中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共125条，第1-10条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
Modal Contrastive Learning Based End-to-End Text Image Machine Translation 期刊论文
IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE/ACM TASLP), 2023, 卷号: 32, 期号: 32, 页码: 2153-2165
作者:  Ma, Cong;  Han, Xu;  Wu, Linghui;  Zhang, Yaping;  Zhao, Yang;  Zhou, Yu;  Zong, Chengqing
Adobe PDF(6551Kb)  |  收藏  |  浏览/下载：31/16  |  提交时间：2024/06/26
Transformers  Machine translation  Decoding  Semantics  Pipelines  Text recognition  Task analysis  Text image machine translation  contrastive learning  text image recognition  machine translation  
Exploring Intrinsic Discrimination and Consistency for Weakly Supervised Object Localization 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 卷号: 33, 期号: 0, 页码: 1045 - 1058
作者:  Changwei Wang;  Rongtao Xu;  Shibiao Xu;  Weiliang Meng;  Ruisheng Wang;  Xiaopeng Zhang
Adobe PDF(3269Kb)  |  收藏  |  浏览/下载：68/23  |  提交时间：2024/05/29
Weakly supervised object localization  intrinsic discrimination and consistency  deep metric learning  geometric transformation consistency  
BSS-TFNet: Attention-Enhanced Background Signal Suppression Network for Time-Frequency Spectrum in Magnetic Particle Imaging 期刊论文
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2023, 页码: 15
作者:  Wei, Zechen;  Liu, Yanjun;  Zhu, Tao;  Yang, Xin;  Tian, Jie;  Hui, Hui
Adobe PDF(6094Kb)  |  收藏  |  浏览/下载：101/5  |  提交时间：2024/02/22
Magnetic particle imaging  deep learning  self-attention mechanism  time-frequency spectrum  background signal  
Learning Human-to-Robot Dexterous Handovers for Anthropomorphic Hand 期刊论文
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2023, 卷号: 15, 期号: 3, 页码: 1224-1238
作者:  Duan, Haonan;  Wang, Peng;  Li, Yiming;  Li, Daheng;  Wei, Wei
Adobe PDF(10850Kb)  |  收藏  |  浏览/下载：146/19  |  提交时间：2023/12/21
Anthropomorphic hand  handovers  human-robot interaction  
Constrained Maximum Cross-Domain Likelihood for Domain Generalization 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 页码: 15
作者:  Lin, Jianxin;  Tang, Yongqiang;  Wang, Junping;  Zhang, Wensheng
Adobe PDF(2518Kb)  |  收藏  |  浏览/下载：167/7  |  提交时间：2023/11/17
Optimization  Feature extraction  Metalearning  Entropy  Training  Hospitals  Task analysis  Distribution shift  domain adaptation  domain generalization  domain-invariant representation  joint distribution alignment  
Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 9, 页码: 4616-4629
作者:  Ma, Chengcheng;  Liu, Yang;  Deng, Jiankang;  Xie, Lingxi;  Dong, Weiming;  Xu, Changsheng
Adobe PDF(1644Kb)  |  收藏  |  浏览/下载：167/26  |  提交时间：2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection  
SMIN: Semi-Supervised Multi-Modal Interaction Network for Conversational Emotion Recognition 期刊论文
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2023, 卷号: 14, 期号: 3, 页码: 2415-2429
作者:  Lian, Zheng;  Liu, Bin;  Tao, Jianhua
Adobe PDF(2103Kb)  |  收藏  |  浏览/下载：160/11  |  提交时间：2023/11/15
Emotion recognition  Feature extraction  Training  Acoustics  Semisupervised learning  Benchmark testing  Hidden Markov models  Semi-supervised multi-modal interaction network (SMIN)  conversational emotion recognition  semi-supervised learning  intra-modal interaction  cross-modal interaction  
Multilevel heterogeneous domain adaptation method for remote sensing image segmentation 期刊论文
IEEE Transactions on Geoscience and Remote Sensing, 2023, 页码: 61
作者:  Liang Chenbin;  Cheng Bo;  Xiao baihua;  Dong Yunyun;  Chen jinfen
Adobe PDF(35677Kb)  |  收藏  |  浏览/下载：202/42  |  提交时间：2023/05/30
MSMFN: An ultrasound based multi-step modality fusion network for identifying the histologic subtypes of metastatic cervical lymphadenopathy 期刊论文
IEEE Transactions on Medical Imaging, 2022, 页码: 1-13
作者:  Zheling, Meng;  Yangyang, Zhu;  Wenjing, Pang;  Jie, Tian;  Fang, Nie;  Kun, Wang
Adobe PDF(3049Kb)  |  收藏  |  浏览/下载：369/62  |  提交时间：2023/03/27
MoEP-AE: Autoencoding Mixtures of Exponential Power Distributions for Open-Set Recognition 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 1, 页码: 312-325
作者:  Jiayin, Sun;  Hong, Wang;  Qiulei, Dong
Adobe PDF(3639Kb)  |  收藏  |  浏览/下载：147/14  |  提交时间：2023/03/20
open-set recognition  autoencoder  scale mixture distribution  exponential power distribution