CASIA OpenIR

Browse/Search Results:  1-2 of 2 Help

Selected(0)Clear Items/Page:    Sort:
Multi-Modal Knowledge Representation Learning via Webly-Supervised Relationships Mining 会议论文
, Mountain View, CA, USA, 2017-10
Authors:  Fudong Nian (年福东);  Bing-Kun BAO;  Teng Li;  Changsheng Xu
View  |  Adobe PDF(7830Kb)  |  Favorite  |  View/Download:49/4  |  Submit date:2018/01/04
Learning explicit video attributes from mid-level representation for video captioning 期刊论文
COMPUTER VISION AND IMAGE UNDERSTANDING, 2017, 卷号: 163, 页码: 126-138
Authors:  Nian, Fudong;  Li, Teng;  Wang, Yan;  Wu, Xinyu;  Ni, Bingbing;  Xu, Changsheng
Favorite  |  View/Download:63/0  |  Submit date:2018/03/03
Mid-level Video Representation  Video Attributes Learning  Video Caption  Sequence-to-sequence Learning