中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共24条，第1-10条 帮助

限定条件    
已选(0)清除 条数/页：   排序方式：
MMT: Cross Domain Few-Shot Learning via Meta-Memory Transfer 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 12, 页码: 15018-15035
作者:  Wang, Wenjian;  Duan, Lijuan;  Wang, Yuxi;  Fan, Junsong;  Zhang, Zhaoxiang
收藏  |  浏览/下载：34/0  |  提交时间：2024/03/26
Memory  few-shot learning  semantic segmentation  cross-domain  
Object Affinity Learning: Towards Annotation-Free Instance Segmentation 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 11, 页码: 13959-13973
作者:  Wang, Yuqi;  Chen, Yuntao;  Zhang, Zhaoxiang
收藏  |  浏览/下载：79/0  |  提交时间：2023/12/21
Videos  Motion segmentation  Visualization  Three-dimensional displays  Task analysis  Object detection  Geometry  Object affinity learning  geometric information  annotation-free instance segmentation  
Visually Guided Sound Source Separation With Audio-Visual Predictive Coding 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 页码: 15
作者:  Song, Zengjie;  Zhang, Zhaoxiang
收藏  |  浏览/下载：47/0  |  提交时间：2023/11/17
Feature fusion  multimodal learning  predictive coding (PC)  self-supervised learning  sound source separation  
Memory-Based Cross-Image Contexts for Weakly Supervised Semantic Segmentation 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 5, 页码: 6006-6020
作者:  Fan, Junsong;  Zhang, Zhaoxiang
收藏  |  浏览/下载：30/0  |  提交时间：2023/11/17
Image segmentation  Semantics  Training  Heating systems  Context modeling  Task analysis  Computational modeling  Weakly-supervised learning  semantic segmentation  image relationship  cross-image context  
Learning to Adapt Across Dual Discrepancy for Cross-Domain Person Re-Identification 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 2, 页码: 1963-1980
作者:  Luo, Chuanchen;  Song, Chunfeng;  Zhang, Zhaoxiang
Adobe PDF(2539Kb)  |  收藏  |  浏览/下载：220/65  |  提交时间：2023/03/20
Person re-identification  domain adaptation  cross-domain mixup  camera-aware learning  self-paced learning  
Instance GNN: A Learning Framework for Joint Symbol Segmentation and Recognition in Online Handwritten Diagrams 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 24, 页码: 2580-2594
作者:  Yun, Xiao-Long;  Zhang, Yan-Ming;  Yin, Fei;  Liu, Cheng-Lin
收藏  |  浏览/下载：241/0  |  提交时间：2022/07/25
Handwriting recognition  Task analysis  Grammar  Semantics  Image segmentation  Trajectory  Text recognition  Online handwritten diagram recognition  symbol segmentation  symbol recognition  freehand sketch analysis  graph neural networks  
One-Stage Open Set Object Detection with Prototype Learning 会议论文
, Bali Indonesia, December 8-12, 2021
作者:  Yongyu Xiong;  Peipei Yang;  Cheng-Lin Liu
Adobe PDF(1184Kb)  |  收藏  |  浏览/下载：262/63  |  提交时间：2022/06/22
object detection  Open set recognition  Prototype learning  
View-Angle Invariant Object Monitoring Without Image Registration 会议论文
, online meeting, 2020-5-4
作者:  Zhang, Xin;  Huo, Chunlei;  Pan, Chunhong
Adobe PDF(23602Kb)  |  收藏  |  浏览/下载：144/39  |  提交时间：2022/06/14
Toward few-shot domain adaptation with perturbation-invariant representation and transferable prototypes 期刊论文
FRONTIERS OF COMPUTER SCIENCE, 2022, 卷号: 16, 期号: 3, 页码: 11
作者:  Fan, Junsong;  Wang, Yuxi;  Guan, He;  Song, Chunfeng;  Zhang, Zhaoxiang
Adobe PDF(4804Kb)  |  收藏  |  浏览/下载：282/49  |  提交时间：2022/06/10
domain adaptation  semantic segmentation  
VAG: A Uniform Model for Cross-Modal Visual-Audio Mutual Generation 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 页码: 13
作者:  Hao, Wangli;  Guan, He;  Zhang, Zhaoxiang
收藏  |  浏览/下载：214/0  |  提交时间：2022/06/10
Task analysis  Instruments  Visualization  Image reconstruction  Generators  Decoding  Generative adversarial networks  Cross modality  cross-modal generation  mutual generation  visual and audio