Saved in:
Bibliographic Details
Main Authors: Qian, Zefeng, Zhang, Chongyang, Huang, Yifei, Wang, Gang, Ying, Jiangyong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.14430
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916656130818048
author Qian, Zefeng
Zhang, Chongyang
Huang, Yifei
Wang, Gang
Ying, Jiangyong
author_facet Qian, Zefeng
Zhang, Chongyang
Huang, Yifei
Wang, Gang
Ying, Jiangyong
contents Few-shot Action Recognition (FSAR) constitutes a crucial challenge in computer vision, entailing the recognition of actions from a limited set of examples. Recent approaches mainly focus on employing image-level features to construct temporal dependencies and generate prototypes for each action category. However, a considerable number of these methods utilize mainly image-level features that incorporate background noise and focus insufficiently on real foreground (action-related instances), thereby compromising the recognition capability, particularly in the few-shot scenario. To tackle this issue, we propose a novel joint Image-Instance level Spatial-temporal attention approach (I2ST) for Few-shot Action Recognition. The core concept of I2ST is to perceive the action-related instances and integrate them with image features via spatial-temporal attention. Specifically, I2ST consists of two key components: Action-related Instance Perception and Joint Image-Instance Spatial-temporal Attention. Given the basic representations from the feature extractor, the Action-related Instance Perception is introduced to perceive action-related instances under the guidance of a text-guided segmentation model. Subsequently, the Joint Image-Instance Spatial-temporal Attention is used to construct the feature dependency between instances and images...
format Preprint
id arxiv_https___arxiv_org_abs_2503_14430
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognition
Qian, Zefeng
Zhang, Chongyang
Huang, Yifei
Wang, Gang
Ying, Jiangyong
Computer Vision and Pattern Recognition
Few-shot Action Recognition (FSAR) constitutes a crucial challenge in computer vision, entailing the recognition of actions from a limited set of examples. Recent approaches mainly focus on employing image-level features to construct temporal dependencies and generate prototypes for each action category. However, a considerable number of these methods utilize mainly image-level features that incorporate background noise and focus insufficiently on real foreground (action-related instances), thereby compromising the recognition capability, particularly in the few-shot scenario. To tackle this issue, we propose a novel joint Image-Instance level Spatial-temporal attention approach (I2ST) for Few-shot Action Recognition. The core concept of I2ST is to perceive the action-related instances and integrate them with image features via spatial-temporal attention. Specifically, I2ST consists of two key components: Action-related Instance Perception and Joint Image-Instance Spatial-temporal Attention. Given the basic representations from the feature extractor, the Action-related Instance Perception is introduced to perceive action-related instances under the guidance of a text-guided segmentation model. Subsequently, the Joint Image-Instance Spatial-temporal Attention is used to construct the feature dependency between instances and images...
title Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.14430