Shiliang Pu
Shiliang Pu
Hikvision Research Insititute
確認したメール アドレス: hikvision.com
タイトル
引用先
引用先
Focusing attention: Towards accurate text recognition in natural images
Z Cheng, F Bai, Y Xu, G Zheng, S Pu, S Zhou
Proceedings of the IEEE international conference on computer vision, 5076-5084, 2017
2252017
Aon: Towards arbitrarily-oriented text recognition
Z Cheng, Y Xu, F Bai, Y Niu, S Pu, S Zhou
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018
1592018
Skeleton-based action recognition with convolutional neural networks
C Li, Q Zhong, D Xie, S Pu
2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW …, 2017
1592017
Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation
C Li, Q Zhong, D Xie, S Pu
arXiv preprint arXiv:1804.06055, 2018
1552018
All you need is beyond a good init: Exploring better solution for training extremely deep convolutional neural networks with orthonormality and modulation
D Xie, J Xiong, S Pu
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2017
1012017
Edit probability for scene text recognition
F Bai, Z Cheng, Y Niu, S Pu, S Zhou
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018
852018
Particle field characterization by digital in-line holography: 3D location and sizing
SL Pu, D Allano, B Patte-Rouland, M Malek, D Lebrun, KF Cen
Experiments in Fluids 39 (1), 1-9, 2005
852005
Small-scale pedestrian detection based on topological line localization and temporal feature aggregation
T Song, L Sun, D Xie, H Sun, S Pu
Proceedings of the European Conference on Computer Vision (ECCV), 536-551, 2018
742018
Content-aware convolutional neural network for in-loop filtering in high efficiency video coding
C Jia, S Wang, X Zhang, S Wang, J Liu, S Pu, S Ma
IEEE Transactions on Image Processing 28 (7), 3343-3356, 2019
612019
Collaborative spatiotemporal feature learning for video action recognition
C Li, Q Zhong, D Xie, S Pu
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019
462019
Counterfactual samples synthesizing for robust visual question answering
L Chen, X Yan, J Xiao, H Zhang, S Pu, Y Zhuang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
432020
Counterfactual critic multi-agent training for scene graph generation
L Chen, H Zhang, J Xiao, X He, S Pu, SF Chang
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019
422019
Extreme network compression via filter group approximation
B Peng, W Tan, Z Li, S Zhang, D Xie, S Pu
Proceedings of the European Conference on Computer Vision (ECCV), 300-316, 2018
412018
Small-scale pedestrian detection based on somatic topology localization and temporal feature aggregation
T Song, L Sun, D Xie, H Sun, S Pu
arXiv preprint arXiv:1807.01438, 2018
332018
All you need is a few shifts: Designing efficient convolutional neural networks for image classification
W Chen, D Xie, Y Zhang, S Pu
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019
322019
Segregated temporal assembly recurrent networks for weakly supervised multiple action detection
Y Xu, C Zhang, Z Cheng, J Xie, Y Niu, S Pu, F Wu
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 9070-9078, 2019
292019
Cascade region proposal and global context for deep object detection
Q Zhong, C Li, Y Zhang, D Xie, S Yang, S Pu
Neurocomputing 395, 170-177, 2020
252020
Cross-relation cross-bag attention for distantly-supervised relation extraction
Y Yuan, L Liu, S Tang, Z Zhang, Y Zhuang, S Pu, F Wu, X Ren
Proceedings of the AAAI conference on artificial intelligence 33 (01), 419-426, 2019
252019
Multi-Turn Video Question Answering via Multi-Stream Hierarchical Attention Context Network.
Z Zhao, X Jiang, D Cai, J Xiao, X He, S Pu
IJCAI, 3690-3696, 2018
222018
Learning incremental triplet margin for person re-identification
Y Zhang, Q Zhong, L Ma, D Xie, S Pu
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 9243-9250, 2019
212019
現在システムで処理を実行できません。しばらくしてからもう一度お試しください。
論文 1–20