机构

• 自动化研究所 [5]
• 长春光学精密机械与物... [4]
• 计算技术研究所 [2]
• 数学与系统科学研究院 [1]

采集方式

• OAI收割 [12]

内容类型

• 会议论文 [6]
• 期刊论文 [6]

发表日期

• 2025 [1]
• 2023 [1]
• 2022 [2]
• 2021 [3]
• 2018 [1]
• 2011 [2]
• 更多

学科主题

筛选

浏览/检索结果: 共12条，第1-10条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择发表日期升序发表日期降序题名升序题名降序提交时间升序提交时间降序作者升序作者降序 Enhancing the Robustness of Vision-Language Foundation Models by Alignment Perturbation 期刊论文  OAI收割 IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2025, 卷号: 20, 页码: 7091-7105 作者:  Zhang, Cong;  Wang, Shuhui;  Li, Xiaodan;  Zhu, Yao;  Qi, Honggang   |  收藏  |  浏览/下载：2/0  |  提交时间：2025/12/03 Multimedia forensics  adversarial perturbation  robust training  robust training  vision-language models  vision-language models  vision-language models   General Greedy De-Bias Learning 期刊论文  OAI收割 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 8, 页码: 9789-9805 作者:  Han, Xinzhe;  Wang, Shuhui;  Su, Chi;  Huang, Qingming;  Tian, Qi   |  收藏  |  浏览/下载：79/0  |  提交时间：2023/12/04 Task analysis  Correlation  Training  Data models  Question answering (information retrieval)  Visualization  Image classification  Curriculum learning  dataset biases  greedy strategy  robust learning   A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies 期刊论文  OAI收割 PATTERN RECOGNITION, 2022, 卷号: 131, 页码: 11 作者:  Qian, Zhuang;  Huang, Kaizhu;  Wang, Qiu-Feng;  Zhang, Xu-Yao   |  收藏  |  浏览/下载：67/0  |  提交时间：2022/11/14 Adversarial examples  Adversarial training  Robust learning   Towards Human-Machine Recognition Alignment: An Adversarilly Robust Multimodal Retrieval Hashing Framework 期刊论文  OAI收割 IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2022, 页码: 13 作者:  Zhang, Xingwei;  Zheng, Xiaolong;  Liu, Bin;  Wang, Xiao;  Mao, Wenji   |  收藏  |  浏览/下载：85/0  |  提交时间：2022/11/14 Training  Task analysis  Semantics  Perturbation methods  Feature extraction  Computational modeling  Robustness  Adversarial perturbation  adversarially robust training  deep hashing  multimodal retrieval   Distribution-Free One-Pass Learning 期刊论文  OAI收割 IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2021, 卷号: 33, 期号: 3, 页码: 951-963 作者:  Zhao, Peng;  Wang, Xinqiang;  Xie, Siyu;  Guo, Lei;  Zhou, Zhi-Hua   |  收藏  |  浏览/下载：82/0  |  提交时间：2021/07/23 Data models  Random variables  Proposals  Training  Prediction algorithms  Task analysis  Compressed sensing  Distribution change  one-pass learning  robust learning  non-stationary environments   Gated Recurrent Fusion With Joint Training Framework for Robust End-to-End Speech Recognition 期刊论文  OAI收割 IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 期号: 29, 页码: 198-209 作者:  Fan, Cunhang;  Yi, Jiangyan;  Tao, Jianhua;  Tian, Zhengkun;  Liu, Bin   |  收藏  |  浏览/下载：78/0  |  提交时间：2021/03/08 Speech enhancement  Speech recognition  Training  Noise measurement  Logic gates  Acoustic distortion  Task analysis  Gated recurrent fusion  robust end-to-end speech recognition  speech distortion  speech enhancement  speech transformer   Audio-Visual Speech Separation with Visual Features Enhanced by Adversarial Training 会议论文  OAI收割 线上会议, 2021-7-18 作者:  Zhang Peng;  Xu Jiaming;  Shi Jing;  Hao Yunzhe;  Qin Lei   |  收藏  |  浏览/下载：79/0  |  提交时间：2021/06/21 audio-visual speech separation  robust  adversarial training method  time-domain approach   Boosting noise robustness of acoustic model via deep adversarial training 会议论文  OAI收割 加拿大卡尔加里, 2018-4-15 作者:  Bin,Liu;  Shuai,Nie;  Yaping,Zhang;  Dengfeng,Ke;  Shan,Liang   |  收藏  |  浏览/下载：68/0  |  提交时间：2020/05/15 Robust Speech Recognition  Deep Adversarial Training  Acoustic Model  Generative Adversarial Net   Efficient human action recognition using accumulated motion image and support vector machines (EI CONFERENCE) 会议论文  OAI收割 International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2011, November 19, 2011 - November 23, 2011, Suzhou, China 作者:  Zhang X.;  Zhang J.;  Zhang J.;  Zhang X.;  Zhang X. 收藏  |  浏览/下载：86/0  |  提交时间：2013/03/25 Vision-based human action recognition provides an advanced interface  and research in this field of human action recognition has been actively carried out. This paper describes a scheme for recognizing human actions from a video sequences. The proposed method is an extension of the Motion History Image(MHI) method based on the ordinal measure of accumulated motion  which is robust to variations of appearances. We define the accumulated motion image(AMI) using image differences firstly. Then the AMI of the video sequencesis resized to a MN regulation following the standard of training phases. Finally  we employ Support Vector Machine(SVM) as a classifier to distinguish the current activity in target video sequences. In a word  our proposed algorithm not only outperforms the state of art on public available KTH data set and Weizmann data set  but also proves practical to some real world applications  in addition  this method is computationally simple and able to achieve a satisfactory accuracy.   Double inverted pendulum control based on three-loop PID and improved BP neural network (EI CONFERENCE) 会议论文  OAI收割 2011 2nd International Conference on Digital Manufacturing and Automation, ICDMA 2011, August 5, 2011 - August 7, 2011, Zhangjiajie, Hunan, China 作者:  Fan Y. 收藏  |  浏览/下载：61/0  |  提交时间：2013/03/25 To deal with the defects of BP neural networks used in balance control of inverted pendulum  such as longer train time and converging in partial minimum  this article reaLizes the control of double inverted pendulum with improved BP algorithm of artificial neural networks(ANN)  builds up a training model of test simulation and the BP network is 6-10-1 structure. Tansig function is used in hidden layer and PureLin function is used in output layer  LM is used in training algorithm. The training data is acquried by three-loop PID algorithm. The model is learned and trained with Matlab calculating software  and the simuLink simulation experiment results prove that improved BP algorithm for inverted pendulum control has higher precision  better astringency and lower calculation. This algorithm has wide appLication on nonLinear control and robust control field in particular. 2011 IEEE.