Sparselet Models for Efficient Multiclass Object Detection View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2012

AUTHORS

Hyun Oh Song , Stefan Zickler , Tim Althoff , Ross Girshick , Mario Fritz , Christopher Geyer , Pedro Felzenszwalb , Trevor Darrell

ABSTRACT

We develop an intermediate representation for deformable part models and show that this representation has favorable performance characteristics for multi-class problems when the number of classes is high. Our model uses sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. This leads to a universal set of parts that are shared among all object classes. Reconstruction of the original part filter responses via sparse matrix-vector product reduces computation relative to conventional part filter convolutions. Our model is well suited to a parallel implementation, and we report a new GPU DPM implementation that takes advantage of sparse coding of part filters. The speed-up offered by our intermediate representation and parallel computation enable real-time DPM detection of 20 different object classes on a laptop computer. More... »

PAGES

802-815

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-33709-3_57

DOI

http://dx.doi.org/10.1007/978-3-642-33709-3_57

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1036259883


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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "UC Berkeley, USA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "UC Berkeley, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Song", 
        "givenName": "Hyun Oh", 
        "id": "sg:person.011500457705.56", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011500457705.56"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "iRobot, USA", 
          "id": "http://www.grid.ac/institutes/grid.455684.e", 
          "name": [
            "iRobot, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zickler", 
        "givenName": "Stefan", 
        "id": "sg:person.011214150241.39", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011214150241.39"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "UC Berkeley, USA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "UC Berkeley, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Althoff", 
        "givenName": "Tim", 
        "id": "sg:person.014466361705.84", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014466361705.84"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Chicago, USA", 
          "id": "http://www.grid.ac/institutes/grid.170205.1", 
          "name": [
            "University of Chicago, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Girshick", 
        "givenName": "Ross", 
        "id": "sg:person.016522642540.28", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016522642540.28"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Max Planck Institute for Informatics, Germany", 
          "id": "http://www.grid.ac/institutes/grid.419528.3", 
          "name": [
            "Max Planck Institute for Informatics, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fritz", 
        "givenName": "Mario", 
        "id": "sg:person.013361072755.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "iRobot, USA", 
          "id": "http://www.grid.ac/institutes/grid.455684.e", 
          "name": [
            "iRobot, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Geyer", 
        "givenName": "Christopher", 
        "id": "sg:person.01201217477.46", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01201217477.46"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Brown University, USA", 
          "id": "http://www.grid.ac/institutes/grid.40263.33", 
          "name": [
            "Brown University, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Felzenszwalb", 
        "givenName": "Pedro", 
        "id": "sg:person.01000754457.49", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01000754457.49"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "UC Berkeley, USA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "UC Berkeley, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Darrell", 
        "givenName": "Trevor", 
        "id": "sg:person.01001613660.25", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01001613660.25"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2012", 
    "datePublishedReg": "2012-01-01", 
    "description": "We develop an intermediate representation for deformable part models and show that this representation has favorable performance characteristics for multi-class problems when the number of classes is high. Our model uses sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. This leads to a universal set of parts that are shared among all object classes. Reconstruction of the original part filter responses via sparse matrix-vector product reduces computation relative to conventional part filter convolutions. Our model is well suited to a parallel implementation, and we report a new GPU DPM implementation that takes advantage of sparse coding of part filters. The speed-up offered by our intermediate representation and parallel computation enable real-time DPM detection of 20 different object classes on a laptop computer.", 
    "editor": [
      {
        "familyName": "Fitzgibbon", 
        "givenName": "Andrew", 
        "type": "Person"
      }, 
      {
        "familyName": "Lazebnik", 
        "givenName": "Svetlana", 
        "type": "Person"
      }, 
      {
        "familyName": "Perona", 
        "givenName": "Pietro", 
        "type": "Person"
      }, 
      {
        "familyName": "Sato", 
        "givenName": "Yoichi", 
        "type": "Person"
      }, 
      {
        "familyName": "Schmid", 
        "givenName": "Cordelia", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-33709-3_57", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-642-33708-6", 
        "978-3-642-33709-3"
      ], 
      "name": "Computer Vision \u2013 ECCV 2012", 
      "type": "Book"
    }, 
    "keywords": [
      "matrix-vector products", 
      "sparse matrix-vector product", 
      "object classes", 
      "linear combination", 
      "intermediate representation", 
      "number of classes", 
      "parallel computation", 
      "sparse coding", 
      "sparse linear combination", 
      "parallel implementation", 
      "multiclass object detection", 
      "different object classes", 
      "deformable part model", 
      "multi-class problems", 
      "universal set", 
      "dictionary elements", 
      "computation", 
      "part filters", 
      "object detection", 
      "part model", 
      "class", 
      "filter convolution", 
      "filter response", 
      "representation", 
      "filter", 
      "laptop computer", 
      "model", 
      "coding", 
      "convolution", 
      "implementation", 
      "problem", 
      "computer", 
      "set", 
      "performance characteristics", 
      "detection", 
      "favorable performance characteristics", 
      "number", 
      "advantages", 
      "elements", 
      "reconstruction", 
      "characteristics", 
      "combination", 
      "part", 
      "products", 
      "response"
    ], 
    "name": "Sparselet Models for Efficient Multiclass Object Detection", 
    "pagination": "802-815", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1036259883"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-33709-3_57"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-33709-3_57", 
      "https://app.dimensions.ai/details/publication/pub.1036259883"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-12-01T06:52", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/chapter/chapter_366.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-642-33709-3_57"
  }
]
 

