite the recent success of deep learning in continuous sign language recognition (CSLR), deep models typically focus on the most discriminative features, ignoring other potentially non-trivial and informative contents. Such characteristic heavily constrains their capability to learn implicit visual grammars behind the collaboration of different visual cues (i,e., hand shape, facial expression and body posture). By injecting multi-cue learning into neural network design, we propose a spatial-temporal multi-cue (STMC) network to solve the vision-based sequence learning problem. Our STMC network consists of a spatial multi-cue (SMC) module and a temporal multi-cue (TMC) module. The SMC module is dedicated to spatial representation and explicitly decomposes visual features of different cues with the aid of a self-contained pose estimation branch. The TMC module models temporal correlations along two parallel paths, i.e., intra-cue and inter-cue, which aims to preserve the uniqueness and explore the collaboration of multiple cues. Finally, we design a joint optimization strategy to achieve the end-to-end sequence learning of the STMC network. To validate the effectiveness, we perform experiments on three large-scale CSLR benchmarks: PHOENIX-2014, CSL and PHOENIX-2014-T. Experimental results demonstrate that the proposed method achieves new state-of-the-art performance on all three benchmarks.