CASIA OpenIR

Browse/Search Results:  1-10 of 3829 Help

Selected(0)Clear Items/Page:    Sort:
Towards Noiseless Object Contours for Weakly Supervised Semantic Segmentation 会议论文
, New Orleans, 2022.6.19-2022.6.24
Authors:  Li, Jing;  Fan, Junsong;  Zhang, Zhaoxiang
Adobe PDF(2241Kb)  |  Favorite  |  View/Download:4/1  |  Submit date:2024/07/24
Segmentation, Weakly Supervised, Contour  
Fully Data-Driven Pseudo Label Estimation for Pointly-Supervised Panoptic Segmentation 会议论文
, Vancouver, 2024.2.22-2024.2.25
Authors:  Li, Jing;  Fan, Junsong;  Yang, Yuran;  Mei, Shuqi;  Xiao, Jun;  Zhang, Zhaoxiang
Adobe PDF(2720Kb)  |  Favorite  |  View/Download:9/4  |  Submit date:2024/07/24
Panoptic Segmentation  Pointly-Supervised  Pseudo Label Estimation  Data-Driven  
Hierarchical Attention Network for Open-Set Fine-Grained Image Recognition 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 卷号: 34, 期号: 5, 页码: 3891-3904
Authors:  Sun, Jiayin;  Wang, Hong;  Dong, Qiulei
Favorite  |  View/Download:2/0  |  Submit date:2024/07/22
Transformers  Feature extraction  Task analysis  Image recognition  Training  Visualization  Computer vision  Open-set fine-grained image recognition  hierarchical attention  long-short term memory  
基于Transformer的几何基元检测与分析 学位论文
, 2024
Authors:  周威
Adobe PDF(10067Kb)  |  Favorite  |  View/Download:30/5  |  Submit date:2024/07/21
基元检测  关系分析  关键点  Transformer  
A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 4, 页码: 801-814
Authors:  Feng Sun;  Ming-Kun Xie;  Sheng-Jun Huang
Adobe PDF(1337Kb)  |  Favorite  |  View/Download:24/7  |  Submit date:2024/07/18
Partial multi-label image classification  curriculum-based disambiguation  consistency regularization  label difficulty  candidate label set.  
Learning Top-K Subtask Planning Tree Based on Discriminative Representation Pretraining for Decision-making 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 4, 页码: 782-800
Authors:  Jingqing Ruan;   Kaishen Wang;   Qingyang Zhang;   Dengpeng Xing;   Bo Xu
Adobe PDF(4577Kb)  |  Favorite  |  View/Download:12/4  |  Submit date:2024/07/18
Reinforcement learning  representation learning  subtask planning  task decomposition  pretraining.  
ReChoreoNet: Repertoire-based Dance Re-choreography with Music-conditioned Temporal and Style Clues 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 4, 页码: 771-781
Authors:  Ho Yin Au;  Jie Chen;  Junkun Jiang;  Yike Guo
Adobe PDF(2161Kb)  |  Favorite  |  View/Download:11/3  |  Submit date:2024/07/18
Generative model  cross-modality learning  normalizing flow  tempo synchronization  style transfer  
Toward Human-centered XAI in Practice: A survey 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 4, 页码: 740-770
Authors:  Xiangwei Kong;  Shujie Liu;  Luhao Zhu
Adobe PDF(1550Kb)  |  Favorite  |  View/Download:11/1  |  Submit date:2024/07/18
Artificial intelligence (AI) application  explainable AI (XAI)  human-centered design  visual computing  medical diagnosis  
Interpretability of Neural Networks Based on Game-theoretic Interactions 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 4, 页码: 718-739
Authors:  Huilin Zhou;   Jie Ren;   Huiqi Deng;   Xu Cheng;  Jinpeng Zhang;   Quanshi Zhang
Adobe PDF(2984Kb)  |  Favorite  |  View/Download:13/3  |  Submit date:2024/07/18
Model interpretability and transparency  explainable AI  game theory  interaction  deep learning  
TextFormer: A Query-based End-to-end Text Spotter with Mixed Supervision 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 4, 页码: 704-717
Authors:  Yukun Zhai;   Xiaoqiang Zhang;   Xiameng Qin;   Sanyuan Zhao;  Xingping Dong;   Jianbing Shen
Adobe PDF(2312Kb)  |  Favorite  |  View/Download:15/5  |  Submit date:2024/07/18
End-to-end text spotting  arbitrarily-shaped texts  transformer  mixed supervision  multitask modeling