Few–Shot Action Recognition

Valeti Likhitha Chowdary , Nidadavolu Bhavya Sree Ratna , Ankitha Lunavath , Rajesh Kandakatla

FSL - Few-Shot Learning PAL - Prototype-centered Attentive Learning

The goal of few-shot action identification is to detect new action classes using only a few sets of training samples. The majority of available approaches use a meta-learning approach combined with episodic training. The few samples in a meta-training job are divided into support and query sets in each episode. The former is used to construct a classifier, which is subsequently assessed on the latter using a query-centered loss for updating the model. However, there are two key limitations, which are: a lack of data efficiency attributable to the query-centered only loss design and an inability to cope with outlying samples and inter-class distribution overlapping anomalies raised within the support set. We address these shortcomings in this study by introducing a new Prototype-centered Attentive Learning (PAL) model consisting of two revolutionary components. To make maximum use of the minimal training samples in each episode, a prototype-centered contrastive learning loss is introduced to enhance the traditional query-centered learning objective. Second, PAL incorporates a hybrid attentive learning method that can reduce the adverse effects of outliers while also promoting class separation.

Published Paper   E-Certificate

"Few–Shot Action Recognition", IJEDR - INTERNATIONAL JOURNAL OF ENGINEERING DEVELOPMENT AND RESEARCH (www.IJEDR.org), ISSN:2321-9939, Vol.10, Issue 2, page no.181-185, June 2022, Available :https://rjwave.org/IJEDR/papers/IJEDR2202031.pdf

Volume 10 Issue 2, May-2022

Pages : 181-185

Paper Reg. ID: IJEDR_220098

Published Paper Id: IJEDR2202031

Research Area: Computer Science & Technology 

Country: Hyderabad, Telangana, India

Published Paper PDF: https://rjwave.org/IJEDR/papers/IJEDR2202031

Published Paper URL: https://rjwave.org/IJEDR/viewpaperforall?paper=IJEDR2202031

DOI: http://doi.one/10.1729/Journal.30748

ISSN: 2321-9939 | IMPACT FACTOR: 9.37 Calculated By Google Scholar | ESTD YEAR: 2013

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.37 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJEDR (IJ Publication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition