<?xml version="1.0" encoding="utf-8"?><!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.2d1 20170631//EN" "JATS-journalpublishing1.dtd">
<ArticleSet>
  <Article>
    <Journal>
      <PublisherName>IJIRCSTJournal</PublisherName>
      <JournalTitle>International Journal of Innovative Research in Computer Science and Technology</JournalTitle>
      <PISSN>I</PISSN>
      <EISSN>S</EISSN>
      <Volume-Issue>Volume 12 Issue 3</Volume-Issue>
      <PartNumber/>
      <IssueTopic>Computer Science and Engineering</IssueTopic>
      <IssueLanguage>English</IssueLanguage>
      <Season>May - June 2024</Season>
      <SpecialIssue>N</SpecialIssue>
      <SupplementaryIssue>N</SupplementaryIssue>
      <IssueOA>Y</IssueOA>
      <PubDate>
        <Year>2024</Year>
        <Month>05</Month>
        <Day>20</Day>
      </PubDate>
      <ArticleType>Computer Sciences</ArticleType>
      <ArticleTitle>A Comprehensive Review of YOLOv5: Advances in Real-Time Object Detection</ArticleTitle>
      <SubTitle/>
      <ArticleLanguage>English</ArticleLanguage>
      <ArticleOA>Y</ArticleOA>
      <FirstPage>75</FirstPage>
      <LastPage>80</LastPage>
      <AuthorList>
        <Author>
          <FirstName>Sandeep Kumar Jaiswal</FirstName>          
          <AuthorLanguage>English</AuthorLanguage>
          <Affiliation/>
          <CorrespondingAuthor>Y</CorrespondingAuthor>
          <ORCID/>
                      <FirstName>Rohit Agrawal</FirstName>          
          <AuthorLanguage>English</AuthorLanguage>
          <Affiliation/>
          <CorrespondingAuthor>N</CorrespondingAuthor>
          <ORCID/>
           
        </Author>
      </AuthorList>
      <DOI>https://doi.org/10.55524/ijircst.2024.12.3.12</DOI>
      <Abstract>YOLOv5 represents a significant advancement in the field of real-time object detection, building upon the YOLO (You Only Look Once) series&amp;#39; legacy. This paper provides a comprehensive review of YOLOv5, examining its architecture, innovations, performance benchmarks, and applications. We also compare YOLOv5 with previous YOLO versions and other state-of-the-art object detection models, highlighting its strengths and limitations. Through this review, we aim to offer insights into the evolution of YOLOv5 and its impact on the field of computer vision.</Abstract>
      <AbstractLanguage>English</AbstractLanguage>
      <Keywords>YOLOv5, YOLOv4, Object Detection, Real-time, Performance Evaluation</Keywords>
      <URLs>
        <Abstract>https://ijircst.org/abstract.php?article_id=1264</Abstract>
      </URLs>      
    </Journal>
  </Article>
</ArticleSet>