Object Localization with Boosting and Weak Supervision for Generic Object Recognition View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2005

AUTHORS

Andreas Opelt , Axel Pinz

ABSTRACT

This paper deals, for the first time, with an analysis of localization capabilities of weakly supervised categorization systems. Most existing categorization approaches have been tested on databases, which (a) either show the object(s) of interest in a very prominent way so that their localization can hardly be judged from these experiments, or (b) at least the learning procedure was done with supervision, which forces the system to learn only object relevant data. These approaches cannot be directly compared to a nearly unsupervised method. The main contribution of our paper thus is twofold: First, we have set up a new database which is sufficiently complex, balanced with respect to background, and includes localization ground truth. Second, we show, how our successful approach for generic object recognition [14] can be extended to perform localization, too.To analyze its localization potential, we develop localization measures which focus on approaches based on Boosting [5]. Our experiments show that localization depends on the object category, as well as on the type of the local descriptor. More... »

PAGES

862-871

References to SciGraph publications

Book

TITLE

Image Analysis

ISBN

978-3-540-26320-3
978-3-540-31566-7

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/11499145_87

DOI

http://dx.doi.org/10.1007/11499145_87

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1030262182


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/2008/0806", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information Systems", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Graz University of Technology", 
          "id": "https://www.grid.ac/institutes/grid.410413.3", 
          "name": [
            "Institute of Electrical Measurement and Measurement Signal Processing, Graz University of Technology, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Opelt", 
        "givenName": "Andreas", 
        "id": "sg:person.013624034621.75", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013624034621.75"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Graz University of Technology", 
          "id": "https://www.grid.ac/institutes/grid.410413.3", 
          "name": [
            "Institute of Electrical Measurement and Measurement Signal Processing, Graz University of Technology, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Pinz", 
        "givenName": "Axel", 
        "id": "sg:person.012033065653.49", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012033065653.49"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/978-3-540-24670-1_19", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003570178", 
          "https://doi.org/10.1007/978-3-540-24670-1_19"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-24670-1_19", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003570178", 
          "https://doi.org/10.1007/978-3-540-24670-1_19"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1006/jcss.1997.1504", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004338842"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bfb0015574", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039472253", 
          "https://doi.org/10.1007/bfb0015574"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-28649-3_18", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040710754", 
          "https://doi.org/10.1007/978-3-540-28649-3_18"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-28649-3_18", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040710754", 
          "https://doi.org/10.1007/978-3-540-28649-3_18"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-24671-8_6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1046580260", 
          "https://doi.org/10.1007/978-3-540-24671-8_6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-24671-8_6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1046580260", 
          "https://doi.org/10.1007/978-3-540-24671-8_6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-47969-4_9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1046596731", 
          "https://doi.org/10.1007/3-540-47969-4_9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/34.1000236", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061155588"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2004.108", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061742623"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2004.1315241", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094870330"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icpr.2004.1334464", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095551955"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2001.937561", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095654754"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.1999.790410", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095766209"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5244/c.18.98", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099382684"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2005", 
    "datePublishedReg": "2005-01-01", 
    "description": "This paper deals, for the first time, with an analysis of localization capabilities of weakly supervised categorization systems. Most existing categorization approaches have been tested on databases, which (a) either show the object(s) of interest in a very prominent way so that their localization can hardly be judged from these experiments, or (b) at least the learning procedure was done with supervision, which forces the system to learn only object relevant data. These approaches cannot be directly compared to a nearly unsupervised method. The main contribution of our paper thus is twofold: First, we have set up a new database which is sufficiently complex, balanced with respect to background, and includes localization ground truth. Second, we show, how our successful approach for generic object recognition [14] can be extended to perform localization, too.To analyze its localization potential, we develop localization measures which focus on approaches based on Boosting [5]. Our experiments show that localization depends on the object category, as well as on the type of the local descriptor.", 
    "editor": [
      {
        "familyName": "Kalviainen", 
        "givenName": "Heikki", 
        "type": "Person"
      }, 
      {
        "familyName": "Parkkinen", 
        "givenName": "Jussi", 
        "type": "Person"
      }, 
      {
        "familyName": "Kaarna", 
        "givenName": "Arto", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/11499145_87", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-540-26320-3", 
        "978-3-540-31566-7"
      ], 
      "name": "Image Analysis", 
      "type": "Book"
    }, 
    "name": "Object Localization with Boosting and Weak Supervision for Generic Object Recognition", 
    "pagination": "862-871", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1030262182"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/11499145_87"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "902a19d884dfeac16e2defd7f89d5581b8d61cd1295861eedf48d5febaa2485a"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/11499145_87", 
      "https://app.dimensions.ai/details/publication/pub.1030262182"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T08:00", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000359_0000000359/records_29191_00000001.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F11499145_87"
  }
]
 

