Low Cost Journal,International Peer Reviewed and Refereed Journals,Fast Paper Publication approved journal IJEDR(ISSN 2321-9939) apply for ugc care approved journal, UGC Approved Journal, ugc approved journal, ugc approved list of journal, ugc care journal, care journal, UGC-CARE list, New UGC-CARE Reference List, UGC CARE Journals, ugc care list of journal, ugc care list 2020, ugc care approved journal, ugc care list 2020, new ugc approved journal in 2020, Low cost research journal, Online international research journal, Peer-reviewed, and Refereed Journals, scholarly journals, impact factor 7.37 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool)
(International Peer Reviewed,Refereed, Indexed, Citation Open Access Journal)
ISSN: 2321-9939 | ESTD Year: 2013

Current Issue

Call For Papers
July 2022

Volume 10 | Issue 3
Last Date : 29 July 2022
Review Results: Within 12-20 Days

For Authors


Indexing Partner

Research Area


Paper Details
Paper Title
Few–Shot Action Recognition
  Valeti Likhitha Chowdary,  Nidadavolu Bhavya Sree Ratna,  Ankitha Lunavath,  Rajesh Kandakatla

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.

Keywords- FSL - Few-Shot Learning PAL - Prototype-centered Attentive Learning
Publication Details
Unique Identification Number - IJEDR2202031
Page Number(s) - 181-185
Pubished in - Volume 10 | Issue 2 | June 2022
DOI (Digital Object Identifier) -    http://doi.one/10.1729/Journal.30748
Publisher - IJEDR (ISSN - 2321-9939)
Cite this Article
  Valeti Likhitha Chowdary,  Nidadavolu Bhavya Sree Ratna,  Ankitha Lunavath,  Rajesh Kandakatla,   "Few–Shot Action Recognition", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.10, Issue 2, pp.181-185, June 2022, Available at :http://www.ijedr.org/papers/IJEDR2202031.pdf
Share This Article

Article Preview

ISSN Details

DOI Details

Providing A digital object identifier by DOI
How to get DOI?

For Reviewer /Referral (RMS)

Important Links

NEWS & Conference

Digital Library

Our Social Link

© Copyright 2022 IJEDR.ORG All rights reserved