中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共15条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
Prompting Video-Language Foundation Models With Domain-Specific Fine-Grained Heuristics for Video Question Answering 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2025, 卷号: 35, 期号: 2, 页码: 1615-1630
作者:  Yu, Ting;  Fu, Kunhao;  Wang, Shuhui;  Huang, Qingming;  Yu, Jun
收藏  |  浏览/下载：5/0  |  提交时间：2025/06/25
Cognition  Computational modeling  Visualization  Context modeling  Data models  Adaptation models  Accuracy  Question answering (information retrieval)  Transformers  Feature extraction  Video question answering  discriminative unimodal comprehension  cross-modal interaction  domain-specific heuristics  video-language foundation models  entity-action relationships  context-aware reasoning  
Toward Egocentric Compositional Action Anticipation with Adaptive Semantic Debiasing 期刊论文
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2024, 卷号: 20, 期号: 5, 页码: 21
作者:  Zhang, Tianyu;  Min, Weiqing;  Liu, Tao;  Jiang, Shuqiang;  Rui, Yong
收藏  |  浏览/下载：34/0  |  提交时间：2024/05/20
Egocentric video understanding  compositional action anticipation  semantic bias  adaptive counterfactual analysis  
Hierarchical compositional representations for few-shot action recognition 期刊论文
COMPUTER VISION AND IMAGE UNDERSTANDING, 2024, 卷号: 240, 页码: 11
作者:  Li, Changzhen;  Zhang, Jie;  Wu, Shuzhe;  Jin, Xin;  Shan, Shiguang
收藏  |  浏览/下载：35/0  |  提交时间：2024/05/20
Action recognition  Few-shot learning  Hierarchical compositional representations  Body parts  EMD distance  
Meta Auxiliary Learning for Facial Action Unit Detection 期刊论文
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2023, 卷号: 14, 期号: 3, 页码: 2526-2538
作者:  Li, Yong;  Shan, Shiguang
收藏  |  浏览/下载：39/0  |  提交时间：2023/12/04
Facial action unit detection  auxiliary learning  meta learning  
MIFNet: Multiple instances focused temporal action proposal generation 期刊论文
NEUROCOMPUTING, 2023, 卷号: 538, 页码: 13
作者:  Wang, Lining;  Yao, Hongxun;  Yang, Haosen;  Wang, Sibo;  Jin, Sheng
收藏  |  浏览/下载：29/0  |  提交时间：2023/12/04
Video understanding  Temporal action proposal  Temporal action detection  Contrastive learning  Multiple instances  
Motif-GCNs With Local and Non-Local Temporal Blocks for Skeleton-Based Action Recognition 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 2, 页码: 2009-2023
作者:  Wen, Yu-Hui;  Gao, Lin;  Fu, Hongbo;  Zhang, Fang-Lue;  Xia, Shihong;  Liu, Yong-Jin
收藏  |  浏览/下载：41/0  |  提交时间：2023/07/12
Skeleton  Feature extraction  Joints  Convolutional codes  Topology  Training  Sparse matrices  Action recognition  graph convolutional neural networks  spatio-temporal attention  non-local block  skeleton sequence  
Contrastive Learning of Person-Independent Representations for Facial Action Unit Detection 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 3212-3225
作者:  Li, Yong;  Shan, Shiguang
收藏  |  浏览/下载：29/0  |  提交时间：2023/12/04
Gold  Videos  Training  Image reconstruction  Feature extraction  Faces  Task analysis  Facial action unit detection  contrastive Learning  self-supervised learning  person-independent action unit detection  
Learning Representations for Facial Actions From Unlabeled Videos 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 卷号: 44, 期号: 1, 页码: 302-317
作者:  Li, Yong;  Zeng, Jiabei;  Shan, Shiguang
收藏  |  浏览/下载：46/0  |  提交时间：2022/06/21
Facial action unit detection  self-supervised learning  representation learning  feature disentanglement  encoder-decoder structure  
Collaborative Local-Global Learning for Temporal Action Proposal 期刊论文
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2021, 卷号: 12, 期号: 5, 页码: 14
作者:  Zhu, Yisheng;  Han, Hu;  Liu, Guangcan;  Liu, Qingshan
收藏  |  浏览/下载：50/0  |  提交时间：2022/06/21
Temporal action proposal generation  untrimmed videos  long short-term memory  attention mechanism  
Multi-Domain and Multi-Task Learning for Human Action Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 2, 页码: 853-867
作者:  Liu, An-An;  Xu, Ning;  Nie, Wei-Zhi;  Su, Yu-Ting;  Zhang, Yong-Dong
收藏  |  浏览/下载：108/0  |  提交时间：2019/04/03
Domain-invariant Learning  multi-task learning  human action recognition