中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共6条，第1-6条 帮助

限定条件                                
已选(0)清除 条数/页：   排序方式：
Cross-Architecture Knowledge Distillation 会议论文
INTERNATIONAL JOURNAL OF COMPUTER VISION, Macau SAR, China, 2022.12.4-2022.12.8
作者:  Yufan Liu;  Jiajiong Cao;  Bing Li;  Weiming Hu;  Jingting Ding;  Liang Li
Adobe PDF(1020Kb)  |  收藏  |  浏览/下载：162/46  |  提交时间：2023/04/23
Knowledge distillation  Cross architecture  Model compression  Deep learning  
Rethinking Pretraining as a Bridge From ANNs to SNNs 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 页码: 14
作者:  Lin, Yihan;  Hu, Yifan;  Ma, Shijie;  Yu, Dongjie;  Li, Guoqi
收藏  |  浏览/下载：322/0  |  提交时间：2023/03/20
Training  Task analysis  Neurons  Pipelines  Artificial neural networks  Feature extraction  Transfer learning  Event-driven dataset  neural network (NN) analysis  pretraining technique  spiking NN (SNN)  transfer learning  
Narrowing the Gap: Improved Detector Training With Noisy Location Annotations 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 6369-6380
作者:  Wang, Shaoru;  Gao, Jin;  Li, Bing;  Hu, Weiming
Adobe PDF(1489Kb)  |  收藏  |  浏览/下载：272/33  |  提交时间：2022/11/14
Annotations  Noise measurement  Detectors  Task analysis  Training  Object detection  Degradation  Object detection  noisy label  Bayesian estimation  teacher-student learning  
PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling 期刊论文
IEEE Transactions on Image Processing, 2022, 卷号: 31, 页码: 5121-5133
作者:  Yang, Li;  Xu, Yan;  Wang, Shaoru;  Yuan, Chunfeng;  Zhang, Ziqi;  Li, Bing;  Hu, Weiming
Adobe PDF(3190Kb)  |  收藏  |  浏览/下载：314/40  |  提交时间：2022/09/19
Object detection  prediction decoupling  convolutional neural network  
Explicit Cross-Modal Representation Learning for Visual Commonsense Reasoning 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 24, 页码: 2986-2997
作者:  Zhang, Xi;  Zhang, Feifei;  Xu, Changsheng
Adobe PDF(5681Kb)  |  收藏  |  浏览/下载：396/0  |  提交时间：2022/07/25
Cognition  Video recording  Syntactics  Visualization  Task analysis  Semantics  Linguistics  Visual Commonsense Reasoning  explicit reasoning  syntactic structure  interpretability  
Holographic Feature Learning of Egocentric-Exocentric Videos for Multi-Domain Action Recognition 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 24, 页码: 2273-2286
作者:  Huang, Yi;  Yang, Xiaoshan;  Gao, Junyun;  Xu, Changsheng
Adobe PDF(2409Kb)  |  收藏  |  浏览/下载：365/73  |  提交时间：2022/07/25
Videos  Feature extraction  Visualization  Task analysis  Computational modeling  Target recognition  Prototypes  Egocentric videos  exocentric videos  holographic feature  multi-domain  action recognition