Image Tag Completion by Noisy Matrix Recovery View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2014

AUTHORS

Zheyun Feng , Songhe Feng , Rong Jin , Anil K. Jain

ABSTRACT

It is now generally recognized that user-provided image tags are incomplete and noisy. In this study, we focus on the problem of tag completion that aims to simultaneously enrich the missing tags and remove noisy tags. The novel component of the proposed framework is a noisy matrix recovery algorithm. It assumes that the observed tags are independently sampled from an unknown tag matrix and our goal is to recover the tag matrix based on the sampled tags. We show theoretically that the proposed noisy tag matrix recovery algorithm is able to simultaneously recover the missing tags and de-emphasize the noisy tags even with a limited number of observations. In addition, a graph Laplacian based component is introduced to combine the noisy matrix recovery component with visual features. Our empirical study with multiple benchmark datasets for image tagging shows that the proposed algorithm outperforms state-of-the-art approaches in terms of both effectiveness and efficiency when handling missing and noisy tags. More... »

PAGES

424-438

Book

TITLE

Computer Vision – ECCV 2014

ISBN

978-3-319-10583-3
978-3-319-10584-0

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-10584-0_28

DOI

http://dx.doi.org/10.1007/978-3-319-10584-0_28

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1046898920


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": "Michigan State University, USA", 
          "id": "http://www.grid.ac/institutes/grid.17088.36", 
          "name": [
            "Michigan State University, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Feng", 
        "givenName": "Zheyun", 
        "id": "sg:person.010364540153.75", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010364540153.75"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Beijing Jiaotong University, China", 
          "id": "http://www.grid.ac/institutes/grid.181531.f", 
          "name": [
            "Beijing Jiaotong University, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Feng", 
        "givenName": "Songhe", 
        "id": "sg:person.07666300667.45", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07666300667.45"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Michigan State University, USA", 
          "id": "http://www.grid.ac/institutes/grid.17088.36", 
          "name": [
            "Michigan State University, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jin", 
        "givenName": "Rong", 
        "id": "sg:person.01274430471.12", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01274430471.12"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Michigan State University, USA", 
          "id": "http://www.grid.ac/institutes/grid.17088.36", 
          "name": [
            "Michigan State University, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jain", 
        "givenName": "Anil K.", 
        "id": "sg:person.01031110710.30", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01031110710.30"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2014", 
    "datePublishedReg": "2014-01-01", 
    "description": "It is now generally recognized that user-provided image tags are incomplete and noisy. In this study, we focus on the problem of tag completion that aims to simultaneously enrich the missing tags and remove noisy tags. The novel component of the proposed framework is a noisy matrix recovery algorithm. It assumes that the observed tags are independently sampled from an unknown tag matrix and our goal is to recover the tag matrix based on the sampled tags. We show theoretically that the proposed noisy tag matrix recovery algorithm is able to simultaneously recover the missing tags and de-emphasize the noisy tags even with a limited number of observations. In addition, a graph Laplacian based component is introduced to combine the noisy matrix recovery component with visual features. Our empirical study with multiple benchmark datasets for image tagging shows that the proposed algorithm outperforms state-of-the-art approaches in terms of both effectiveness and efficiency when handling missing and noisy tags.", 
    "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.10.1007/978-3-319-10584-0_28", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-10583-3", 
        "978-3-319-10584-0"
      ], 
      "name": "Computer Vision \u2013 ECCV 2014", 
      "type": "Book"
    }, 
    "keywords": [
      "completion", 
      "study", 
      "limited number", 
      "recovery component", 
      "recovery", 
      "novel component", 
      "components", 
      "addition", 
      "number", 
      "effectiveness", 
      "features", 
      "goal", 
      "observations", 
      "tags", 
      "approach", 
      "tag matrix", 
      "state", 
      "visual features", 
      "terms", 
      "show", 
      "problem", 
      "matrix", 
      "dataset", 
      "noisy tags", 
      "tag completion", 
      "recovery algorithm", 
      "empirical study", 
      "multiple benchmark datasets", 
      "efficiency", 
      "Image Tag Completion", 
      "image tags", 
      "framework", 
      "observed tags", 
      "benchmark datasets", 
      "art approaches", 
      "algorithm", 
      "graph Laplacian", 
      "matrix recovery", 
      "Laplacian"
    ], 
    "name": "Image Tag Completion by Noisy Matrix Recovery", 
    "pagination": "424-438", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1046898920"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-10584-0_28"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-10584-0_28", 
      "https://app.dimensions.ai/details/publication/pub.1046898920"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-11-24T21:14", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221124/entities/gbq_results/chapter/chapter_263.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-10584-0_28"
  }
]
 

