Multi-scale Orderless Pooling of Deep Convolutional Activation Features View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2014

AUTHORS

Yunchao Gong , Liwei Wang , Ruiqi Guo , Svetlana Lazebnik

ABSTRACT

Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustness for classification and matching of highly variable scenes. To improve the invariance of CNN activations without degrading their discriminative power, this paper presents a simple but effective scheme called multi-scale orderless pooling (MOP-CNN). This scheme extracts CNN activations for local patches at multiple scale levels, performs orderless VLAD pooling of these activations at each level separately, and concatenates the result. The resulting MOP-CNN representation can be used as a generic feature for either supervised or unsupervised recognition tasks, from image classification to instance-level retrieval; it consistently outperforms global CNN activations without requiring any joint training of prediction layers for a particular target dataset. In absolute terms, it achieves state-of-the-art results on the challenging SUN397 and MIT Indoor Scenes classification datasets, and competitive results on ILSVRC2012/2013 classification and INRIA Holidays retrieval datasets. More... »

PAGES

392-407

References to SciGraph publications

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_26

DOI

http://dx.doi.org/10.1007/978-3-319-10584-0_26

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1032984348


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/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "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": "University of North Carolina System", 
          "id": "https://www.grid.ac/institutes/grid.410711.2", 
          "name": [
            "University of North Carolina, Chapel Hill, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Gong", 
        "givenName": "Yunchao", 
        "id": "sg:person.0664116115.60", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0664116115.60"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Illinois at Urbana Champaign", 
          "id": "https://www.grid.ac/institutes/grid.35403.31", 
          "name": [
            "University of Illinois, Urbana-Champaign, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Liwei", 
        "id": "sg:person.010456203413.99", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010456203413.99"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Illinois at Urbana Champaign", 
          "id": "https://www.grid.ac/institutes/grid.35403.31", 
          "name": [
            "University of Illinois, Urbana-Champaign, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Guo", 
        "givenName": "Ruiqi", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Illinois at Urbana Champaign", 
          "id": "https://www.grid.ac/institutes/grid.35403.31", 
          "name": [
            "University of Illinois, Urbana-Champaign, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lazebnik", 
        "givenName": "Svetlana", 
        "id": "sg:person.01270671277.61", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01270671277.61"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1145/1553374.1553453", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004476131"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11263-013-0636-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1012698338", 
          "https://doi.org/10.1007/s11263-013-0636-x"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-33709-3_6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1023026646", 
          "https://doi.org/10.1007/978-3-642-33709-3_6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-88682-2_24", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045157785", 
          "https://doi.org/10.1007/978-3-540-88682-2_24"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-88682-2_24", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045157785", 
          "https://doi.org/10.1007/978-3-540-88682-2_24"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-15561-1_11", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045344996", 
          "https://doi.org/10.1007/978-3-642-15561-1_11"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-15561-1_11", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045344996", 
          "https://doi.org/10.1007/978-3-642-15561-1_11"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/b:visi.0000029664.99615.94", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052687286", 
          "https://doi.org/10.1023/b:visi.0000029664.99615.94"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-33709-3_55", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053473906", 
          "https://doi.org/10.1007/978-3-642-33709-3_55"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2013.146", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061744460"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2013.258", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093328144"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2013.124", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093568253"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2013.124", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093568253"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2010.5539970", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093603006"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvprw.2014.131", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093645378"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2014.222", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094012327"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2006.68", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094512911"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2011.6126383", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094624803"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2014.81", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094727707"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2013.177", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094888549"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2003.1238663", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094978467"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2013.6639343", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095400300"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2010.5540009", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095484171"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2010.5540018", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095506116"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2009.5206537", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095519187"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2007.383266", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095559903"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2005.239", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095611654"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2009.5206848", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095689025"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2010.5540039", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095738093"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2014", 
    "datePublishedReg": "2014-01-01", 
    "description": "Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustness for classification and matching of highly variable scenes. To improve the invariance of CNN activations without degrading their discriminative power, this paper presents a simple but effective scheme called multi-scale orderless pooling (MOP-CNN). This scheme extracts CNN activations for local patches at multiple scale levels, performs orderless VLAD pooling of these activations at each level separately, and concatenates the result. The resulting MOP-CNN representation can be used as a generic feature for either supervised or unsupervised recognition tasks, from image classification to instance-level retrieval; it consistently outperforms global CNN activations without requiring any joint training of prediction layers for a particular target dataset. In absolute terms, it achieves state-of-the-art results on the challenging SUN397 and MIT Indoor Scenes classification datasets, and competitive results on ILSVRC2012/2013 classification and INRIA Holidays retrieval datasets.", 
    "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_26", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-10583-3", 
        "978-3-319-10584-0"
      ], 
      "name": "Computer Vision \u2013 ECCV 2014", 
      "type": "Book"
    }, 
    "name": "Multi-scale Orderless Pooling of Deep Convolutional Activation Features", 
    "pagination": "392-407", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-10584-0_26"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "9d21fb63ff3806ee28ed2c3316669c03c82d7eb0fa06960a209060f0daa9f5cb"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1032984348"
        ]
      }
    ], 
    "publisher": {
      "location": "Cham", 
      "name": "Springer International Publishing", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-10584-0_26", 
      "https://app.dimensions.ai/details/publication/pub.1032984348"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T00:49", 
    "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/v90/0000000001_0000000264/records_8700_00000263.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/978-3-319-10584-0_26"
  }
]
 

