MA-FSAR: Multimodal Adaptation of CLIP for few-shot action recognition
Authors:
- Jiazheng XingJiazheng Xing
- Jian ZhaoJZJian Zhao
- Chao XuChao Xu
- Mengmeng WangMWMengmeng Wang
- Guang DaiGDGuang Dai
- Yong LiuYLYong Liu
- Jingdong WangJWJingdong Wang
- Xuelong LiXLXuelong Li
- 9 June 2025
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 169
Abstract
No abstract availableAll Related Versions
Funding Information
- Zhejiang University State Key Laboratory of Industrial Control Technology (ICT2024A09)
- National Natural Science Foundation of China (62476224)
This publication has 15 references indexed in Scilit:
- Multi-view distillation based on multi-modal fusion for few-shot action recognition (CLIP-MDMF)Knowledge-Based Systems, 2024
- Consistency Prototype Module and Motion Compensation for few-shot action recognition (CLIP-CPMC)Neurocomputing, 2024
- Dual-Path Adaptation from Image to Video Transformers2023
- Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring2023
- GroupViT: Semantic Segmentation Emerges from Text Supervision2022
- Spatio-temporal Relation Modeling for Few-shot Action Recognition2022
- Hybrid Relation Guided Set Matching for Few-shot Action Recognition2022
- Temporal-Relational CrossTransformers for Few-Shot Action Recognition2021
- Compound Memory Networks for Few-Shot Video Classification2018
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017