Improving Unsupervised Label Propagation for Pose Tracking and Video Object Segmentation

Waldmann, Urs; Bamberger, Jannik; Johannsen, Ole; Deussen, Oliver; Goldlücke, Bastian

Improving Unsupervised Label Propagation for Pose Tracking and Video Object Segmentation

Files

Waldmann_2-mn1vmh1ak0gf4.pdf(346.38 KB)

Date

2022

Restricted until

September 30, 2023

Publication type

Contribution to a conference collection

Publication status

Published

Published in

Pattern Recognition : 44th DAGM German Conference, DAGM GCPR 2022, Konstanz, Germany, September 27–30, 2022, Proceedings / Andres, Björn et al. (ed.). - Cham : Springer, 2022. - (Lecture Notes in Computer Science ; 13485). - pp. 230-245. - ISSN 0302-9743. - eISSN 1611-3349. - ISBN 978-3-031-16787-4

Abstract

Label propagation is a challenging task in computer vision with many applications. One approach is to learn representations of visual correspondence. In this paper, we study recent works on label propagation based on correspondence, carefully evaluate the effect of various aspects of their implementation, and improve upon various details. Our pipeline assembled from these best practices outperforms the previous state of the art in terms of PCK_0.1 on the JHMDB dataset by 6.5%. We also propose a novel joint framework for tracking and keypoint propagation, which in contrast to the core pipeline is applicable to tracking small objects and obtains results that substantially exceed the performance of the core pipeline. Finally, for VOS, we extend the core pipeline to a fully unsupervised one by initializing the first frame with the self-attention layer from DINO. Our pipeline for VOS runs online and can handle static objects. It outperforms unsupervised frameworks with these characteristics.

Subject (DDC)

004 Computer Science

Conference

4th DAGM German Conference on Pattern Recognition (DAGM GCPR 2022), Sep 27, 2022 - Sep 30, 2022, Konstanz

Cite This

ISO 690

WALDMANN, Urs, Jannik BAMBERGER, Ole JOHANNSEN, Oliver DEUSSEN, Bastian GOLDLÜCKE, 2022. Improving Unsupervised Label Propagation for Pose Tracking and Video Object Segmentation. 4th DAGM German Conference on Pattern Recognition (DAGM GCPR 2022). Konstanz, Sep 27, 2022 - Sep 30, 2022. In: ANDRES, Björn, ed. and others. Pattern Recognition : 44th DAGM German Conference, DAGM GCPR 2022, Konstanz, Germany, September 27–30, 2022, Proceedings. Cham:Springer, pp. 230-245. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-031-16787-4. Available under: doi: 10.1007/978-3-031-16788-1_15

BibTex

@inproceedings{Waldmann2022Impro-58701,
  year={2022},
  doi={10.1007/978-3-031-16788-1_15},
  title={Improving Unsupervised Label Propagation for Pose Tracking and Video Object Segmentation},
  number={13485},
  isbn={978-3-031-16787-4},
  issn={0302-9743},
  publisher={Springer},
  address={Cham},
  series={Lecture Notes in Computer Science},
  booktitle={Pattern Recognition : 44th DAGM German Conference, DAGM GCPR 2022, Konstanz, Germany, September 27–30, 2022, Proceedings},
  pages={230--245},
  editor={Andres, Björn},
  author={Waldmann, Urs and Bamberger, Jannik and Johannsen, Ole and Deussen, Oliver and Goldlücke, Bastian}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/58701">
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/58701"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-09-28T13:26:00Z</dcterms:available>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:language>eng</dc:language>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:rights>terms-of-use</dc:rights>
    <dc:contributor>Johannsen, Ole</dc:contributor>
    <dc:contributor>Waldmann, Urs</dc:contributor>
    <dc:contributor>Deussen, Oliver</dc:contributor>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dcterms:abstract xml:lang="eng">Label propagation is a challenging task in computer vision with many applications. One approach is to learn representations of visual correspondence. In this paper, we study recent works on label propagation based on correspondence, carefully evaluate the effect of various aspects of their implementation, and improve upon various details. Our pipeline assembled from these best practices outperforms the previous state of the art in terms of PCK&lt;sub&gt;0.1&lt;/sub&gt; on the JHMDB dataset by 6.5%. We also propose a novel joint framework for tracking and keypoint propagation, which in contrast to the core pipeline is applicable to tracking small objects and obtains results that substantially exceed the performance of the core pipeline. Finally, for VOS, we extend the core pipeline to a fully unsupervised one by initializing the first frame with the self-attention layer from DINO. Our pipeline for VOS runs online and can handle static objects. It outperforms unsupervised frameworks with these characteristics.</dcterms:abstract>
    <dc:contributor>Bamberger, Jannik</dc:contributor>
    <dcterms:title>Improving Unsupervised Label Propagation for Pose Tracking and Video Object Segmentation</dcterms:title>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Bamberger, Jannik</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-09-28T13:26:00Z</dc:date>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/>
    <dcterms:issued>2022</dcterms:issued>
    <dc:creator>Johannsen, Ole</dc:creator>
    <dc:creator>Deussen, Oliver</dc:creator>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Waldmann, Urs</dc:creator>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

Yes