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_26'

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_26'

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_26'

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_26'


 

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

187 TRIPLES      23 PREDICATES      53 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-10584-0_26 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nd29730041e6d4e4db4af8db2be050aa9
4 schema:citation sg:pub.10.1007/978-3-540-88682-2_24
5 sg:pub.10.1007/978-3-642-15561-1_11
6 sg:pub.10.1007/978-3-642-33709-3_55
7 sg:pub.10.1007/978-3-642-33709-3_6
8 sg:pub.10.1007/s11263-013-0636-x
9 sg:pub.10.1023/b:visi.0000029664.99615.94
10 https://doi.org/10.1109/cvpr.2006.68
11 https://doi.org/10.1109/cvpr.2007.383266
12 https://doi.org/10.1109/cvpr.2009.5206537
13 https://doi.org/10.1109/cvpr.2009.5206848
14 https://doi.org/10.1109/cvpr.2010.5539970
15 https://doi.org/10.1109/cvpr.2010.5540009
16 https://doi.org/10.1109/cvpr.2010.5540018
17 https://doi.org/10.1109/cvpr.2010.5540039
18 https://doi.org/10.1109/cvpr.2013.124
19 https://doi.org/10.1109/cvpr.2014.222
20 https://doi.org/10.1109/cvpr.2014.81
21 https://doi.org/10.1109/cvprw.2014.131
22 https://doi.org/10.1109/icassp.2013.6639343
23 https://doi.org/10.1109/iccv.2003.1238663
24 https://doi.org/10.1109/iccv.2005.239
25 https://doi.org/10.1109/iccv.2011.6126383
26 https://doi.org/10.1109/iccv.2013.177
27 https://doi.org/10.1109/iccv.2013.258
28 https://doi.org/10.1109/tpami.2013.146
29 https://doi.org/10.1145/1553374.1553453
30 schema:datePublished 2014
31 schema:datePublishedReg 2014-01-01
32 schema:description Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustness for classification and matching of highly variable scenes. To improve the invariance of CNN activations without degrading their discriminative power, this paper presents a simple but effective scheme called multi-scale orderless pooling (MOP-CNN). This scheme extracts CNN activations for local patches at multiple scale levels, performs orderless VLAD pooling of these activations at each level separately, and concatenates the result. The resulting MOP-CNN representation can be used as a generic feature for either supervised or unsupervised recognition tasks, from image classification to instance-level retrieval; it consistently outperforms global CNN activations without requiring any joint training of prediction layers for a particular target dataset. In absolute terms, it achieves state-of-the-art results on the challenging SUN397 and MIT Indoor Scenes classification datasets, and competitive results on ILSVRC2012/2013 classification and INRIA Holidays retrieval datasets.
33 schema:editor N462f437629174d14b482490149809eb0
34 schema:genre chapter
35 schema:inLanguage en
36 schema:isAccessibleForFree true
37 schema:isPartOf N18e9e5d6ccd74030954aef788a56b175
38 schema:name Multi-scale Orderless Pooling of Deep Convolutional Activation Features
39 schema:pagination 392-407
40 schema:productId N093bc2f610214eb2b61dad32f3558c6d
41 N245c1e84060c4f0a9386d6cf9d71cbfb
42 N9d75431cece84510a91c70b07f911430
43 schema:publisher Nfc9ea35af4044b4d9174a92d7a520f0a
44 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032984348
45 https://doi.org/10.1007/978-3-319-10584-0_26
46 schema:sdDatePublished 2019-04-16T00:49
47 schema:sdLicense https://scigraph.springernature.com/explorer/license/
48 schema:sdPublisher N53135f63a3d9404d9dc68da4bfada053
49 schema:url http://link.springer.com/10.1007/978-3-319-10584-0_26
50 sgo:license sg:explorer/license/
51 sgo:sdDataset chapters
52 rdf:type schema:Chapter
