Academic Journal
Προβολή σε EDS

SETJiP: Spatial and Extra Temporal Jigsaw Puzzles for Video Anomaly Detection †.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: SETJiP: Spatial and Extra Temporal Jigsaw Puzzles for Video Anomaly Detection †.
Συγγραφείς: Shen, Liheng1 (AUTHOR) lihengsh666@gmail.com, Matsukawa, Tetsu2 (AUTHOR), Suzuki, Einoshin1,2 (AUTHOR)
Πηγή: Sensors (14248220). May2026, Vol. 26 Issue 9, p2889. 37p.
Θεματικοί όροι: *Jigsaw puzzles, *Computer vision, *Anomaly detection (Computer security), *Machine learning, *Supervised learning
Περίληψη: Video Anomaly Detection (VAD) is commonly formulated as a one-class classification task. Global motion, with temporal variations across most pixels within an object-centric region, e.g., walking, is typically regular, whereas localized motion, e.g., waving, can be ambiguous. Decoupled spatial and temporal jigsaw puzzles (DSTJiP) is a self-supervised method that learns discriminative representations by predicting the original order of spatially and temporally shuffled patches. However, DSTJiP's uniform sampling and equal weighting do not assign stronger supervision to global-motion examples within the temporal objective. Consequently, the temporal supervision allocated to global-motion examples may become insufficient across training-data regimes with varying proportions of these examples, deteriorating VAD performance. Nevertheless, excessively strengthening such supervision also degrades performance. To address these issues, we propose spatial and extra temporal jigsaw puzzles (SETJiP) with two RGB-only training schemes that provide stronger and more conservative temporal supervision for global-motion examples, respectively. One scheme strengthens temporal supervision on these examples via additional temporal jigsaw puzzles. The other does so more conservatively by upweighting their temporal jigsaw puzzles. Experiments on four VAD benchmarks show that both schemes improve on DSTJiP and remain highly competitive with state-of-the-art methods. [ABSTRACT FROM AUTHOR]
Βάση Δεδομένων: Academic Search Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:asx&genre=article&issn=14248220&ISBN=&volume=26&issue=9&date=20260501&spage=2889&pages=2889-2925&title=Sensors (14248220)&atitle=SETJiP%3A%20Spatial%20and%20Extra%20Temporal%20Jigsaw%20Puzzles%20for%20Video%20Anomaly%20Detection%20%E2%80%A0.&aulast=Shen%2C%20Liheng&id=DOI:10.3390/s26092889
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: asx
DbLabel: Academic Search Index
An: 193714793
RelevancyScore: 1431
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1430.76245117188
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: SETJiP: Spatial and Extra Temporal Jigsaw Puzzles for Video Anomaly Detection †.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Shen%2C+Liheng%22">Shen, Liheng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> lihengsh666@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Matsukawa%2C+Tetsu%22">Matsukawa, Tetsu</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Suzuki%2C+Einoshin%22">Suzuki, Einoshin</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Sensors+%2814248220%29%22">Sensors (14248220)</searchLink>. May2026, Vol. 26 Issue 9, p2889. 37p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Jigsaw+puzzles%22">Jigsaw puzzles</searchLink><br />*<searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br />*<searchLink fieldCode="DE" term="%22Anomaly+detection+%28Computer+security%29%22">Anomaly detection (Computer security)</searchLink><br />*<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Supervised+learning%22">Supervised learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Video Anomaly Detection (VAD) is commonly formulated as a one-class classification task. Global motion, with temporal variations across most pixels within an object-centric region, e.g., walking, is typically regular, whereas localized motion, e.g., waving, can be ambiguous. Decoupled spatial and temporal jigsaw puzzles (DSTJiP) is a self-supervised method that learns discriminative representations by predicting the original order of spatially and temporally shuffled patches. However, DSTJiP's uniform sampling and equal weighting do not assign stronger supervision to global-motion examples within the temporal objective. Consequently, the temporal supervision allocated to global-motion examples may become insufficient across training-data regimes with varying proportions of these examples, deteriorating VAD performance. Nevertheless, excessively strengthening such supervision also degrades performance. To address these issues, we propose spatial and extra temporal jigsaw puzzles (SETJiP) with two RGB-only training schemes that provide stronger and more conservative temporal supervision for global-motion examples, respectively. One scheme strengthens temporal supervision on these examples via additional temporal jigsaw puzzles. The other does so more conservatively by upweighting their temporal jigsaw puzzles. Experiments on four VAD benchmarks show that both schemes improve on DSTJiP and remain highly competitive with state-of-the-art methods. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=asx&AN=193714793
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/s26092889
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 37
        StartPage: 2889
    Subjects:
      – SubjectFull: Jigsaw puzzles
        Type: general
      – SubjectFull: Computer vision
        Type: general
      – SubjectFull: Anomaly detection (Computer security)
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Supervised learning
        Type: general
    Titles:
      – TitleFull: SETJiP: Spatial and Extra Temporal Jigsaw Puzzles for Video Anomaly Detection †.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Shen, Liheng
      – PersonEntity:
          Name:
            NameFull: Matsukawa, Tetsu
      – PersonEntity:
          Name:
            NameFull: Suzuki, Einoshin
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 14248220
          Numbering:
            – Type: volume
              Value: 26
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: Sensors (14248220)
              Type: main
ResultId 1