CSpace

浏览/检索结果: 共3条,第1-3条 帮助

限定条件    
已选(0)清除 条数/页:   排序方式:
CLIP4Clip: An empirical study of CLIP for end to end video clip retrieval and captioning 期刊论文
NEUROCOMPUTING, 2022, 卷号: 508, 页码: 293-304
作者:  Luo, Huaishao;  Ji, Lei;  Zhong, Ming;  Chen, Yang;  Lei, Wen;  Duan, Nan;  Li, Tianrui
收藏  |  浏览/下载:30/0  |  提交时间:2022/12/07
Video retrieval  Video captioning  CLIP  
I(2)Transformer: Intra- and Inter-Relation Embedding Transformer for TV Show Captioning 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 3565-3577
作者:  Tu, Yunbin;  Li, Liang;  Su, Li;  Gao, Shengxiang;  Yan, Chenggang;  Zha, Zheng-Jun;  Yu, Zhengtao;  Huang, Qingming
收藏  |  浏览/下载:20/0  |  提交时间:2022/12/07
Transformers  Semantics  Task analysis  Visualization  TV  Electronic mail  Graph neural networks  TV Show captioning  video and subtitle  intra-relation embedding  inter-relation embedding  transformer  
Learning Representations for Facial Actions From Unlabeled Videos 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 卷号: 44, 期号: 1, 页码: 302-317
作者:  Li, Yong;  Zeng, Jiabei;  Shan, Shiguang
收藏  |  浏览/下载:22/0  |  提交时间:2022/06/21
Facial action unit detection  self-supervised learning  representation learning  feature disentanglement  encoder-decoder structure