CSpace

浏览/检索结果: 共23条,第1-10条 帮助

已选(0)清除 条数/页:   排序方式:
DyPipe: A Holistic Approach to Accelerating Dynamic Neural Networks with Dynamic Pipelining 期刊论文
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2023, 卷号: 38, 期号: 4, 页码: 899-910
作者:  Zhuang, Yi-Min;  Hu, Xing;  Chen, Xiao-Bing;  Zhi, Tian
收藏  |  浏览/下载:9/0  |  提交时间:2024/05/20
dynamic neural network (NN)  deep neural network (DNN) accelerator  dynamic pipelining  
Viewpoint Alignment and Discriminative Parts Enhancement in 3D Space for Vehicle ReID 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 2954-2965
作者:  Meng, Dechao;  Li, Liang;  Liu, Xuejing;  Gao, Lin;  Huang, Qingming
收藏  |  浏览/下载:15/0  |  提交时间:2023/12/04
3D reconstruction  feature enhancement  vehicle ReID  viewpoint alignment  
Rubik: A Hierarchical Architecture for Efficient Graph Neural Network Training 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2022, 卷号: 41, 期号: 4, 页码: 936-949
作者:  Chen, Xiaobing;  Wang, Yuke;  Xie, Xinfeng;  Hu, Xing;  Basak, Abanti;  Liang, Ling;  Yan, Mingyu;  Deng, Lei;  Ding, Yufei;  Du, Zidong;  Xie, Yuan
收藏  |  浏览/下载:32/0  |  提交时间:2022/12/07
Deep learning accelerator  graph neural network (GNN)  
Syntax-Guided Hierarchical Attention Network for Video Captioning 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 卷号: 32, 期号: 2, 页码: 880-892
作者:  Deng, Jincan;  Li, Liang;  Zhang, Beichen;  Wang, Shuhui;  Zha, Zhengjun;  Huang, Qingming
收藏  |  浏览/下载:27/0  |  提交时间:2022/12/07
Syntactics  Feature extraction  Visualization  Generators  Semantics  Two dimensional displays  Three-dimensional displays  Video captioning  syntax attention  content attention  global sentence-context  
Age-Invariant Face Recognition by Multi-Feature Fusion and Decomposition with Self-attention 期刊论文
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2022, 卷号: 18, 期号: 1, 页码: 18
作者:  Yan, Chenggang;  Meng, Lixuan;  Li, Liang;  Zhang, Jiehua;  Wang, Zhan;  Yin, Jian;  Zhang, Jiyong;  Sun, Yaoqi;  Zheng, Bolun
收藏  |  浏览/下载:34/0  |  提交时间:2022/12/07
Age-invariant face recognition  feature fusion  feature decomposition  self-attention  
Task-Adaptive Attention for Image Captioning 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 卷号: 32, 期号: 1, 页码: 43-51
作者:  Yan, Chenggang;  Hao, Yiming;  Li, Liang;  Yin, Jian;  Liu, Anan;  Mao, Zhendong;  Chen, Zhenyu;  Gao, Xingyu
收藏  |  浏览/下载:25/0  |  提交时间:2022/12/07
Task analysis  Visualization  Feature extraction  Decoding  Computational modeling  Adaptation models  Feeds  Image captioning  attention mechanism  transformer  
Breaking the Interaction Wall: A DLPU-Centric Deep Learning Computing System 期刊论文
IEEE TRANSACTIONS ON COMPUTERS, 2022, 卷号: 71, 期号: 1, 页码: 209-222
作者:  Du, Zidong;  Guo, Qi;  Zhao, Yongwei;  Zeng, Xi;  Li, Ling;  Cheng, Limin;  Xu, Zhiwei;  Sun, Ninghui;  Chen, Yunji
收藏  |  浏览/下载:41/0  |  提交时间:2022/06/21
Deep learning  Central Processing Unit  Process control  Task analysis  Computational modeling  Pipelines  Runtime  Neural net accelerators  system architectures  interaction wall  
Cambricon-G: A Polyvalent Energy-Efficient Accelerator for Dynamic Graph Neural Networks 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2022, 卷号: 41, 期号: 1, 页码: 116-128
作者:  Song, Xinkai;  Zhi, Tian;  Fan, Zhe;  Zhang, Zhenxing;  Zeng, Xi;  Li, Wei;  Hu, Xing;  Du, Zidong;  Guo, Qi;  Chen, Yunji
收藏  |  浏览/下载:37/0  |  提交时间:2022/06/21
Accelerator  architecture  graph neural networks (GNNs)  
Local-binarized very deep residual network for visual categorization 期刊论文
NEUROCOMPUTING, 2021, 卷号: 430, 页码: 82-93
作者:  Liu, Xuejing;  Li, Liang;  Wang, Shuhui;  Zha, Zheng-Jun;  Huang, Qingming
收藏  |  浏览/下载:48/0  |  提交时间:2021/12/01
Network compression and acceleration  Pose estimation  Object recognition  Saliency detection  Local binary residual block  
Graph Regularized Encoder-Decoder Networks for Image Representation Learning 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 3124-3136
作者:  Yang, Shijie;  Li, Liang;  Wang, Shuhui;  Zhang, Weigang;  Huang, Qingming;  Tian, Qi
收藏  |  浏览/下载:45/0  |  提交时间:2021/12/01
Laplace equations  Visualization  Manifolds  Image reconstruction  Task analysis  Decoding  Semantics  Auto-encoder  encoder-decoder  graph regularizer  image representation learning