中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共5条，第1-5条 帮助

限定条件    
已选(0)清除 条数/页：   排序方式：
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：78/11  |  提交时间：2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection  
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：186/51  |  提交时间：2021/06/21
Person Search, Person Re-Identification, Pedestrian Detection, Feature Learning, Attention  
Deep Hybrid Similarity Learning for Person Re-Identification 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2018, 卷号: 28, 期号: 11, 页码: 3183-3193
作者:  Zhu JQ(朱建清);  Huanqiang Zeng;  Liao SC(廖胜才);  Lei Z(雷震);  Canhui Cai;  Li Xin Zheng
收藏  |  浏览/下载：261/0  |  提交时间：2018/02/26
Metric learning  convolution neural network  deep hybrid similarity learning  person re-identification (Re-ID)  
Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2017, 卷号: 27, 期号: 6, 页码: 1263-1274
作者:  Xie, Guo-Sen;  Zhang, Xu-Yao;  Yan, Shuicheng;  Liu, Cheng-Lin
浏览  |  Adobe PDF(5307Kb)  |  收藏  |  浏览/下载：493/160  |  提交时间：2016/07/14
Convolutional Neural Networks (Cnns)  Dictionary  Domain ADaptation (Da)  Fisher Vector  Part Learning  Scene Recognition  
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：364/144  |  提交时间：2016/12/26
Deep Discriminant Face Representation  Face Recognition  Learning-based Descriptor  Stacked Image Descriptor (Sid)