CASIA OpenIR

浏览/检索结果: 共14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:78/11  |  提交时间:2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection  
Face swapping detection based on identity spatial constraints with weighted frequency division 期刊论文
MULTIMEDIA SYSTEMS, 2022, 页码: 14
作者:  Ai, Zupeng;  Peng, Chengwei;  Jiang, Jun;  Li, Zekun;  Li, Bing
收藏  |  浏览/下载:165/0  |  提交时间:2022/11/14
Face swapping  Face manipulation  Frequency division  Identity constraints  
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:185/23  |  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  
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  
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:77/21  |  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  
Partial NIR-VIS Heterogeneous Face Recognition With Automatic Saliency Search 期刊论文
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2021, 卷号: 16, 页码: 5003-5017
作者:  Luo, Mandi;  Ma, Xin;  Li, Zhihang;  Cao, Jie;  He, Ran
Adobe PDF(4346Kb)  |  收藏  |  浏览/下载:239/52  |  提交时间:2021/12/28
Face recognition  Task analysis  Visualization  Image recognition  Lighting  Feature extraction  Training  Heterogeneous face recognition  near infrared-visible matching  information bottleneck  neural architecture search  
Visual Question Answering With Dense Inter- and Intra-Modality Interactions 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 3518-3529
作者:  Liu, Fei;  Liu, Jing;  Fang, Zhiwei;  Hong, Richang;  Lu, Hanqing
Adobe PDF(2891Kb)  |  收藏  |  浏览/下载:247/55  |  提交时间:2021/12/28
Visualization  Knowledge discovery  Connectors  Encoding  Task analysis  Image coding  Stacking  Visual question answering  attention  dense interactions  
Distractor-aware discrimination learning for online multiple object tracking 期刊论文
PATTERN RECOGNITION, 2020, 期号: 107, 页码: 10
作者:  Zhou, Zongwei;  Luo, Wenhan;  Wang, Qiang;  Xing, Junliang;  Hu, Weiming
Adobe PDF(840Kb)  |  收藏  |  浏览/下载:342/105  |  提交时间:2020/08/31
Multi-object tracking  Distractor-aware discrimination learning  Relational attention learning  
Show, Tell, and Polish: Ruminant Decoding for Image Captioning 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 卷号: 22, 期号: 8, 页码: 2149-2162
作者:  Guo, Longteng;  Liu, Jing;  Lu, Shichen;  Lu, Hanqing
Adobe PDF(4378Kb)  |  收藏  |  浏览/下载:197/28  |  提交时间:2020/08/31
Image captioning  Multi-pass decoding  Rumination  
MGCN: Descriptor Learning using Multiscale GCNs 期刊论文
ACM TRANSACTIONS ON GRAPHICS, 2020, 卷号: 39, 期号: 4, 页码: 15
作者:  Wang, Yiqun;  Ren, Jing;  Yan, Dong-Ming;  Guo, Jianwei;  Zhang, Xiaopeng;  Wonka, Peter
Adobe PDF(32624Kb)  |  收藏  |  浏览/下载:289/14  |  提交时间:2021/01/06
Multiscale  Energy Decomposition  Wavelet Convolution  Shape Matching