CASIA OpenIR

Browse/Search Results:  1-10 of 14 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
基于多模态表征学习与融合的情感识别研究 学位论文
, 2024
Authors:  孙立才
Adobe PDF(5844Kb)  |  Favorite  |  View/Download:36/4  |  Submit date:2024/06/27
情感识别  表征学习  自监督学习  多模态融合  注意力机制  
MULTIMODAL CROSS- AND SELF-ATTENTION NETWORK FOR SPEECH EMOTION RECOGNITION 会议论文
, Toronto, Canada, 6-12 June 2021
Authors:  Licai Sun;  Bin Liu;  Jianhua Tao;  Zheng Lian
Adobe PDF(1078Kb)  |  Favorite  |  View/Download:34/8  |  Submit date:2024/06/03
EmotionNAS: Two-stream Neural Architecture Search for Speech Emotion Recognition 会议论文
, Dublin, Ireland, 20-24 August 2023
Authors:  Haiyang Sun;  Zheng Lian;  Bin Liu;  Ying Li;  Licai Sun;  Cong Cai;  Jianhua Tao;  Meng Wang;  Yuan Cheng
Adobe PDF(826Kb)  |  Favorite  |  View/Download:36/10  |  Submit date:2024/05/31
Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis 期刊论文
IEEE Transactions on Affective Computing, 2023, 卷号: 15, 期号: 1, 页码: 1-17
Authors:  Licai Sun;  Zheng Lian;  Bin Liu;  Jianhua Tao
Adobe PDF(2371Kb)  |  Favorite  |  View/Download:60/18  |  Submit date:2024/05/31
Transformers  Robustness  Semantics  Data models  Computational modeling  Videos  Training  Multimodal sentiment analysis  unaligned and incomplete data  efficient multimodal Transformer  dual-level feature restoration  robustness  
MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition 会议论文
, Ottawa, ON, Canada, October 29-November 3, 2023
Authors:  Licai Sun;  Zheng Lian;  Bin Liu;  Jianhua Tao
Adobe PDF(1960Kb)  |  Favorite  |  View/Download:35/11  |  Submit date:2024/05/31
MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning 会议论文
, Ottawa, ON, Canada, October 29-November 3, 2023
Authors:  Zheng Lian;  Haiyang Sun;  Licai Sun;  Kang Chen;  Mingyu Xu;  Kexin Wang;  Ke Xu;  Yu He;  Ying Li;  Jinming Zhao;  Ye Liu;  Bin Liu;  Jiangyan Yi;  Meng Wang;  Erik Cambria;  Guoying Zhao;  Björn W. Schuller;  Jianhua Tao
Adobe PDF(993Kb)  |  Favorite  |  View/Download:46/15  |  Submit date:2024/05/31
HiCMAE: Hierarchical Contrastive Masked Autoencoder for self-supervised Audio-Visual Emotion Recognition 期刊论文
Information Fusion, 2024, 卷号: 108, 页码: 1-20
Authors:  Licai Sun;  Zheng Lian;  Bin Liu;  Jianhua Tao
Adobe PDF(2281Kb)  |  Favorite  |  View/Download:48/11  |  Submit date:2024/05/31
Audio-Visual Emotion Recognition  Self-supervised learning  Masked autoencoder  Contrastive learning  
GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition 期刊论文
Information Fusion, 2024, 页码: 1-12
Authors:  Zheng Lian;  Licai Sun;  Haiyang Sun;  Kang Chen;  Zhuofan Wen;  Hao Gu;  Bin Liu;  Jianhua Tao
Adobe PDF(6888Kb)  |  Favorite  |  View/Download:62/9  |  Submit date:2024/05/31
GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 7, 页码: 8419-8432
Authors:  Lian, Zheng;  Chen, Lan;  Sun, Licai;  Liu, Bin;  Tao, Jianhua
Adobe PDF(3959Kb)  |  Favorite  |  View/Download:177/7  |  Submit date:2023/11/17
Oral communication  Correlation  Data models  Task analysis  Feature extraction  Tensors  Benchmark testing  Conversational data  graph complete network (GCNet)  incomplete multimodal learning  speaker-sensitive modeling  temporal-sensitive modeling  
Multi-modal Continuous Dimensional Emotion Recognition Using Recurrent Neural Network and Self-Atention Mechanism 会议论文
, Seattle, United States, 12-16 October, 2020
Authors:  Licai Sun;  Zheng Lian;  Jianhua Tao;  Bin Liu;  Mingyue Niu
Adobe PDF(1041Kb)  |  Favorite  |  View/Download:201/62  |  Submit date:2021/06/16