Training Deformable Object Models for Human Detection Based on Alignment and Clustering View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2014

AUTHORS

Benjamin Drayer , Thomas Brox

ABSTRACT

We propose a clustering method that considers non-rigid alignment of samples. The motivation for such a clustering is training of object detectors that consist of multiple mixture components. In particular, we consider the deformable part model (DPM) of Felzenszwalb et al., where each mixture component includes a learned deformation model. We show that alignment based clustering distributes the data better to the mixture components of the DPM than previous methods. Moreover, the alignment helps the non-convex optimization of the DPM find a consistent placement of its parts and, thus, learn more accurate part filters. More... »

PAGES

406-420

Book

TITLE

Computer Vision – ECCV 2014

ISBN

978-3-319-10601-4
978-3-319-10602-1

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-10602-1_27

DOI

http://dx.doi.org/10.1007/978-3-319-10602-1_27

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1008343541


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Department of Computer Science, Centre of Biological Signalling Studies (BIOSS), University of Freiburg, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "Department of Computer Science, Centre of Biological Signalling Studies (BIOSS), University of Freiburg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Drayer", 
        "givenName": "Benjamin", 
        "id": "sg:person.01172274323.26", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01172274323.26"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Computer Science, Centre of Biological Signalling Studies (BIOSS), University of Freiburg, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "Department of Computer Science, Centre of Biological Signalling Studies (BIOSS), University of Freiburg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Brox", 
        "givenName": "Thomas", 
        "id": "sg:person.012443225372.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2014", 
    "datePublishedReg": "2014-01-01", 
    "description": "We propose a clustering method that considers non-rigid alignment of samples. The motivation for such a clustering is training of object detectors that consist of multiple mixture components. In particular, we consider the deformable part model (DPM) of Felzenszwalb et al., where each mixture component includes a learned deformation model. We show that alignment based clustering distributes the data better to the mixture components of the DPM than previous methods. Moreover, the alignment helps the non-convex optimization of the DPM find a consistent placement of its parts and, thus, learn more accurate part filters.", 
    "editor": [
      {
        "familyName": "Fleet", 
        "givenName": "David", 
        "type": "Person"
      }, 
      {
        "familyName": "Pajdla", 
        "givenName": "Tomas", 
        "type": "Person"
      }, 
      {
        "familyName": "Schiele", 
        "givenName": "Bernt", 
        "type": "Person"
      }, 
      {
        "familyName": "Tuytelaars", 
        "givenName": "Tinne", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-10602-1_27", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-10601-4", 
        "978-3-319-10602-1"
      ], 
      "name": "Computer Vision \u2013 ECCV 2014", 
      "type": "Book"
    }, 
    "keywords": [
      "non-convex optimization", 
      "mixture components", 
      "deformable object model", 
      "multiple mixture components", 
      "deformable part model", 
      "previous methods", 
      "et al", 
      "clustering", 
      "model", 
      "object model", 
      "part model", 
      "optimization", 
      "deformation model", 
      "filter", 
      "detector", 
      "al", 
      "components", 
      "non-rigid alignment", 
      "part filters", 
      "alignment", 
      "object detector", 
      "consistent placement", 
      "data", 
      "part", 
      "motivation", 
      "placement", 
      "human detection", 
      "samples", 
      "detection", 
      "training", 
      "Felzenszwalb et al", 
      "method"
    ], 
    "name": "Training Deformable Object Models for Human Detection Based on Alignment and Clustering", 
    "pagination": "406-420", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1008343541"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-10602-1_27"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-10602-1_27", 
      "https://app.dimensions.ai/details/publication/pub.1008343541"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-10-01T06:54", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221001/entities/gbq_results/chapter/chapter_221.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-10602-1_27"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-10602-1_27'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-10602-1_27'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-10602-1_27'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-10602-1_27'


 

This table displays all metadata directly associated to this object as RDF triples.