53 N041629cc243b42ff830cf7e955ffb76a rdf:first sg:person.01270671277.61
54 rdf:rest rdf:nil
55 N093bc2f610214eb2b61dad32f3558c6d schema:name doi
56 schema:value 10.1007/978-3-319-10584-0_26
57 rdf:type schema:PropertyValue
58 N18e9e5d6ccd74030954aef788a56b175 schema:isbn 978-3-319-10583-3
59 978-3-319-10584-0
60 schema:name Computer Vision – ECCV 2014
61 rdf:type schema:Book
62 N245c1e84060c4f0a9386d6cf9d71cbfb schema:name dimensions_id
63 schema:value pub.1032984348
64 rdf:type schema:PropertyValue
65 N2ffa34fc7b17435f96315269fb1f4279 schema:familyName Fleet
66 schema:givenName David
67 rdf:type schema:Person
68 N462f437629174d14b482490149809eb0 rdf:first N2ffa34fc7b17435f96315269fb1f4279
69 rdf:rest N4be446f82b6f4eab8e931ea29b08fddb
70 N4be446f82b6f4eab8e931ea29b08fddb rdf:first Nd1001de259aa40a5bf7b65bea8174861
71 rdf:rest Nd02f342155e04147818b534501b61fbc
72 N53135f63a3d9404d9dc68da4bfada053 schema:name Springer Nature - SN SciGraph project
73 rdf:type schema:Organization
74 N6de224bc52c54289806ee6c6f8916036 rdf:first N97e8f3b2182f4dd59964130216f37560
75 rdf:rest N041629cc243b42ff830cf7e955ffb76a
76 N97e8f3b2182f4dd59964130216f37560 schema:affiliation https://www.grid.ac/institutes/grid.35403.31
77 schema:familyName Guo
78 schema:givenName Ruiqi
79 rdf:type schema:Person
80 N9d75431cece84510a91c70b07f911430 schema:name readcube_id
81 schema:value 9d21fb63ff3806ee28ed2c3316669c03c82d7eb0fa06960a209060f0daa9f5cb
82 rdf:type schema:PropertyValue
83 Nd02f342155e04147818b534501b61fbc rdf:first Nf978ab1af57342cdacd1fa9ef995d6ca
84 rdf:rest Nd6e20742151f47fa8b72ddd862450488
85 Nd1001de259aa40a5bf7b65bea8174861 schema:familyName Pajdla
86 schema:givenName Tomas
87 rdf:type schema:Person
88 Nd29730041e6d4e4db4af8db2be050aa9 rdf:first sg:person.0664116115.60
89 rdf:rest Nda06feee97474251bca6bea52065dc20
90 Nd6e20742151f47fa8b72ddd862450488 rdf:first Nf73b9fcfbc1f408b85b94dc807b9cec1
91 rdf:rest rdf:nil
92 Nda06feee97474251bca6bea52065dc20 rdf:first sg:person.010456203413.99
93 rdf:rest N6de224bc52c54289806ee6c6f8916036
94 Nf73b9fcfbc1f408b85b94dc807b9cec1 schema:familyName Tuytelaars
95 schema:givenName Tinne
96 rdf:type schema:Person
97 Nf978ab1af57342cdacd1fa9ef995d6ca schema:familyName Schiele
98 schema:givenName Bernt
99 rdf:type schema:Person
100 Nfc9ea35af4044b4d9174a92d7a520f0a schema:location Cham
101 schema:name Springer International Publishing
102 rdf:type schema:Organisation
103 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
104 schema:name Information and Computing Sciences
105 rdf:type schema:DefinedTerm
106 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
107 schema:name Artificial Intelligence and Image Processing
108 rdf:type schema:DefinedTerm
109 sg:person.010456203413.99 schema:affiliation https://www.grid.ac/institutes/grid.35403.31
110 schema:familyName Wang
111 schema:givenName Liwei
112 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010456203413.99
113 rdf:type schema:Person
114 sg:person.01270671277.61 schema:affiliation https://www.grid.ac/institutes/grid.35403.31
115 schema:familyName Lazebnik
116 schema:givenName Svetlana
117 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01270671277.61
118 rdf:type schema:Person
119 sg:person.0664116115.60 schema:affiliation https://www.grid.ac/institutes/grid.410711.2
120 schema:familyName Gong
121 schema:givenName Yunchao
122 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0664116115.60
123 rdf:type schema:Person
124 sg:pub.10.1007/978-3-540-88682-2_24 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045157785
125 https://doi.org/10.1007/978-3-540-88682-2_24
126 rdf:type schema:CreativeWork
127 sg:pub.10.1007/978-3-642-15561-1_11 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045344996
