CASIA OpenIR

Browse/Search Results:  1-10 of 106 Help

Selected(0)Clear Items/Page:    Sort:
Metadata Connector: Exploiting Hashtag and Tag for Cross-OSN Event Search 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 510-523
Authors:  Gao, Yuqi;  Sang, Jitao;  Fu, Chengpeng;  Wang, Zhengjia;  Ren, Tongwei;  Xu, Changsheng
Favorite  |  View/Download:19/0  |  Submit date:2021/03/08
Twitter  Tagging  Videos  YouTube  Flickr  Games  Social media search  cross-OSN application  social multimedia  
Density-Aware Multi-Task Learning for Crowd Counting 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 443-453
Authors:  Jiang, Xiaoheng;  Zhang, Li;  Zhang, Tianzhu;  Lv, Pei;  Zhou, Bing;  Pang, Yanwei;  Xu, Mingliang;  Xu, Changsheng
Favorite  |  View/Download:20/0  |  Submit date:2021/03/08
Task analysis  Semantics  Estimation  Feature extraction  Convolutional neural networks  Cameras  Head  Convolutional neural network  crowd counting  density-level classification  density map estimation  multi-task learning  
Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 1239-1251
Authors:  Cao, Min;  Chen, Chen;  Dou, Hao;  Hu, Xiyuan;  Peng, Silong;  Kuijper, Arjan
Favorite  |  View/Download:20/0  |  Submit date:2021/06/07
Probes  Feature extraction  Computational complexity  Visualization  Manifolds  Context modeling  Training  Contextual information  person re-identification  post-processing  
Context-Dependent Propagating-Based Video Recommendation in Multimodal Heterogeneous Information Networks 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 2019-2032
Authors:  Sang, Lei;  Xu, Min;  Qian, Shengsheng;  Martin, Matt;  Li, Peter;  Wu, Xindong
Favorite  |  View/Download:7/0  |  Submit date:2021/08/15
Semantics  Collaboration  YouTube  Australia  Visualization  Context modeling  Video recommendation  context-dependent propagating  Heterogeneous Information Network (HIN)  Network embedding  
Adversarial Multimodal Network for Movie Story Question Answering 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 1744-1756
Authors:  Yuan, Zhaoquan;  Sun, Siyuan;  Duan, Lixin;  Li, Changsheng;  Wu, Xiao;  Xu, Changsheng
Favorite  |  View/Download:5/0  |  Submit date:2021/08/15
Knowledge discovery  Motion pictures  Visualization  Task analysis  Generators  Gallium nitride  Natural languages  Movie question answering  adversarial network  multimodal understanding  
Adaptive Deep Metric Learning for Affective Image Retrieval and Classification 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 1640-1653
Authors:  Yao, Xingxu;  She, Dongyu;  Zhang, Haiwei;  Yang, Jufeng;  Cheng, Ming-Ming;  Wang, Liang
Favorite  |  View/Download:5/0  |  Submit date:2021/08/15
Measurement  Visualization  Semantics  Feature extraction  Task analysis  Image analysis  Image retrieval  Affective image retrieval  convolutional neural network  deep metric learning  visual sentiment analysis  
Intra-domain Consistency Enhancement for Unsupervised Person Re-identification 期刊论文
IEEE Transactions on Multimedia, 2021, 卷号: 0, 期号: 0, 页码: 0-0
Authors:  Li, Yaoyu;  Yao, Hantao;  Xu, Changsheng
Adobe PDF(2167Kb)  |  Favorite  |  View/Download:20/6  |  Submit date:2021/06/22
Person Re-identification  unsupervised domain adaptation  representation learning  
Learning Coarse-to-Fine Graph Neural Networks for Video-Text Retrieval 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 2386-2397
Authors:  Wang, Wei;  Gao, Junyu;  Yang, Xiaoshan;  Xu, Changsheng
Favorite  |  View/Download:2/0  |  Submit date:2021/11/02
Feature extraction  Encoding  Task analysis  Semantics  Data models  Cognition  Focusing  Video-text retrieval  graph neural network  coarse-to-fine strategy  
HAPGN: Hierarchical Attentive Pooling Graph Network for Point Cloud Segmentation 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 2335-2346
Authors:  Chen, Chaofan;  Qian, Shengsheng;  Fang, Quan;  Xu, Changsheng
Favorite  |  View/Download:2/0  |  Submit date:2021/11/02
Three-dimensional displays  Feature extraction  Task analysis  Layout  Logic gates  Machine learning  Two dimensional displays  Point cloud segmentation  hierarchical graph pooling  gated graph attention network  
Heterogeneous Community Question Answering via Social-Aware Multi-Modal Co-Attention Convolutional Matching 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 2321-2334
Authors:  Hu, Jun;  Qian, Shengsheng;  Fang, Quan;  Xu, Changsheng
Favorite  |  View/Download:2/0  |  Submit date:2021/11/02
Visualization  Semantics  Knowledge discovery  Context modeling  Portable computers  Task analysis  Object detection  Question-answering  attention  multi-modal  social multimedia