中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共147条，第1-10条 帮助

限定条件            
已选(0)清除 条数/页：   排序方式：
Unbiased Visual Question Answering by Leveraging Instrumental Variable 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 6648-6662
作者:  Pan, Yonghua;  Liu, Jing;  Jin, Lu;  Li, Zechao
收藏  |  浏览/下载：1/0  |  提交时间：2024/07/22
Visualization  Correlation  Instruments  Training  Predictive models  Color  Generators  Visual question answering  instrumental variable  causal inference  out of distribution  
Snippet-to-Prototype Contrastive Consensus Network for Weakly Supervised Temporal Action Localization 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 6717-6729
作者:  Shao, Yuxiang;  Zhang, Feifei;  Xu, Changsheng
收藏  |  浏览/下载：1/0  |  提交时间：2024/07/22
Contrastive learning  knowledge distillation  weakly-supervised temporal action localization  
RISTRA: Recursive Image Super-Resolution Transformer With Relativistic Assessment 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 6475-6487
作者:  Zhou, Xiaoqiang;  Huang, Huaibo;  Wang, Zilei;  He, Ran
收藏  |  浏览/下载：1/0  |  提交时间：2024/07/22
Super resolution  vision transformer  parameter sharing  
CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 6906-6916
作者:  Wang, Wenxuan;  He, Xingjian;  Zhang, Yisi;  Guo, Longteng;  Shen, Jiachen;  Li, Jiangyun;  Liu, Jing
收藏  |  浏览/下载：6/0  |  提交时间：2024/07/03
Referring image segmentation  cross-modality guidance  masked self-distillation  vision and language  
Completed Part Transformer for Person Re-Identification 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 2303-2313
作者:  Zhang, Zhong;  He, Di;  Liu, Shuang;  Xiao, Baihua;  Durrani, Tariq S.
收藏  |  浏览/下载：12/0  |  提交时间：2024/07/03
Person ReID  transformer  adaptive refined tokens  
Non-Maximum Suppression Guided Label Assignment for Object Detection in Crowd Scenes 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 2207-2218
作者:  Jiang, Hangzhi;  Zhang, Xin;  Xiang, Shiming
收藏  |  浏览/下载：7/0  |  提交时间：2024/07/03
Object detection  Crowd scenes  Label assignment  Non-maximum suppression  
A Two-Stream Hybrid Convolution-Transformer Network Architecture for Clothing-Change Person Re-Identification 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 5326-5339
作者:  Wu, Junyi;  Huang, Yan;  Gao, Min;  Gao, Zhipeng;  Zhao, Jianqiang;  Zhang, Huiji;  Zhang, Anguo
收藏  |  浏览/下载：4/0  |  提交时间：2024/07/03
Clothing-change person re-identification  ID-unique feature  feature supplement module  hierarchical supervision  
Comment-Context Dual Collaborative Masked Transformer Network for Fake News Detection 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 5170-5180
作者:  Wang, Jinguang;  Qian, Shengsheng;  Hu, Jun;  Hong, Richang
收藏  |  浏览/下载：16/0  |  提交时间：2024/07/03
Fake news detection  multi-modal learning  social media  
Exploring Rich Semantics for Open-Set Action Recognition 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 5410-5421
作者:  Hu, Yufan;  Gao, Junyu;  Dong, Jianfeng;  Fan, Bin;  Liu, Hongmin
收藏  |  浏览/下载：10/0  |  提交时间：2024/07/03
Semantics  Prototypes  Knowledge graphs  Visualization  Task analysis  Uncertainty  Training  Open-set action recognition  video action recognition  semantic relation modeling  
SgVA-CLIP: Semantic-Guided Visual Adapting of Vision-Language Models for Few-Shot Image Classification 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 3469-3480
作者:  Peng, Fang;  Yang, Xiaoshan;  Xiao, Linhui;  Wang, Yaowei;  Xu, Changsheng
收藏  |  浏览/下载：7/0  |  提交时间：2024/07/03
Few-shot  image classification  vision-language models