OTDE: optimal transport distribution enhancement for few-shot video recognition

In recent years, action recognition has become a subject of focus in the field of computer vision. Interest has emerged regarding the recognition of previously unseen classes given a few labeled examples; this is known as few-shot video recognition (F-SVR). However, it is particularly challenging to...

Full description

Saved in:
Bibliographic Details
Published in:Applied intelligence (Dordrecht, Netherlands) Netherlands), 2023-07, Vol.53 (13), p.17115-17127
Main Authors: Qin, Yanfei, Liu, Baolin
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Classification
Computer Science
Computer vision
Datasets
Deep learning
Machines
Manufacturing
Mechanical Engineering
Methods
Processes
Recognition
Text categorization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, action recognition has become a subject of focus in the field of computer vision. Interest has emerged regarding the recognition of previously unseen classes given a few labeled examples; this is known as few-shot video recognition (F-SVR). However, it is particularly challenging to learn the class representation in this kind of setting. In response to this difficulty, we present an optimal transport distribution enhancement (OTDE) mechanism that enables networks to adaptively enhance the given support videos. Our main idea is to design an optimal transport method by using the base classes of data to calibrate the biased distribution of the support set in F-SVR and generate enhanced samples to better model the distribution of intra-class features and estimate the similarity between them in an accurate and robust manner. In addition, the proposed OTDE component is a simple yet flexible approach and is adaptable to multiple existing F-SVR frameworks. By adopting OTDE, our design brings substantial performance improvements to a variety of current works, achieving competitive results on the Kinetics, UCF101 and HMDB51 datasets under various evaluation settings.
ISSN:0924-669X
1573-7497
DOI:10.1007/s10489-022-04369-4