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.10.1007/978-3-642-33709-3_57'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33709-3_57'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33709-3_57'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33709-3_57'


 

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

185 TRIPLES      22 PREDICATES      70 URIs      63 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-33709-3_57 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N88ccf47fc87d406e92ca8060621b7290
4 schema:datePublished 2012
5 schema:datePublishedReg 2012-01-01
6 schema:description We develop an intermediate representation for deformable part models and show that this representation has favorable performance characteristics for multi-class problems when the number of classes is high. Our model uses sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. This leads to a universal set of parts that are shared among all object classes. Reconstruction of the original part filter responses via sparse matrix-vector product reduces computation relative to conventional part filter convolutions. Our model is well suited to a parallel implementation, and we report a new GPU DPM implementation that takes advantage of sparse coding of part filters. The speed-up offered by our intermediate representation and parallel computation enable real-time DPM detection of 20 different object classes on a laptop computer.
7 schema:editor Nd2dfd1d986f24f0f856940979fd0d7a5
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N8648ea1fa534450f881d7ede6ccfc0bd
11 schema:keywords advantages
12 characteristics
13 class
14 coding
15 combination
16 computation
17 computer
18 convolution
19 deformable part model
20 detection
21 dictionary elements
22 different object classes
23 elements
24 favorable performance characteristics
25 filter
26 filter convolution
27 filter response
28 implementation
29 intermediate representation
30 laptop computer
31 linear combination
32 matrix-vector products
33 model
34 multi-class problems
35 multiclass object detection
36 number
37 number of classes
38 object classes
39 object detection
40 parallel computation
41 parallel implementation
42 part
43 part filters
44 part model
45 performance characteristics
46 problem
47 products
48 reconstruction
49 representation
50 response
51 set
52 sparse coding
53 sparse linear combination
54 sparse matrix-vector product
55 universal set
56 schema:name Sparselet Models for Efficient Multiclass Object Detection
57 schema:pagination 802-815
58 schema:productId N000b69e4b2b64bc29624c1d0c6cf2a16
59 N7784d26d8b5043f1bbb835b0d53047ab
60 schema:publisher N01db555016a84bc3be954ec255e85970
61 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036259883
62 https://doi.org/10.1007/978-3-642-33709-3_57
63 schema:sdDatePublished 2022-12-01T06:52
64 schema:sdLicense https://scigraph.springernature.com/explorer/license/
65 schema:sdPublisher N1cc813994542453fabe48739b927dc40
66 schema:url https://doi.org/10.1007/978-3-642-33709-3_57
67 sgo:license sg:explorer/license/
68 sgo:sdDataset chapters
69 rdf:type schema:Chapter
70 N000b69e4b2b64bc29624c1d0c6cf2a16 schema:name doi
71 schema:value 10.1007/978-3-642-33709-3_57
72 rdf:type schema:PropertyValue
73 N01db555016a84bc3be954ec255e85970 schema:name Springer Nature
74 rdf:type schema:Organisation
75 N1cc813994542453fabe48739b927dc40 schema:name Springer Nature - SN SciGraph project
76 rdf:type schema:Organization
77 N28cf93ae66004bcabfa26b14a7f9efe5 rdf:first sg:person.011214150241.39
78 rdf:rest N842e5a5959e5491eb3a9e676ad8a7fcb
79 N30730420f23a4d7583aefab0e993d572 schema:familyName Fitzgibbon
80 schema:givenName Andrew
81 rdf:type schema:Person
82 N3e84f7ff2f774864a2435415394e46c5 schema:familyName Perona
83 schema:givenName Pietro
84 rdf:type schema:Person
85 N4adede7ed7e14702bf5e778820137c71 rdf:first sg:person.01000754457.49
86 rdf:rest N6fe451f5562f4ca3b9ddbec51ff4cc34
87 N55994ff89bbf4e0398901bc3723d8dcb rdf:first sg:person.016522642540.28
88 rdf:rest Nb39ca61a8d074d07aff6dd759ca4373f
89 N5e9173b3283244c3bbf6638101e0ffe4 schema:familyName Schmid
90 schema:givenName Cordelia
91 rdf:type schema:Person
92 N671a4d17b1e84a0fa7f6a3f03c314a45 schema:familyName Lazebnik
93 schema:givenName Svetlana
94 rdf:type schema:Person
95 N6fe451f5562f4ca3b9ddbec51ff4cc34 rdf:first sg:person.01001613660.25
96 rdf:rest rdf:nil
97 N7784d26d8b5043f1bbb835b0d53047ab schema:name dimensions_id