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.10.1007/978-3-319-10584-0_28'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-10584-0_28'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-10584-0_28'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-10584-0_28'


 

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

137 TRIPLES      22 PREDICATES      64 URIs      57 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-10584-0_28 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N07e6cd46a3764705815ba369f1cfe1c3
4 schema:datePublished 2014
5 schema:datePublishedReg 2014-01-01
6 schema:description It is now generally recognized that user-provided image tags are incomplete and noisy. In this study, we focus on the problem of tag completion that aims to simultaneously enrich the missing tags and remove noisy tags. The novel component of the proposed framework is a noisy matrix recovery algorithm. It assumes that the observed tags are independently sampled from an unknown tag matrix and our goal is to recover the tag matrix based on the sampled tags. We show theoretically that the proposed noisy tag matrix recovery algorithm is able to simultaneously recover the missing tags and de-emphasize the noisy tags even with a limited number of observations. In addition, a graph Laplacian based component is introduced to combine the noisy matrix recovery component with visual features. Our empirical study with multiple benchmark datasets for image tagging shows that the proposed algorithm outperforms state-of-the-art approaches in terms of both effectiveness and efficiency when handling missing and noisy tags.
7 schema:editor N069c0cc9a6174f338344e3bafbc3cdf3
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N9587a4bae81f411cbcaa4b7b2a642cac
11 schema:keywords Image Tag Completion
12 Laplacian
13 addition
14 algorithm
15 approach
16 art approaches
17 benchmark datasets
18 completion
19 components
20 dataset
21 effectiveness
22 efficiency
23 empirical study
24 features
25 framework
26 goal
27 graph Laplacian
28 image tags
29 limited number
30 matrix
31 matrix recovery
32 multiple benchmark datasets
33 noisy tags
34 novel component
35 number
36 observations
37 observed tags
38 problem
39 recovery
40 recovery algorithm
41 recovery component
42 show
43 state
44 study
45 tag completion
46 tag matrix
47 tags
48 terms
49 visual features
50 schema:name Image Tag Completion by Noisy Matrix Recovery
51 schema:pagination 424-438
52 schema:productId Nf494e61ee580412b9afa785a53d328c1
53 Nf78e833cc898404fbafd3debb0da5fae
54 schema:publisher Nbe4f4784b6ac4bc38968aef56376c177
55 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046898920
56 https://doi.org/10.1007/978-3-319-10584-0_28
57 schema:sdDatePublished 2022-11-24T21:14
58 schema:sdLicense https://scigraph.springernature.com/explorer/license/
59 schema:sdPublisher N84b27cf992104d4186cde1e12393f073
60 schema:url https://doi.org/10.1007/978-3-319-10584-0_28
61 sgo:license sg:explorer/license/
62 sgo:sdDataset chapters
63 rdf:type schema:Chapter
64 N069c0cc9a6174f338344e3bafbc3cdf3 rdf:first Nfb516e1b91f143a396a4b3156331f2ca
65 rdf:rest N868e2240a9e94916ae20bbf84c1877dc
66 N06d423846cfc489e8a4b9ec63ec78d20 schema:familyName Schiele
67 schema:givenName Bernt
68 rdf:type schema:Person
69 N07e6cd46a3764705815ba369f1cfe1c3 rdf:first sg:person.010364540153.75
