CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共8条,第1-8条 帮助

限定条件            
已选(0)清除 条数/页:   排序方式:
AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models 会议论文
, VANCOUVER, CANADA, 2024-2-20至2024-2-27
作者:  Zhaopeng Gu;  Bingke Zhu;  Guibo Zhu;  Yingying Chen;  Ming Tang;  Jinqiao Wang
Adobe PDF(4846Kb)  |  收藏  |  浏览/下载:5/0  |  提交时间:2024/06/06
BFRFormer: Transformer-based generator for Real-World Blind Face Restoration 会议论文
, Seoul, Korea, 2024年4月14日到2024年4月19日
作者:  Guojing Ge;  Qi Song;  Guibo Zhu;  Yuting Zhang;  Jinglu Chen;  Miao Xin;  Ming Tang;  Jinqiao Wang
Adobe PDF(6872Kb)  |  收藏  |  浏览/下载:4/2  |  提交时间:2024/06/06
SlowFastFormer for 3D human pose estimation 期刊论文
Computer Vision and Image Understanding, 2024, 期号: 243, 页码: 103992
作者:  Zhou Lu;  Chen Yingying;  Wang Jinqiao
Adobe PDF(989Kb)  |  收藏  |  浏览/下载:7/3  |  提交时间:2024/06/03
Dual-Path Transformer for 3D Human Pose Estimation 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 卷号: 34, 期号: 5, 页码: 3260-3270
作者:  Zhou Lu;  Chen Yingying;  Wang Jinqiao
Adobe PDF(2410Kb)  |  收藏  |  浏览/下载:6/4  |  提交时间:2024/06/03
The Devil is in Details: Delving Into Lite FFN Design for Vision Transformers 会议论文
, Seoul, Korea, 2024-4-14
作者:  Chen, Zhiyang;  Zhu, Yousong;  Li, Zhaowen;  Yang, Fan;  Zhao, Chaoyang;  Wang, Jinqiao;  Tang, Ming
Adobe PDF(407Kb)  |  收藏  |  浏览/下载:11/4  |  提交时间:2024/05/28
Vision Transformer  Light-Weight Structure  Feed-Forward Networks  
Structural Dependence Learning Based on Self-attention for Face Alignment 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 3, 页码: 514-525
作者:  Biying Li;  Zhiwei Liu;  Wei Zhou;  Haiyun Guo;  Xin Wen;  Min Huang;  Jinqiao Wang
Adobe PDF(5139Kb)  |  收藏  |  浏览/下载:27/11  |  提交时间:2024/05/23
Computer vision, face alignment, self-attention, facial structure, contextual information  
ImFusion: Boosting Two-Stage 3D Object Detection via Image Candidates 期刊论文
IEEE SIGNAL PROCESSING LETTERS, 2024, 卷号: 31, 页码: 241-245
作者:  Tao, Manli;  Zhao, Chaoyang;  Wang, Jinqiao;  Tang, Ming
Adobe PDF(3506Kb)  |  收藏  |  浏览/下载:38/1  |  提交时间:2024/03/26
Three-dimensional displays  Proposals  Object detection  Feature extraction  Point cloud compression  Aggregates  Sun  3D object detection  image candidates  pseudo 3D proposal  target missing  
Objformer: Boosting 3D object detection via instance-wise interaction 期刊论文
PATTERN RECOGNITION, 2024, 卷号: 146, 页码: 9
作者:  Tao, Manli;  Zhao, Chaoyang;  Tang, Ming;  Wang, Jinqiao
Adobe PDF(3261Kb)  |  收藏  |  浏览/下载:114/3  |  提交时间:2024/02/22
3D object detection  Point clouds  Incompletion and occlusion  Instance-wise interaction