98 schema:value pub.1036259883
99 rdf:type schema:PropertyValue
100 N842e5a5959e5491eb3a9e676ad8a7fcb rdf:first sg:person.014466361705.84
101 rdf:rest N55994ff89bbf4e0398901bc3723d8dcb
102 N8480e20b03044d3ea04fcf22761546f3 rdf:first N671a4d17b1e84a0fa7f6a3f03c314a45
103 rdf:rest Ne083b5a5d755478a8eba2d57fc7a4a29
104 N8648ea1fa534450f881d7ede6ccfc0bd schema:isbn 978-3-642-33708-6
105 978-3-642-33709-3
106 schema:name Computer Vision – ECCV 2012
107 rdf:type schema:Book
108 N88ccf47fc87d406e92ca8060621b7290 rdf:first sg:person.011500457705.56
109 rdf:rest N28cf93ae66004bcabfa26b14a7f9efe5
110 N9c51cb4b71734e81bcc73d1ac6023a45 schema:familyName Sato
111 schema:givenName Yoichi
112 rdf:type schema:Person
113 Nb39ca61a8d074d07aff6dd759ca4373f rdf:first sg:person.013361072755.17
114 rdf:rest Nd574aa2562da4bfda2cab25cea854635
115 Ncdbe5485c59a4b1db329d6bfedb6287d rdf:first N9c51cb4b71734e81bcc73d1ac6023a45
116 rdf:rest Ne91a7833bde2450b8c08284739df1998
117 Nd2dfd1d986f24f0f856940979fd0d7a5 rdf:first N30730420f23a4d7583aefab0e993d572
118 rdf:rest N8480e20b03044d3ea04fcf22761546f3
119 Nd574aa2562da4bfda2cab25cea854635 rdf:first sg:person.01201217477.46
120 rdf:rest N4adede7ed7e14702bf5e778820137c71
121 Ne083b5a5d755478a8eba2d57fc7a4a29 rdf:first N3e84f7ff2f774864a2435415394e46c5
122 rdf:rest Ncdbe5485c59a4b1db329d6bfedb6287d
123 Ne91a7833bde2450b8c08284739df1998 rdf:first N5e9173b3283244c3bbf6638101e0ffe4
124 rdf:rest rdf:nil
125 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
126 schema:name Information and Computing Sciences
127 rdf:type schema:DefinedTerm
128 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
129 schema:name Artificial Intelligence and Image Processing
130 rdf:type schema:DefinedTerm
131 sg:person.01000754457.49 schema:affiliation grid-institutes:grid.40263.33
132 schema:familyName Felzenszwalb
133 schema:givenName Pedro
134 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01000754457.49
135 rdf:type schema:Person
136 sg:person.01001613660.25 schema:affiliation grid-institutes:grid.47840.3f
137 schema:familyName Darrell
138 schema:givenName Trevor
139 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01001613660.25
140 rdf:type schema:Person
141 sg:person.011214150241.39 schema:affiliation grid-institutes:grid.455684.e
142 schema:familyName Zickler
143 schema:givenName Stefan
144 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011214150241.39
145 rdf:type schema:Person
146 sg:person.011500457705.56 schema:affiliation grid-institutes:grid.47840.3f
147 schema:familyName Song
148 schema:givenName Hyun Oh
149 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011500457705.56
150 rdf:type schema:Person
151 sg:person.01201217477.46 schema:affiliation grid-institutes:grid.455684.e
152 schema:familyName Geyer
153 schema:givenName Christopher
154 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01201217477.46
155 rdf:type schema:Person
156 sg:person.013361072755.17 schema:affiliation grid-institutes:grid.419528.3
157 schema:familyName Fritz
158 schema:givenName Mario
159 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17
160 rdf:type schema:Person
161 sg:person.014466361705.84 schema:affiliation grid-institutes:grid.47840.3f
162 schema:familyName Althoff
163 schema:givenName Tim
164 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014466361705.84
165 rdf:type schema:Person
166 sg:person.016522642540.28 schema:affiliation grid-institutes:grid.170205.1
167 schema:familyName Girshick
168 schema:givenName Ross
169 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016522642540.28
170 rdf:type schema:Person
171 grid-institutes:grid.170205.1 schema:alternateName University of Chicago, USA
172 schema:name University of Chicago, USA
173 rdf:type schema:Organization
174 grid-institutes:grid.40263.33 schema:alternateName Brown University, USA
175 schema:name Brown University, USA
176 rdf:type schema:Organization
177 grid-institutes:grid.419528.3 schema:alternateName Max Planck Institute for Informatics, Germany
178 schema:name Max Planck Institute for Informatics, Germany
179 rdf:type schema:Organization
180 grid-institutes:grid.455684.e schema:alternateName iRobot, USA
181 schema:name iRobot, USA
182 rdf:type schema:Organization
183 grid-institutes:grid.47840.3f schema:alternateName UC Berkeley, USA
184 schema:name UC Berkeley, USA
185 rdf:type schema:Organization
 




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


...