A dual-prototype network combining query-specific and class-specific attentive learning for few-shot action recognition
Authors:
- Lei JiangLJLei Jiang
- Yongzhao ZhanYZYongzhao Zhan
- Zhen JiangZJZhen Jiang
- Na TangNTNa Tang
- 9 May 2024
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 598
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (61672268)
This publication has 9 references indexed in Scilit:
- Cross-domain few-shot action recognition with unlabeled videosComputer Vision and Image Understanding, 2023
- Multi-view learning for hyperspectral image classification: An overviewNeurocomputing, 2022
- Multidimensional Prototype Refactor Enhanced Network for Few-Shot Action RecognitionIEEE Transactions on Circuits and Systems for Video Technology, 2022
- Attention in Attention: Modeling Context Correlation for Efficient Video ClassificationIEEE Transactions on Circuits and Systems for Video Technology, 2022
- Semantic-Guided Relation Propagation Network for Few-shot Action Recognition2021
- DB-LSTM: Densely-connected Bi-directional LSTM for human action recognitionNeurocomputing, 2021
- Human action recognition using convolutional LSTM and fully-connected LSTM with different attentionsNeurocomputing, 2020
- A Two-Stage Approach to Few-Shot Learning for Image RecognitionIEEE Transactions on Image Processing, 2019
- Long Short-Term MemoryNeural Computation, 1997