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.10.1007/11499145_87'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/11499145_87'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/11499145_87'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/11499145_87'


 

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

126 TRIPLES      23 PREDICATES      40 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/11499145_87 schema:about anzsrc-for:08
2 anzsrc-for:0806
3 schema:author N0de7bf0a48714197b2784bee4200afa2
4 schema:citation sg:pub.10.1007/3-540-47969-4_9
5 sg:pub.10.1007/978-3-540-24670-1_19
6 sg:pub.10.1007/978-3-540-24671-8_6
7 sg:pub.10.1007/978-3-540-28649-3_18
8 sg:pub.10.1007/bfb0015574
9 https://doi.org/10.1006/jcss.1997.1504
10 https://doi.org/10.1109/34.1000236
11 https://doi.org/10.1109/cvpr.2004.1315241
12 https://doi.org/10.1109/iccv.1999.790410
13 https://doi.org/10.1109/iccv.2001.937561
14 https://doi.org/10.1109/icpr.2004.1334464
15 https://doi.org/10.1109/tpami.2004.108
16 https://doi.org/10.5244/c.18.98
17 schema:datePublished 2005
18 schema:datePublishedReg 2005-01-01
19 schema:description This paper deals, for the first time, with an analysis of localization capabilities of weakly supervised categorization systems. Most existing categorization approaches have been tested on databases, which (a) either show the object(s) of interest in a very prominent way so that their localization can hardly be judged from these experiments, or (b) at least the learning procedure was done with supervision, which forces the system to learn only object relevant data. These approaches cannot be directly compared to a nearly unsupervised method. The main contribution of our paper thus is twofold: First, we have set up a new database which is sufficiently complex, balanced with respect to background, and includes localization ground truth. Second, we show, how our successful approach for generic object recognition [14] can be extended to perform localization, too.To analyze its localization potential, we develop localization measures which focus on approaches based on Boosting [5]. Our experiments show that localization depends on the object category, as well as on the type of the local descriptor.
20 schema:editor N02408e1fa64d4a9abdf41204d2d762ce
21 schema:genre chapter
22 schema:inLanguage en
23 schema:isAccessibleForFree true
24 schema:isPartOf N277b6e1644674f9aa61ebe23ccd056e2
25 schema:name Object Localization with Boosting and Weak Supervision for Generic Object Recognition
26 schema:pagination 862-871
27 schema:productId N105e7f303eca49c9a2f299b6e9e5c385
28 N4879fa45fe6c4d32bee15231b41f74af
29 Ncbac3a0666e74c2ca64dd5717641a086
30 schema:publisher N8f582ce9cd234b58a53ede15dd4cc3f0
31 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030262182
32 https://doi.org/10.1007/11499145_87
33 schema:sdDatePublished 2019-04-16T08:00
34 schema:sdLicense https://scigraph.springernature.com/explorer/license/
35 schema:sdPublisher N062aa1a28fe8411dbdd5ee39c7d1f7e9
36 schema:url https://link.springer.com/10.1007%2F11499145_87
37 sgo:license sg:explorer/license/
38 sgo:sdDataset chapters
39 rdf:type schema:Chapter
40 N02408e1fa64d4a9abdf41204d2d762ce rdf:first Na099df3c38cc4f31b43179587a922558
41 rdf:rest N238f22fc785d400984d498eefc643600
42 N062aa1a28fe8411dbdd5ee39c7d1f7e9 schema:name Springer Nature - SN SciGraph project
43 rdf:type schema:Organization
44 N0de7bf0a48714197b2784bee4200afa2 rdf:first sg:person.013624034621.75
45 rdf:rest N803a52a824cb4c24944633e062559480
46 N105e7f303eca49c9a2f299b6e9e5c385 schema:name dimensions_id
47 schema:value pub.1030262182
48 rdf:type schema:PropertyValue
49 N238f22fc785d400984d498eefc643600 rdf:first N351eb6d69f7e4fdb991f6c9a4318826f
50 rdf:rest N70041891012d4abbac25cf10790c3dd5
51 N277b6e1644674f9aa61ebe23ccd056e2 schema:isbn 978-3-540-26320-3
52 978-3-540-31566-7
53 schema:name Image Analysis
54 rdf:type schema:Book
55 N351eb6d69f7e4fdb991f6c9a4318826f schema:familyName Parkkinen
