CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共70条,第1-10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:79/11  |  提交时间:2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection  
Recovering Generalization via Pre-training-like Knowledge Distillation for Out-of-Distribution Visual Question Answering 期刊论文
IEEE Transactions on Multimedia, 2023, 页码: 1-15
作者:  Song, Yaguang;  Yang, Xiaoshan;  Wang, Yaowei;  Xu, Changsheng
Adobe PDF(2397Kb)  |  收藏  |  浏览/下载:151/41  |  提交时间:2023/06/12
Multi-modal Foundation Model  Out-of-Distribution Generalization  Visual Question Answering  Knowledge Distillation  
Weakly-supervised video object grounding via causal intervention 期刊论文
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 卷号: 45, 期号: 3, 页码: 3933 - 3948
作者:  Wang, Wei;  Gao, Junyu;  Xu, Changsheng
Adobe PDF(4558Kb)  |  收藏  |  浏览/下载:119/50  |  提交时间:2023/04/25
Spatial-Temporal Exclusive Capsule Network for Open Set Action Recognition 期刊论文
IEEE Transactions on Multimedia, 2023, 卷号: 0, 期号: 0, 页码: 1-16
作者:  Feng, Yangbo;  Gao, Junyu;  Yang, Shicai;  Xu, Changsheng
收藏  |  浏览/下载:52/0  |  提交时间:2023/04/25
Towards Corruption-Agnostic Robust Domain Adaptation 期刊论文
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2022, 卷号: 18, 期号: 4, 页码: 16
作者:  Xu, Yifan;  Sheng, Kekai;  Dong, Weiming;  Wu, Baoyuan;  Xu, Changsheng;  Hu, Bao-Gang
Adobe PDF(2116Kb)  |  收藏  |  浏览/下载:370/82  |  提交时间:2022/06/10
Domain adaptation  corruption robustness  transfer learning  
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:287/61  |  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  
StyTr2: Image Style Transfer with Transformers 会议论文
, New Orleans, Louisiana, 2022-6
作者:  Deng, Yingying;  Tang, Fan;  Dong, Weiming;  Ma, Chongyang;  Pan, Xingjia;  Wang, Lei;  Xu, Changsheng
Adobe PDF(10025Kb)  |  收藏  |  浏览/下载:212/28  |  提交时间:2022/06/14
Many Hands Make Light Work: Transferring Knowledge from Auxiliary Tasks for Video-Text Retrieval 期刊论文
IEEE Transactions on Multimedia, 2022, 页码: 1-15
作者:  Wang, Wei;  Gao, Junyu;  Yang, Xiaoshan;  Xu, Changsheng
Adobe PDF(3679Kb)  |  收藏  |  浏览/下载:90/17  |  提交时间:2023/04/25
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:78/21  |  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  
Transformers in computational visual media: A survey 期刊论文
Computational Visual Media, 2021, 卷号: 8, 期号: 1, 页码: 33-62
作者:  Xu,Yifan;  Wei,Huapeng;  Lin,Minxuan;  Deng,Yingying;  Sheng,Kekai;  Zhang,Mengdan;  Tang,Fan;  Dong,Weiming;  Huang,Feiyue;  Xu,Changsheng
Adobe PDF(5366Kb)  |  收藏  |  浏览/下载:246/32  |  提交时间:2021/12/28
visual transformer  computational visual media (CVM)  high-level vision  low-level vision  image generation  multi-modal learning