113 TRIPLES      22 PREDICATES      57 URIs      50 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-10602-1_27 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 schema:author N59102ed28ffe4a63af4543ba8b2f809f
4 schema:datePublished 2014
5 schema:datePublishedReg 2014-01-01
6 schema:description We propose a clustering method that considers non-rigid alignment of samples. The motivation for such a clustering is training of object detectors that consist of multiple mixture components. In particular, we consider the deformable part model (DPM) of Felzenszwalb et al., where each mixture component includes a learned deformation model. We show that alignment based clustering distributes the data better to the mixture components of the DPM than previous methods. Moreover, the alignment helps the non-convex optimization of the DPM find a consistent placement of its parts and, thus, learn more accurate part filters.
7 schema:editor Nb914824fafd74d42bb89b859f04b75a5
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N1e1c6dbc714c441389f120bd7efa69e2
11 schema:keywords Felzenszwalb et al
12 al
13 alignment
14 clustering
15 components
16 consistent placement
17 data
18 deformable object model
19 deformable part model
20 deformation model
21 detection
22 detector
23 et al
24 filter
25 human detection
26 method
27 mixture components
28 model
29 motivation
30 multiple mixture components
31 non-convex optimization
32 non-rigid alignment
33 object detector
34 object model
35 optimization
36 part
37 part filters
38 part model
39 placement
40 previous methods
41 samples
42 training
43 schema:name Training Deformable Object Models for Human Detection Based on Alignment and Clustering
44 schema:pagination 406-420
45 schema:productId N3ddc7ca7a8964dac8e239f6dfe1b5002
46 N9820b15d4a244f70a82ecda1e2e10861
47 schema:publisher N86166432b3454e5091383a2d7dcffb4c
48 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008343541
49 https://doi.org/10.1007/978-3-319-10602-1_27
50 schema:sdDatePublished 2022-10-01T06:54
51 schema:sdLicense https://scigraph.springernature.com/explorer/license/
52 schema:sdPublisher N55fb2d158042446db6250c947c0e7517
53 schema:url https://doi.org/10.1007/978-3-319-10602-1_27
54 sgo:license sg:explorer/license/
55 sgo:sdDataset chapters
56 rdf:type schema:Chapter
57 N0dad50d27be24d47bcd7be612d9fc994 rdf:first N3ce02c81666d48dc96e7c20910249692
58 rdf:rest Na0414690786b484db0340b7080103a29
59 N1dfb223ed04a430bb574578ff07e271b rdf:first Nf40aa0f947b44fb9860788276b3a2213
60 rdf:rest N0dad50d27be24d47bcd7be612d9fc994
61 N1e1c6dbc714c441389f120bd7efa69e2 schema:isbn 978-3-319-10601-4
62 978-3-319-10602-1
63 schema:name Computer Vision – ECCV 2014
64 rdf:type schema:Book
65 N3ce02c81666d48dc96e7c20910249692 schema:familyName Schiele
66 schema:givenName Bernt
67 rdf:type schema:Person
68 N3ddc7ca7a8964dac8e239f6dfe1b5002 schema:name doi
69 schema:value 10.1007/978-3-319-10602-1_27
70 rdf:type schema:PropertyValue
71 N55fb2d158042446db6250c947c0e7517 schema:name Springer Nature - SN SciGraph project
72 rdf:type schema:Organization
73 N59102ed28ffe4a63af4543ba8b2f809f rdf:first sg:person.01172274323.26
74 rdf:rest Neeb7f7eb7fe8471f9ea72c64d19f3ed3
75 N7acb2cc94fea483195422b3420d8c1ac schema:familyName Fleet
76 schema:givenName David
77 rdf:type schema:Person
78 N86166432b3454e5091383a2d7dcffb4c schema:name Springer Nature
79 rdf:type schema:Organisation
80 N9820b15d4a244f70a82ecda1e2e10861 schema:name dimensions_id
81 schema:value pub.1008343541
82 rdf:type schema:PropertyValue
83 Na0414690786b484db0340b7080103a29 rdf:first Nd485df814d6f4e4a98195be3f296e2b0
84 rdf:rest rdf:nil
85 Nb914824fafd74d42bb89b859f04b75a5 rdf:first N7acb2cc94fea483195422b3420d8c1ac
86 rdf:rest N1dfb223ed04a430bb574578ff07e271b
87 Nd485df814d6f4e4a98195be3f296e2b0 schema:familyName Tuytelaars
88 schema:givenName Tinne
89 rdf:type schema:Person
90 Neeb7f7eb7fe8471f9ea72c64d19f3ed3 rdf:first sg:person.012443225372.65
91 rdf:rest rdf:nil
92 Nf40aa0f947b44fb9860788276b3a2213 schema:familyName Pajdla
93 schema:givenName Tomas
94 rdf:type schema:Person
95 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
96 schema:name Mathematical Sciences
97 rdf:type schema:DefinedTerm
98 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
99 schema:name Statistics
100 rdf:type schema:DefinedTerm
101 sg:person.01172274323.26 schema:affiliation grid-institutes:grid.5963.9
102 schema:familyName Drayer
103 schema:givenName Benjamin
104 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01172274323.26
105 rdf:type schema:Person
106 sg:person.012443225372.65 schema:affiliation grid-institutes:grid.5963.9
107 schema:familyName Brox
108 schema:givenName Thomas
109 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65
110 rdf:type schema:Person
111 grid-institutes:grid.5963.9 schema:alternateName Department of Computer Science, Centre of Biological Signalling Studies (BIOSS), University of Freiburg, Germany
112 schema:name Department of Computer Science, Centre of Biological Signalling Studies (BIOSS), University of Freiburg, Germany
113 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...