CASIA OpenIR

Browse/Search Results:  1-10 of 49 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
Triple-strip attention mechanism-based natural disaster images classification and segmentation 期刊论文
VISUAL COMPUTER, 2022, 页码: 11
Authors:  Ma, Zhihao;  Yuan, Mengke;  Gu, Jiaming;  Meng, Weiliang;  Xu, Shibiao;  Zhang, Xiaopeng
Favorite  |  View/Download:23/0  |  Submit date:2022/07/25
Natural disaster image analysis  Image segmentation  Attention mechanism  
Compressing Speaker Extraction Model with Ultra-low Precision Quantization and Knowledge Distillation 期刊论文
Neural Networks, 2022, 卷号: 154, 页码: 13-21
Authors:  Yating Huang;  Yunzhe Hao;  Jiaming Xu;  Bo Xu
Adobe PDF(801Kb)  |  Favorite  |  View/Download:23/3  |  Submit date:2022/09/17
Improving Cross-State and Cross-Subject Visual ERP-Based BCI With Temporal Modeling and Adversarial Training 期刊论文
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2022, 卷号: 30, 页码: 369-379
Authors:  Ni, Ziyi;  Xu, Jiaming;  Wu, Yuwei;  Li, Mengfan;  Xu, Guizhi;  Xu, Bo
Favorite  |  View/Download:33/0  |  Submit date:2022/06/06
Brain modeling  Electroencephalography  Visualization  Training  Task analysis  Feature extraction  Adaptation models  Brain-computer interface  temporal modeling  adversarial training  cross-subject  cross-state  
Towards Modeling Auditory Restoration in Noisy Environments 会议论文
, 线上会议, Jul 18, 2021
Authors:  Yating Huang;  Yunzhe Hao;  Jiaming Xu;  Bo Xu
Adobe PDF(628Kb)  |  Favorite  |  View/Download:22/3  |  Submit date:2022/09/17
WASE: LEARNING WHEN TO ATTEND FOR SPEAKER EXTRACTION IN COCKTAIL PARTY ENVIRONMENTS 会议论文
, Toronto, June 6-11, 2021
Authors:  Yunzhe Hao;  Jiaming Xu;  Peng Zhang;  Bo Xu
Adobe PDF(2034Kb)  |  Favorite  |  View/Download:35/1  |  Submit date:2022/06/23
LISNN: Improving Spiking Neural Networks with Lateral Interactions for Robust Object Recognition 会议论文
, Yokohama, Japan, January 7-15, 2021
Authors:  Xiang Cheng;  Yunzhe Hao;  Jiaming Xu;  Bo Xu
Adobe PDF(2275Kb)  |  Favorite  |  View/Download:26/1  |  Submit date:2022/06/23
Audio-Visual Speech Separation with Visual Features Enhanced by Adversarial Training 会议论文
0, 线上会议, 2021-7-18
Authors:  Zhang Peng;  Xu Jiaming;  Shi Jing;  Hao Yunzhe;  Qin Lei;  Xu Bo
Adobe PDF(1900Kb)  |  Favorite  |  View/Download:58/6  |  Submit date:2021/06/21
audio-visual speech separation  robust  adversarial training method  time-domain approach  
Online Audio-Visual Speech Separation with Generative Adversarial Training 会议论文
0, 线上会议, 2021-4-23
Authors:  Zhang Peng;  Xu Jiaming;  Hao Yunzhe;  Xu Bo
Adobe PDF(532Kb)  |  Favorite  |  View/Download:53/5  |  Submit date:2021/06/21
audio-visual speech separation  online processing  generative adversarial training  causal temporal convolutional network  
A Unified Framework for Low-Latency Speaker Extraction in Cocktail Party Environments 会议论文
, Shanghai, China, October 25–29, 2020
Authors:  Yunzhe Hao;  Jiaming Xu;  Jing Shi;  Peng Zhang;  Lei Qin;  Bo Xu
Adobe PDF(399Kb)  |  Favorite  |  View/Download:33/3  |  Submit date:2022/06/23
Modelling Speaker-dependent Auditory Attention Using A Spiking Neural Network with Temporal Coding and Supervised Learning 会议论文
, Sydney, Australia, December 12-15, 2019
Authors:  Yating Huang;  Jiaming Xu;  Bo Xu
Adobe PDF(3377Kb)  |  Favorite  |  View/Download:15/2  |  Submit date:2022/09/17