中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共12条，第1-10条 帮助

限定条件    
已选(0)清除 条数/页：   排序方式：
DomainFeat: Learning Local Features With Domain Adaptation 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 卷号: 34, 期号: 1, 页码: 46-59
作者:  Xu, Rongtao;  Wang, Changwei;  Xu, Shibiao;  Meng, Weiliang;  Zhang, Yuyang;  Fan, Bin;  Zhang, Xiaopeng
收藏  |  浏览/下载：13/0  |  提交时间：2024/03/26
Feature extraction  Location awareness  Visualization  Robustness  Image matching  Detectors  Decoding  Local features  domain adaptation  cross-domain data  consistency loss  
Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 9, 页码: 4616-4629
作者:  Ma, Chengcheng;  Liu, Yang;  Deng, Jiankang;  Xie, Lingxi;  Dong, Weiming;  Xu, Changsheng
Adobe PDF(1644Kb)  |  收藏  |  浏览/下载：92/12  |  提交时间：2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection  
Cross-Domain Person Re-Identification Using Heterogeneous Convolutional Network 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 卷号: 32, 期号: 3, 页码: 1160-1171
作者:  Zhang, Zhong;  Wang, Yanan;  Liu, Shuang;  Xiao, Baihua;  Durrani, Tariq S.
收藏  |  浏览/下载：197/0  |  提交时间：2022/06/06
Correlation  Feature extraction  Couplings  Convolution  Training  Cameras  Loss measurement  Cross-domain person re-identification  graph convolution network  dual graph convolution  
Bottom-Up Foreground-Aware Feature Fusion for Practical Person Search 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2021, 卷号: 0, 期号: 0, 页码: 0
作者:  Yang, Wenjie;  Huang, Houjing;  Chen, Xiaotang;  Huang, Kaiqi
Adobe PDF(38609Kb)  |  收藏  |  浏览/下载：190/51  |  提交时间：2021/06/21
Person Search, Person Re-Identification, Pedestrian Detection, Feature Learning, Attention  
Adversarial Deep Tracking 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2019, 卷号: 29, 期号: 7, 页码: 1998-2011
作者:  Zhao, Fei;  Wang, Jinqiao;  Wu, Yi;  Tang, Ming
浏览  |  Adobe PDF(6455Kb)  |  收藏  |  浏览/下载：290/99  |  提交时间：2019/04/30
Visual tracking  deep learning  adversarial training  attention  
Learning Stacked Image Descriptor for Face Recognition 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2016, 卷号: 26, 期号: 9, 页码: 1685-1696
作者:  Lei, Zhen;  Yi, Dong;  Li, Stan Z.
Adobe PDF(5197Kb)  |  收藏  |  浏览/下载：372/144  |  提交时间：2016/12/26
Deep Discriminant Face Representation  Face Recognition  Learning-based Descriptor  Stacked Image Descriptor (Sid)  
Multicamera Joint Video Synopsis 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2016, 卷号: 26, 期号: 6, 页码: 1058-1069
作者:  Zhu, Jianqing;  Liao, Shengcai;  Li, Stan Z.
Adobe PDF(5716Kb)  |  收藏  |  浏览/下载：292/78  |  提交时间：2016/09/30
Camera Network  Joint Video Synopsis (Jvs)  Video Surveillance  
Adaptive Slice Representation for Human Action Classification 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2015, 卷号: 25, 期号: 10, 页码: 1624-1636
作者:  Shan, Yanhu;  Zhang, Zhang;  Yang, Peipei;  Huang, Kaiqi;  Kaiqi Huang
浏览  |  Adobe PDF(2720Kb)  |  收藏  |  浏览/下载：349/103  |  提交时间：2015/11/12
Action Recognition  Adaptive Slice  Mel Frequency Cepstrum Coefficient (Mfcc)  Minimum Average Entropy (Minae)  
Image Tag Refinement With View-Dependent Concept Representations 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2015, 卷号: 25, 期号: 8, 页码: 1409-1422
作者:  Fu, Jianlong;  Wang, Jinqiao;  Rui, Yong;  Wang, Xin-Jing;  Mei, Tao;  Lu, Hanqing
浏览  |  Adobe PDF(3630Kb)  |  收藏  |  浏览/下载：435/97  |  提交时间：2015/09/23
Concept Representations  Image Tag Refinement  Image Tagging  
Scene Text Recognition Using Structure-Guided Character Detection and Linguistic Knowledge 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2014, 卷号: 24, 期号: 7, 页码: 1235-1250
作者:  Shi, CZ;  Wang, CH;  Xiao, BH;  Gao, S;  Hu, JL;  Wang Chunheng
浏览  |  Adobe PDF(2421Kb)  |  收藏  |  浏览/下载：270/70  |  提交时间：2015/08/12
Character Recognition  Cropped Word Recognition  Part-based Tree-structured Models (Tsms)