CASIA OpenIR

浏览/检索结果: 共15条,第1-10条 帮助

限定条件                    
已选(0)清除 条数/页:   排序方式:
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
作者:  Yukun Zhai;   Xiaoqiang Zhang;   Xiameng Qin;   Sanyuan Zhao;  Xingping Dong;   Jianbing Shen
Adobe PDF(2312Kb)  |  收藏  |  浏览/下载:13/5  |  提交时间:2024/07/18
End-to-end text spotting  arbitrarily-shaped texts  transformer  mixed supervision  multitask modeling  
Cogeneration of Innovative Audio-visual Content: A New Challenge for Computing Art 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 1, 页码: 4-28
作者:  Mengting Liu;  Ying Zhou;  Yuwei Wu;  Feng Gao
Adobe PDF(14438Kb)  |  收藏  |  浏览/下载:63/9  |  提交时间:2024/04/23
Artificial intelligence (AI) art, audio-visual, artificial intelligence generated content (AIGC), multimodal, artistic evaluation  
Multitask Learning with Multiscale Residual Attention for Brain Tumor Segmentation and Classification 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 6, 页码: 897-908
作者:  Gaoxiang Li;  Xiao Hui;  Wenjing Li;  Yanlin Luo
Adobe PDF(2873Kb)  |  收藏  |  浏览/下载:55/16  |  提交时间:2024/04/23
Brain tumor segmentation and classification, multitask learning, multiscale residual attention module (MRAM), dynamic weight training, prior knowledge  
A Survey on Collaborative DNN Inference for Edge Intelligence 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 3, 页码: 370-395
作者:  Wei-Qing Ren;  Yu-Ben Qu;  Chao Dong;  Yu-Qian Jing;  Hao Sun;  Qi-Hui Wu;  Song Guo
Adobe PDF(2969Kb)  |  收藏  |  浏览/下载:55/16  |  提交时间:2024/04/23
Artificial intelligence (AI), edge intelligence (EI), distributed computing, deep neural network (DNN), collaborative inference  
针对身份证文本识别的黑盒攻击算法研究 期刊论文
自动化学报, 2024, 卷号: 50, 期号: 1, 页码: 103-120
作者:  徐昌凯;  冯卫栋;  张淳杰;  郑晓龙;  张辉;  王飞跃
Adobe PDF(20872Kb)  |  收藏  |  浏览/下载:91/27  |  提交时间:2024/04/12
对抗样本  黑盒攻击  身份证文本识别  物理世界  二值化掩码  
How Generative Adversarial Networks Promote the Development of Intelligent Transportation Systems: A Survey 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 9, 页码: 1781-1796
作者:  Hongyi Lin;  Yang Liu;  Shen Li;  Xiaobo Qu
Adobe PDF(1497Kb)  |  收藏  |  浏览/下载:232/140  |  提交时间:2023/08/10
Autonomous driving  generative adversarial network (GAN)  intelligent transportation system (ITS)  traffic anomaly inspection  traffic flow  
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
作者:  Tianyu Wu;  Shizhu He;  Jingping Liu;  Siqi Sun;  Kang Liu;  Qing-Long Han;  Yang Tang
Adobe PDF(4650Kb)  |  收藏  |  浏览/下载:886/705  |  提交时间:2023/04/26
AIGC  ChatGPT  GPT-3  GPT-4  human feedback  large language models  
Squeezing More Past Knowledge for Online Class-Incremental Continual Learning 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 3, 页码: 722-736
作者:  Da Yu;  Mingyi Zhang;  Mantian Li;  Fusheng Zha;  Junge Zhang;  Lining Sun;  Kaiqi Huang
Adobe PDF(7599Kb)  |  收藏  |  浏览/下载:280/103  |  提交时间:2023/03/02
Catastrophic forgetting  class-incremental learning  continual learning (CL)  experience replay  
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
作者:  Qinghai Miao;  Yisheng Lv;  Min Huang;  Xiao Wang;  Fei-Yue Wang
Adobe PDF(11937Kb)  |  收藏  |  浏览/下载:944/151  |  提交时间:2023/03/02
Machine learning  parallel learning  parallel systems  sim-to-real  syn-to-real  virtual-to-real  
Visuals to Text: A Comprehensive Review on Automatic Image Captioning 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2022, 卷号: 9, 期号: 8, 页码: 1339-1365
作者:  Yue Ming;  Nannan Hu;  Chunxiao Fan;  Fan Feng;  Jiangwan Zhou;  Hui Yu
Adobe PDF(56128Kb)  |  收藏  |  浏览/下载:184/23  |  提交时间:2022/08/01
Artificial intelligence  attention mechanism  encoder-decoder framework  image captioning  multi-modal understanding  training strategies