A distinct classification of attention mechanisms in video understanding
Authors:
- Shilin ChenSCShilin Chen
- Xingwang WangXWXingwang Wang
- Yafeng SunYSYafeng Sun
- Kun YangKYKun Yang
- Xiaohui WeiXWXiaohui Wei
- 26 August 2025
- journal article
- Published by Elsevier in Information Sciences
- Vol. 721
Abstract
No abstract availableFunding Information
- National Key Research and Development Program of China
- National Key Research and Development Program of China Stem Cell and Translational Research (2023YFB4502304)
This publication has 14 references indexed in Scilit:
- Mamba-driven hierarchical temporal multimodal alignment for referring video object segmentationNeurocomputing, 2025
- Aggregating nearest sharp features via hybrid transformers for video deblurringInformation Sciences, 2024
- TODO: Task Offloading Decision Optimizer for the efficient provision of offloading schemesPervasive and Mobile Computing, 2024
- Multi-layer representation for cross-view action recognitionInformation Sciences, 2024
- Relative-position embedding based spatially and temporally decoupled Transformer for action recognitionPattern Recognition, 2023
- Dual attentional transformer for video visual relation predictionNeurocomputing, 2023
- MuAt-Va: Multi-Attention and Video-Auxiliary Network for Device-Free Action RecognitionIEEE Internet of Things Journal, 2023
- Shape-Former: Bridging CNN and Transformer via ShapeConv for multimodal image matchingInformation Fusion, 2022
- Video representation learning for temporal action detection using global-local attentionPattern Recognition, 2022
- Spatial-temporal interaction learning based two-stream network for action recognitionInformation Sciences, 2022