CASIA OpenIR

Browse/Search Results:  1-10 of 180 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
Ensemble Quadratic Assignment Network for Graph Matching 期刊论文
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2024, 页码: 23
Authors:  Tan, Haoru;  Wang, Chuang;  Wu, Sitong;  Zhang, Xu-Yao;  Yin, Fei;  Liu, Cheng-Lin
Favorite  |  View/Download:16/0  |  Submit date:2024/07/03
Graph matching  Combinatorial optimization  Graph neural network  Ensemble learning  
基于单应性扩散约束的二步网格优化视差图像对齐 期刊论文
自动化学报, 2024, 卷号: 50, 期号: 6, 页码: 1129-1142
Authors:  陈殷齐;  郑慧诚;  严志伟;  林峻宇
Adobe PDF(70190Kb)  |  Favorite  |  View/Download:7/1  |  Submit date:2024/07/02
图像对齐  视差场景  网格优化  匹配特征缺失区域  
An Approach for Handwritten Chinese Text Recognition Unifying Character Segmentation and Recognition 期刊论文
Pattern Recognition, 2024, 页码: 110373
Authors:  MingMing Yu(于明明);  Zhang H(张恒);  Fei Yin(殷飞);  Cheng-Lin Liu(刘成林)
Adobe PDF(5849Kb)  |  Favorite  |  View/Download:46/16  |  Submit date:2024/06/24
Deep Metric Learning with Cross-Writer Attention for Offline Signature Verification 期刊论文
ICDAR2024, 2024, 页码: 1
Authors:  Ling LR(凌禄蓉);  Zhang H(张恒);  Yin F(殷飞);  Liu CL(刘成林)
Adobe PDF(520Kb)  |  Favorite  |  View/Download:40/10  |  Submit date:2024/06/24
Social Relation Reasoning Based on Triangular Constraints 会议论文
, 美国华盛顿, 2023年2月7日-14日
Authors:  Guo, Yunfei;  Yin, Fei;  Feng, Wei;  Yan, Xudong;  Xue, Tao;  Mei, Shuqi;  Liu, Cheng-Lin
Adobe PDF(977Kb)  |  Favorite  |  View/Download:63/23  |  Submit date:2024/06/13
Visual Traffic Knowledge Graph Generation from Scene Images 会议论文
, 法国巴黎, 2023年10月2日-6日
Authors:  Guo, Yunfei;  Yin, Fei;  Li, Xiao-Hui;  Yan, Xudong;  Xue, Tao;  Mei, Shuqi;  Liu, Cheng-Lin
Adobe PDF(2506Kb)  |  Favorite  |  View/Download:62/23  |  Submit date:2024/06/13
Learning to Understand Traffic Signs 会议论文
, 四川成都, 2021年10月20日-24日
Authors:  Guo, Yunfei;  Feng, Wei;  Yin, Fei;  Xue, Tao;  Mei, Shuqi;  Liu, Cheng-Lin
Adobe PDF(3271Kb)  |  Favorite  |  View/Download:49/21  |  Submit date:2024/06/13
traffic sign understanding  semantic description  multi-task learning  
GraphMLLM: A Graph-based Multi-level Layout Language-independent Model for Document Understanding 会议论文
, 希腊雅典, 2024-09
Authors:  He-Sen Dai;  Xiao-Hui Li;  Fei Yin;  Xudong Yan;  Shuqi Mei;  Cheng-Lin Liu
Adobe PDF(967Kb)  |  Favorite  |  View/Download:52/12  |  Submit date:2024/06/05
Visual information extraction  Self-supervised pre-training  Multi-level page layouts  
Diff-Writer: A Diffusion Model-Based Stylized Online Handwritten Chinese Character Generator 会议论文
, 湖南省 长沙市, 2023-11
Authors:  Ren MS(任敏思);  Zhang YM(张燕明);  Wang QF(王秋锋);  Yin F(殷飞);  Liu CL(刘成林)
Adobe PDF(64745Kb)  |  Favorite  |  View/Download:61/9  |  Submit date:2024/05/31
Generative model  
Cross-modal Prototype Learning for Zero-shot Handwriting Recognition 会议论文
, Sydney, Australia, 20-25 Septemper 2019
Authors:  Ao, Xiang;  Zhang, Xu-Yao;  Yang, Hong-Ming;  Yin, Fei;  Liu, Cheng-Lin
Adobe PDF(226Kb)  |  Favorite  |  View/Download:56/26  |  Submit date:2024/05/30
printed character  handwritten character  cross-modal  prototype learning  zero-shot