CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共53条,第1-10条 帮助

限定条件                
已选(0)清除 条数/页:   排序方式:
CLIP-VG: Self-Paced Curriculum Adapting of CLIP for Visual Grounding 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 4334-4347
作者:  Xiao, Linhui;  Yang, Xiaoshan;  Peng, Fang;  Yan, Ming;  Wang, Yaowei;  Xu, Changsheng
收藏  |  浏览/下载:0/0  |  提交时间:2024/05/30
Grounding  Reliability  Adaptation models  Task analysis  Visualization  Data models  Annotations  Visual grounding  curriculum learning  pseudo-language label  and vision-language models  
SPA2Net: Structure-Preserved Attention Activated Network for Weakly Supervised Object Localization 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 5779-5793
作者:  Chen, Dong;  Pan, Xingjia;  Tang, Fan;  Dong, Weiming;  Xu, Changsheng
收藏  |  浏览/下载:30/0  |  提交时间:2024/02/22
High-order self-correlation  class activation map  structure preservation  weakly supervised object localization  
Robust Video-Text Retrieval Via Noisy Pair Calibration 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 8632-8645
作者:  Zhang, Huaiwen;  Yang, Yang;  Qi, Fan;  Qian, Shengsheng;  Xu, Changsheng
收藏  |  浏览/下载:25/0  |  提交时间:2024/02/22
Noise calibration  uncertainty  video text retrieval  
SMNet: Synchronous Multi-Scale Low Light Enhancement Network With Local and Global Concern 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 9506-9517
作者:  Lin, Shideng;  Tang, Fan;  Dong, Weiming;  Pan, Xingjia;  Xu, Changsheng
收藏  |  浏览/下载:24/0  |  提交时间:2024/02/21
Low-light image enhancement  multi-scale feature learning  deep-learning  
Dual Structural Knowledge Interaction for Domain Adaptation 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 9057-9070
作者:  Zuo, Yukun;  Yao, Hantao;  Zhuang, Liansheng;  Xu, Changsheng
收藏  |  浏览/下载:27/0  |  提交时间:2024/02/21
Manifolds  Feature extraction  Adaptation models  Representation learning  Task analysis  Semisupervised learning  Pattern recognition  Domain adaptation  structural knowledge  dual structural knowledge interaction  
Reducing Vision-Answer Biases for Multiple-Choice VQA 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 4621-4634
作者:  Zhang, Xi;  Zhang, Feifei;  Xu, Changsheng
收藏  |  浏览/下载:44/0  |  提交时间:2023/11/17
Multiple-choice VQA  vision-answer bias  causal intervention  counterfactual interaction learning  
Zero-Shot Predicate Prediction for Scene Graph Parsing 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 3140-3153
作者:  Li, Yiming;  Yang, Xiaoshan;  Huang, Xuhui;  Ma, Zhe;  Xu, Changsheng
收藏  |  浏览/下载:135/0  |  提交时间:2023/11/17
Deep learning  zero-shot  scene graph  
Debiased Video-Text Retrieval via Soft Positive Sample Calibration 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 9, 页码: 5257-5270
作者:  Zhang, Huaiwen;  Yang, Yang;  Qi, Fan;  Qian, Shengsheng;  Xu, Changsheng
收藏  |  浏览/下载:68/0  |  提交时间:2023/11/16
debias  soft positive samples  
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:111/15  |  提交时间:2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection  
Weakly-Supervised Video Object Grounding Via Learning Uni-Modal Associations 期刊论文
IEEE Transactions on Multimedia, 2022, 卷号: 25, 页码: 1-12
作者:  Wang, Wei;  Gao, Junyu;  Xu, Changsheng
Adobe PDF(5406Kb)  |  收藏  |  浏览/下载:104/31  |  提交时间:2023/04/25
Visualization  Grounding  Task analysis  Prototypes  Annotations  Uncertainty  Proposals  Cross-modal retrieval  weakly-supervised learning  video object grounding  uni-modal association