Di Xie
Di Xie
Hikvision Research Institute
確認したメール アドレス: hikvision.com
タイトル
引用先
引用先
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
1922018
Skeleton-based action recognition with convolutional neural networks
C Li, Q Zhong, D Xie, S Pu
Multimedia & Expo Workshops (ICMEW), 2017 IEEE International Conference on …, 2017
1682017
Self-supervised spatiotemporal learning via video clip order prediction
D Xu, J Xiao, Z Zhao, J Shao, D Xie, Y Zhuang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019
1392019
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
Fusing geometric features for skeleton-based action recognition using multilayer LSTM networks
S Zhang, Y Yang, J Xiao, X Liu, Y Yang, D Xie, Y Zhuang
IEEE Transactions on Multimedia 20 (9), 2330-2343, 2018
862018
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
752018
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
552019
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
422018
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
342018
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
Video based head detection and tracking surveillance system
D Xie, L Dang, R Tong
2012 9th International Conference on Fuzzy Systems and Knowledge Discovery …, 2012
282012
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
272020
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
242019
A practical convolutional neural network as loop filter for intra frame
X Song, J Yao, L Zhou, L Wang, X Wu, D Xie, S Pu
2018 25th IEEE International Conference on Image Processing (ICIP), 1133-1137, 2018
232018
Advancing image understanding in poor visibility environments: A collective benchmark study
W Yang, Y Yuan, W Ren, J Liu, WJ Scheirer, Z Wang, T Zhang, Q Zhong, ...
IEEE Transactions on Image Processing 29, 5737-5752, 2020
192020
Estimation of crowd density in surveillance scenes based on deep convolutional neural network
S Pu, T Song, Y Zhang, D Xie
Procedia computer science 111, 154-159, 2017
172017
Upper body human detection and segmentation in low contrast video
R Tong, D Xie, M Tang
IEEE transactions on circuits and systems for video technology 23 (9), 1502-1509, 2013
162013
Towards good practices for recognition & detection
Q Zhong, C Li, Y Zhang, H Sun, S Yang, D Xie, S Pu
CVPR workshops 1, 2, 2016
112016
Mixed context networks for semantic segmentation
H Sun, D Xie, S Pu
arXiv preprint arXiv:1610.05854, 2016
102016
A layer decomposition-recomposition framework for neuron pruning towards accurate lightweight networks
W Chen, Y Zhang, D Xie, S Pu
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 3355-3362, 2019
62019
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