CASIA OpenIR

Browse/Search Results:  1-7 of 7 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
Self-Supervised Representation Learning from Arbitrary Scenarios 会议论文
, 美国西雅图, 2024
Authors:  Li, Zhaowen;  Zhu, Yousong;  Chen, Zhiyang;  Gao, Zongxin;  Zhao, Chaoyang;  Zhao, Rui;  Tang, Ming;  Wang, Jinqiao
Adobe PDF(7423Kb)  |  Favorite  |  View/Download:64/26  |  Submit date:2024/05/30
Mst: Masked self-supervised transformer for visual representation 会议论文
, 北京(虚拟会议), 2021
Authors:  Li, Zhaowen;  Chen, Zhiyang;  Yang, Fan;  Li, Wei;  Zhu, Yousong;  Zhao, Chaoyang;  Zhao, Rui;  Deng, Rui;  Tang, Ming;  Wang, Jinqiao
Adobe PDF(1021Kb)  |  Favorite  |  View/Download:51/13  |  Submit date:2024/05/30
基于序列自注意机制的通用视觉模型研究 学位论文
, 2024
Authors:  陈志扬
Adobe PDF(16306Kb)  |  Favorite  |  View/Download:84/8  |  Submit date:2024/05/29
图像识别  注意力机制  基础视觉模型  通用视觉模型  
The Devil is in Details: Delving Into Lite FFN Design for Vision Transformers 会议论文
, Seoul, Korea, 2024-4-14
Authors:  Chen, Zhiyang;  Zhu, Yousong;  Li, Zhaowen;  Yang, Fan;  Zhao, Chaoyang;  Wang, Jinqiao;  Tang, Ming
Adobe PDF(407Kb)  |  Favorite  |  View/Download:55/16  |  Submit date:2024/05/28
Vision Transformer  Light-Weight Structure  Feed-Forward Networks  
Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks 会议论文
, New Orleans, Louisiana & Online, 2022-11-28
Authors:  Chen, Zhiyang;  Zhu, Yousong;  Li, Zhaowen;  Yang, Fan;  Li, Wei;  Wang, Haixin;  Zhao, Chaoyang;  Wu, Liwei;  Zhao, Rui;  Wang, Jinqiao;  Tang, Ming
Adobe PDF(1289Kb)  |  Favorite  |  View/Download:38/10  |  Submit date:2024/05/28
transformer  general visual framework  sequence prediction  multi-task  
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training 会议论文
, New Orleans, Louisiana & Online, 2022-6-19
Authors:  Li, Zhaowen;  Zhu, Yousong;  Yang, Fan;  Li, Wei;  Zhao, Chaoyang;  Chen, Yingying;  Chen, Zhiyang;  Xie, Jiahao;  Wu, Liwei;  Zhao, Rui;  Tang, Ming;  Wang, Jinqiao
Adobe PDF(1929Kb)  |  Favorite  |  View/Download:345/56  |  Submit date:2022/04/01
DPT: Deformable Patch-based Transformer for Visual Recognition 会议论文
, Chengdu, China, 2021-10-20
Authors:  Chen,Zhiyang;  Zhu, Yousong;  Zhao,Chaoyang;  Hu, Guosheng;  Zeng, Wei;  Wang, Jinqiao;  Tang, Ming
Adobe PDF(3799Kb)  |  Favorite  |  View/Download:228/37  |  Submit date:2022/04/01