70 rdf:rest N7f5dd48e59fd4e3a8970b462d5d42138
71 N3b1975102f7645b9b250e1c65ece5df6 rdf:first sg:person.01031110710.30
72 rdf:rest rdf:nil
73 N42947c6a1c7c4c6e8af970f1f59673ae schema:familyName Tuytelaars
74 schema:givenName Tinne
75 rdf:type schema:Person
76 N7a48ba0b3966477b8ef161ea888c85fd schema:familyName Pajdla
77 schema:givenName Tomas
78 rdf:type schema:Person
79 N7f5dd48e59fd4e3a8970b462d5d42138 rdf:first sg:person.07666300667.45
80 rdf:rest Nc70d6e508e0c42549449fc884fb20d0e
81 N84b27cf992104d4186cde1e12393f073 schema:name Springer Nature - SN SciGraph project
82 rdf:type schema:Organization
83 N868e2240a9e94916ae20bbf84c1877dc rdf:first N7a48ba0b3966477b8ef161ea888c85fd
84 rdf:rest Na5daf01e7d1148a88032171435edb34e
85 N9587a4bae81f411cbcaa4b7b2a642cac schema:isbn 978-3-319-10583-3
86 978-3-319-10584-0
87 schema:name Computer Vision – ECCV 2014
88 rdf:type schema:Book
89 Na5daf01e7d1148a88032171435edb34e rdf:first N06d423846cfc489e8a4b9ec63ec78d20
90 rdf:rest Nc53594db2e3a4c70b4fef0578af0825b
91 Nbe4f4784b6ac4bc38968aef56376c177 schema:name Springer Nature
92 rdf:type schema:Organisation
93 Nc53594db2e3a4c70b4fef0578af0825b rdf:first N42947c6a1c7c4c6e8af970f1f59673ae
94 rdf:rest rdf:nil
95 Nc70d6e508e0c42549449fc884fb20d0e rdf:first sg:person.01274430471.12
96 rdf:rest N3b1975102f7645b9b250e1c65ece5df6
97 Nf494e61ee580412b9afa785a53d328c1 schema:name dimensions_id
98 schema:value pub.1046898920
99 rdf:type schema:PropertyValue
100 Nf78e833cc898404fbafd3debb0da5fae schema:name doi
101 schema:value 10.1007/978-3-319-10584-0_28
102 rdf:type schema:PropertyValue
103 Nfb516e1b91f143a396a4b3156331f2ca schema:familyName Fleet
104 schema:givenName David
105 rdf:type schema:Person
106 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
107 schema:name Information and Computing Sciences
108 rdf:type schema:DefinedTerm
109 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
110 schema:name Artificial Intelligence and Image Processing
111 rdf:type schema:DefinedTerm
112 sg:person.01031110710.30 schema:affiliation grid-institutes:grid.17088.36
113 schema:familyName Jain
114 schema:givenName Anil K.
115 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01031110710.30
116 rdf:type schema:Person
117 sg:person.010364540153.75 schema:affiliation grid-institutes:grid.17088.36
118 schema:familyName Feng
119 schema:givenName Zheyun
120 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010364540153.75
121 rdf:type schema:Person
122 sg:person.01274430471.12 schema:affiliation grid-institutes:grid.17088.36
123 schema:familyName Jin
124 schema:givenName Rong
125 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01274430471.12
126 rdf:type schema:Person
127 sg:person.07666300667.45 schema:affiliation grid-institutes:grid.181531.f
128 schema:familyName Feng
129 schema:givenName Songhe
130 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07666300667.45
131 rdf:type schema:Person
132 grid-institutes:grid.17088.36 schema:alternateName Michigan State University, USA
133 schema:name Michigan State University, USA
134 rdf:type schema:Organization
135 grid-institutes:grid.181531.f schema:alternateName Beijing Jiaotong University, China
136 schema:name Beijing Jiaotong University, China
137 rdf:type schema:Organization
 




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


...