CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共2条,第1-2条 帮助

限定条件                                
已选(0)清除 条数/页:   排序方式:
Multi-Stage Image-Language Cross-Generative Fusion Network for Video-Based Referring Expression Comprehension 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 卷号: 33, 页码: 3256-3270
作者:  Zhang, Yujia;  Li, Qianzhong;  Pan, Yi;  Zhao, Xiaoguang;  Tan, Min
收藏  |  浏览/下载:2/0  |  提交时间:2024/07/03
Feature extraction  Visualization  Task analysis  Representation learning  Location awareness  Linguistics  Grounding  Video-based referring expression comprehension  multi-stage learning  image-language cross-generative fusion  consistency loss  
Visual enhanced hierarchical network for sentence-based video thumbnail generation 期刊论文
APPLIED INTELLIGENCE, 2023, 页码: 17
作者:  Wu, Junxian;  Zhang, Yujia;  Zhao, Xiaoguang
收藏  |  浏览/下载:75/0  |  提交时间:2023/11/17
Video thumbnail  DVTG task  Multi-modal fusion  Visual information  Hierarchical multi-layer perceptions