CASIA OpenIR

Browse/Search Results:  1-10 of 337 Help

Selected(0)Clear Items/Page:    Sort:
ZBS:Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection 会议论文
, 加拿大温哥华, 2023-6-18到2023-6-22
Authors:  安永琪;  赵旭;  于涛;  郭海云;  赵朝阳;  唐明;  王金桥
Adobe PDF(4738Kb)  |  Favorite  |  View/Download:27/6  |  Submit date:2023/04/25
面向非结构化场景的日常物品抓取 学位论文
, 2023
Authors:  郑力铭
Adobe PDF(25181Kb)  |  Favorite  |  View/Download:10/0  |  Submit date:2023/05/29
机器人抓取  深度学习  领域自适应  虚实迁移  抓取视角搜索  
深度学习中的视觉对抗攻击方法研究 学位论文
, 2023
Authors:  何子文
Adobe PDF(13003Kb)  |  Favorite  |  View/Download:21/2  |  Submit date:2023/05/26
对抗攻击  对抗样本  深度神经网络  人工智能安全  
多模态超声时空特征互作融合智能分析算法及其辅助临床诊断研究 学位论文
, 2023
Authors:  孟哲令
Adobe PDF(10969Kb)  |  Favorite  |  View/Download:22/1  |  Submit date:2023/05/18
多模态超声影像  互作融合  人工智能辅助临床诊断  多步模态融合网络  层次化诊断网络  
VLP: A Survey on Vision-language Pre-training 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 1, 页码: 38-56
Authors:  Fei-Long Chen
Adobe PDF(1427Kb)  |  Favorite  |  View/Download:51/6  |  Submit date:2023/01/18
Vision and language  pre-training  transformers  multimodal learning  representation learning  
Parallel Learning: Overview and Perspective for Computational Learning Across Syn2Real and Sim2Real 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 3, 页码: 603-631
Authors:  Qinghai Miao;  Yisheng Lv;  Min Huang;  Xiao Wang;  Fei-Yue Wang
Adobe PDF(11937Kb)  |  Favorite  |  View/Download:35/4  |  Submit date:2023/03/02
Machine learning  parallel learning  parallel systems  sim-to-real  syn-to-real  virtual-to-real  
Contrastive Learning for Blind Super-Resolution via A Distortion-Specific Network 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 1, 页码: 78-89
Authors:  Xinya Wang;  Jiayi Ma;  Junjun Jiang
Adobe PDF(11082Kb)  |  Favorite  |  View/Download:35/3  |  Submit date:2023/01/03
Blind super-resolution  contrastive learning  deep learning  image super-resolution (SR)  
Axial Assembled Correspondence Network for Few-Shot Semantic Segmentation 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 3, 页码: 711-721
Authors:  Yu Liu;  Bin Jiang;  Jiaming Xu
Adobe PDF(3290Kb)  |  Favorite  |  View/Download:19/3  |  Submit date:2023/03/02
Artificial intelligence  computer vision  deep convolutional neural network  few-shot semantic segmentation  
A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 5, 页码: 1122-1136
Authors:  Tianyu Wu;  Shizhu He;  Jingping Liu;  Siqi Sun;  Kang Liu;  Qing-Long Han;  Yang Tang
Adobe PDF(4650Kb)  |  Favorite  |  View/Download:10/0  |  Submit date:2023/04/26
AIGC  ChatGPT  GPT-3  GPT-4  human feedback  large language models  
Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 5, 页码: 1192-1208
Authors:  Zheyun Qin;  Xiankai Lu;  Xiushan Nie;  Dongfang Liu;  Yilong Yin;  Wenguan Wang
Adobe PDF(42794Kb)  |  Favorite  |  View/Download:6/0  |  Submit date:2023/04/26
Embedding learning  generative model  normalizing flows  video instance segmentation (VIS)