56 schema:givenName Jussi
57 rdf:type schema:Person
58 N4879fa45fe6c4d32bee15231b41f74af schema:name doi
59 schema:value 10.1007/11499145_87
60 rdf:type schema:PropertyValue
61 N70041891012d4abbac25cf10790c3dd5 rdf:first Naa124c83647d4d41be162491e7a9e079
62 rdf:rest rdf:nil
63 N803a52a824cb4c24944633e062559480 rdf:first sg:person.012033065653.49
64 rdf:rest rdf:nil
65 N8f582ce9cd234b58a53ede15dd4cc3f0 schema:location Berlin, Heidelberg
66 schema:name Springer Berlin Heidelberg
67 rdf:type schema:Organisation
68 Na099df3c38cc4f31b43179587a922558 schema:familyName Kalviainen
69 schema:givenName Heikki
70 rdf:type schema:Person
71 Naa124c83647d4d41be162491e7a9e079 schema:familyName Kaarna
72 schema:givenName Arto
73 rdf:type schema:Person
74 Ncbac3a0666e74c2ca64dd5717641a086 schema:name readcube_id
75 schema:value 902a19d884dfeac16e2defd7f89d5581b8d61cd1295861eedf48d5febaa2485a
76 rdf:type schema:PropertyValue
77 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
78 schema:name Information and Computing Sciences
79 rdf:type schema:DefinedTerm
80 anzsrc-for:0806 schema:inDefinedTermSet anzsrc-for:
81 schema:name Information Systems
82 rdf:type schema:DefinedTerm
83 sg:person.012033065653.49 schema:affiliation https://www.grid.ac/institutes/grid.410413.3
84 schema:familyName Pinz
85 schema:givenName Axel
86 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012033065653.49
87 rdf:type schema:Person
88 sg:person.013624034621.75 schema:affiliation https://www.grid.ac/institutes/grid.410413.3
89 schema:familyName Opelt
90 schema:givenName Andreas
91 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013624034621.75
92 rdf:type schema:Person
93 sg:pub.10.1007/3-540-47969-4_9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046596731
94 https://doi.org/10.1007/3-540-47969-4_9
95 rdf:type schema:CreativeWork
96 sg:pub.10.1007/978-3-540-24670-1_19 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003570178
97 https://doi.org/10.1007/978-3-540-24670-1_19
98 rdf:type schema:CreativeWork
99 sg:pub.10.1007/978-3-540-24671-8_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046580260
100 https://doi.org/10.1007/978-3-540-24671-8_6
101 rdf:type schema:CreativeWork
102 sg:pub.10.1007/978-3-540-28649-3_18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040710754
103 https://doi.org/10.1007/978-3-540-28649-3_18
104 rdf:type schema:CreativeWork
105 sg:pub.10.1007/bfb0015574 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039472253
106 https://doi.org/10.1007/bfb0015574
107 rdf:type schema:CreativeWork
108 https://doi.org/10.1006/jcss.1997.1504 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004338842
109 rdf:type schema:CreativeWork
110 https://doi.org/10.1109/34.1000236 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061155588
111 rdf:type schema:CreativeWork
112 https://doi.org/10.1109/cvpr.2004.1315241 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094870330
113 rdf:type schema:CreativeWork
114 https://doi.org/10.1109/iccv.1999.790410 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095766209
115 rdf:type schema:CreativeWork
116 https://doi.org/10.1109/iccv.2001.937561 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095654754
117 rdf:type schema:CreativeWork
118 https://doi.org/10.1109/icpr.2004.1334464 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095551955
119 rdf:type schema:CreativeWork
120 https://doi.org/10.1109/tpami.2004.108 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742623
121 rdf:type schema:CreativeWork
122 https://doi.org/10.5244/c.18.98 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099382684
123 rdf:type schema:CreativeWork
124 https://www.grid.ac/institutes/grid.410413.3 schema:alternateName Graz University of Technology
125 schema:name Institute of Electrical Measurement and Measurement Signal Processing, Graz University of Technology, Austria
126 rdf:type schema:Organization
 




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


...