CASIA OpenIR

Browse/Search Results:  1-10 of 57 Help

Selected(0)Clear Items/Page:    Sort:
Reducing Vision-Answer Biases for Multiple-Choice VQA 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 4621-4634
Authors:  Zhang, Xi;  Zhang, Feifei;  Xu, Changsheng
Adobe PDF(2684Kb)  |  Favorite  |  View/Download:91/6  |  Submit date:2023/11/17
Multiple-choice VQA  vision-answer bias  causal intervention  counterfactual interaction learning  
Zero-Shot Predicate Prediction for Scene Graph Parsing 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 3140-3153
Authors:  Li, Yiming;  Yang, Xiaoshan;  Huang, Xuhui;  Ma, Zhe;  Xu, Changsheng
Favorite  |  View/Download:168/0  |  Submit date:2023/11/17
Deep learning  zero-shot  scene graph  
Multi-Source Knowledge Reasoning Graph Network for Multi-Modal Commonsense Inference 期刊论文
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2023, 卷号: 19, 期号: 4, 页码: 17
Authors:  Ma, Xuan;  Yang, Xiaoshan;  Xu, Changsheng
Favorite  |  View/Download:106/0  |  Submit date:2023/11/17
Knowledge reasoning  multi-modal commonsense inference  graph neural network  
Learning Semantic-Aware Spatial-Temporal Attention for Interpretable Action Recognition 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 卷号: 32, 期号: 8, 页码: 5213-5224
Authors:  Fu, Jie;  Gao, Junyu;  Xu, Changsheng
Favorite  |  View/Download:375/0  |  Submit date:2022/09/19
Visualization  Semantics  Task analysis  Three-dimensional displays  Feature extraction  Solid modeling  Predictive models  Semantic-aware  spatial-temporal attention  interpretable  action recognition  
Explicit Cross-Modal Representation Learning for Visual Commonsense Reasoning 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 24, 页码: 2986-2997
Authors:  Zhang, Xi;  Zhang, Feifei;  Xu, Changsheng
Adobe PDF(5681Kb)  |  Favorite  |  View/Download:418/5  |  Submit date:2022/07/25
Cognition  Video recording  Syntactics  Visualization  Task analysis  Semantics  Linguistics  Visual Commonsense Reasoning  explicit reasoning  syntactic structure  interpretability  
Holographic Feature Learning of Egocentric-Exocentric Videos for Multi-Domain Action Recognition 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 24, 页码: 2273-2286
Authors:  Huang, Yi;  Yang, Xiaoshan;  Gao, Junyun;  Xu, Changsheng
Adobe PDF(2409Kb)  |  Favorite  |  View/Download:381/75  |  Submit date:2022/07/25
Videos  Feature extraction  Visualization  Task analysis  Computational modeling  Target recognition  Prototypes  Egocentric videos  exocentric videos  holographic feature  multi-domain  action recognition  
The Model May Fit You: User-Generalized Cross-Modal Retrieval 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 24, 页码: 2998-3012
Authors:  Ma, Xinhong;  Yang, Xiaoshan;  Gao, Junyu;  Xu, Changsheng
Adobe PDF(6549Kb)  |  Favorite  |  View/Download:289/56  |  Submit date:2022/06/17
cross-modal retrieval  domain generalization  meta-learning  
GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation 会议论文
IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, JUN 16-20, 2019
Authors:  Ma, Xinhong;  Zhang, Tianzhu;  Xu, Changsheng
Adobe PDF(7239Kb)  |  Favorite  |  View/Download:231/49  |  Submit date:2022/06/14
Multi-Object Tracking With Spatial-Temporal Topology-Based Detector 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 卷号: 32, 期号: 5, 页码: 3023-3035
Authors:  You, Sisi;  Yao, Hantao;  Xu, Changsheng
Favorite  |  View/Download:286/0  |  Submit date:2022/06/10
Target tracking  Topology  Tracking  Detectors  Visualization  Trajectory  Proposals  Multi-object tracking  spatial-temporal topology-based detector  spatial topology constraint  temporal topology constraint  
Weakly-Supervised Facial Expression Recognition in the Wild With Noisy Data 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 24, 页码: 1800-1814
Authors:  Zhang, Feifei;  Xu, Mingliang;  Xu, Changsheng
Favorite  |  View/Download:270/0  |  Submit date:2022/06/10
Noise measurement  Face recognition  Data models  Task analysis  Training data  Training  Annotations  Facial expression recognition  noisy labeled data  clean labels  end-to-end  pose modeling  noise modeling