English | 繁體

Search in the results

UM

Browse/Search Results:  1-6 of 6 Help

Selected(0)Clear Items/Page:    Sort:
A simple but effective vision transformer framework for visible–infrared person re-identification Journal article
Li, Yudong, Zhao, Sanyuan, Shen, Jianbing. A simple but effective vision transformer framework for visible–infrared person re-identification[J]. Computer Vision and Image Understanding, 2024, 249, 104192.
Authors:  Li, Yudong;  Zhao, Sanyuan;  Shen, Jianbing
Favorite | TC[WOS]:0 TC[Scopus]:0  IF:4.3/4.9 | Submit date：2024/11/05
Cross-modality  Visual Infrared Person Re-identification  Vit  
GSB: Group superposition binarization for vision transformer with limited training samples Journal article
Gao, Tian, Xu, Cheng Zhong, Zhang, Le, Kong, Hui. GSB: Group superposition binarization for vision transformer with limited training samples[J]. Neural Networks, 2024, 172, 106133.
Authors:  Gao, Tian;  Xu, Cheng Zhong;  Zhang, Le;  Kong, Hui
Favorite | TC[WOS]:1 TC[Scopus]:1  IF:6.0/7.9 | Submit date：2024/05/02
Group Superposition Binarization  Insufficient Training Data  Self-attention  Vision Transformer (Vit)  
Group Multi-View Transformer for 3D Shape Analysis with Spatial Encoding Journal article
Xu, Lixiang, Cui, Qingzhe, Hong, Richang, Xu, Wei, Chen, Enhong, Yuan, Xin, Li, Chenglong, Tang, Yuanyan. Group Multi-View Transformer for 3D Shape Analysis with Spatial Encoding[J]. IEEE Transactions on Multimedia, 2024, 1-14.
Authors:  Xu, Lixiang;  Cui, Qingzhe;  Hong, Richang;  Xu, Wei;  Chen, Enhong; et al.
Favorite | TC[WOS]:1 TC[Scopus]:1  IF:8.4/8.0 | Submit date：2024/05/16
3d Object Recognition  3d Position Embedding  Aggregates  Computational Modeling  Feature Extraction  Knowledge Distillation  Long Short Term Memory  Multi-view Vit  Shape  Solid Modeling  Three-dimensional Displays  View Grouping  
P3 ViT: A CIM-Based High-Utilization Architecture With Dynamic Pruning and Two-Way Ping-Pong Macro for Vision Transformer Journal article
Fu, Xiangqu, Ren, Qirui, Wu, Hao, Xiang, Feibin, Luo, Qing, Yue, Jinshan, Chen, Yong, Zhang, Feng. P3 ViT: A CIM-Based High-Utilization Architecture With Dynamic Pruning and Two-Way Ping-Pong Macro for Vision Transformer[J]. IEEE Transactions on Circuits and Systems I: Regular Papers, 2023, 70(12), 4938-4948.
Authors:  Fu, Xiangqu;  Ren, Qirui;  Wu, Hao;  Xiang, Feibin;  Luo, Qing; et al.
Favorite | TC[WOS]:3 TC[Scopus]:3  IF:5.2/4.5 | Submit date：2024/02/22
Accelerator  Cmos  Computing-in-memory (Cim)  Dynamic Prune  Prediction Network  Vision Transformer (Vit)  
More Efficient and Locally Enhanced Transformer Conference paper
Zhu,Zhefeng, Qi,Ke, Zhou,Yicong, Chen,Wenbin, Zhang,Jingdong. More Efficient and Locally Enhanced Transformer[C]:Springer Science and Business Media Deutschland GmbH, 2023, 86-97.
Authors:  Zhu,Zhefeng;  Qi,Ke;  Zhou,Yicong;  Chen,Wenbin;  Zhang,Jingdong
Favorite | TC[Scopus]:1 | Submit date：2023/08/03
Efficient Self-attention  Image Recognition  Locally Enhanced  Vit  
A Local-Global Estimator based on Large Kernel CNN and Transformer for Human Pose Estimation and Running Pose Measurement Journal article
Qingtian Wu, Yongfei Wu, Yu Zhang, Liming Zhang. A Local-Global Estimator based on Large Kernel CNN and Transformer for Human Pose Estimation and Running Pose Measurement[J]. IEEE transactions on Instrumentation and Instrumentation & Measurement, 2022, 71, 1-12.
Authors:  Qingtian Wu;  Yongfei Wu;  Yu Zhang;  Liming Zhang
Favorite | TC[WOS]:0 TC[Scopus]:20  IF:5.6/5.6 | Submit date：2022/08/30
Convolutional Neural Networks (Cnn)  Human Pose Estimation (Hpe)  Local–global Estimator  Running Pose Measurement  Vision Transformer (Vit)