128 https://doi.org/10.1007/978-3-642-15561-1_11
129 rdf:type schema:CreativeWork
130 sg:pub.10.1007/978-3-642-33709-3_55 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053473906
131 https://doi.org/10.1007/978-3-642-33709-3_55
132 rdf:type schema:CreativeWork
133 sg:pub.10.1007/978-3-642-33709-3_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023026646
134 https://doi.org/10.1007/978-3-642-33709-3_6
135 rdf:type schema:CreativeWork
136 sg:pub.10.1007/s11263-013-0636-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1012698338
137 https://doi.org/10.1007/s11263-013-0636-x
138 rdf:type schema:CreativeWork
139 sg:pub.10.1023/b:visi.0000029664.99615.94 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052687286
140 https://doi.org/10.1023/b:visi.0000029664.99615.94
141 rdf:type schema:CreativeWork
142 https://doi.org/10.1109/cvpr.2006.68 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094512911
143 rdf:type schema:CreativeWork
144 https://doi.org/10.1109/cvpr.2007.383266 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095559903
145 rdf:type schema:CreativeWork
146 https://doi.org/10.1109/cvpr.2009.5206537 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095519187
147 rdf:type schema:CreativeWork
148 https://doi.org/10.1109/cvpr.2009.5206848 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095689025
149 rdf:type schema:CreativeWork
150 https://doi.org/10.1109/cvpr.2010.5539970 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093603006
151 rdf:type schema:CreativeWork
152 https://doi.org/10.1109/cvpr.2010.5540009 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095484171
153 rdf:type schema:CreativeWork
154 https://doi.org/10.1109/cvpr.2010.5540018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095506116
155 rdf:type schema:CreativeWork
156 https://doi.org/10.1109/cvpr.2010.5540039 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095738093
157 rdf:type schema:CreativeWork
158 https://doi.org/10.1109/cvpr.2013.124 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093568253
159 rdf:type schema:CreativeWork
160 https://doi.org/10.1109/cvpr.2014.222 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094012327
161 rdf:type schema:CreativeWork
162 https://doi.org/10.1109/cvpr.2014.81 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094727707
163 rdf:type schema:CreativeWork
164 https://doi.org/10.1109/cvprw.2014.131 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093645378
165 rdf:type schema:CreativeWork
166 https://doi.org/10.1109/icassp.2013.6639343 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095400300
167 rdf:type schema:CreativeWork
168 https://doi.org/10.1109/iccv.2003.1238663 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094978467
169 rdf:type schema:CreativeWork
170 https://doi.org/10.1109/iccv.2005.239 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095611654
171 rdf:type schema:CreativeWork
172 https://doi.org/10.1109/iccv.2011.6126383 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094624803
173 rdf:type schema:CreativeWork
174 https://doi.org/10.1109/iccv.2013.177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094888549
175 rdf:type schema:CreativeWork
176 https://doi.org/10.1109/iccv.2013.258 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093328144
177 rdf:type schema:CreativeWork
178 https://doi.org/10.1109/tpami.2013.146 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744460
179 rdf:type schema:CreativeWork
180 https://doi.org/10.1145/1553374.1553453 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004476131
181 rdf:type schema:CreativeWork
182 https://www.grid.ac/institutes/grid.35403.31 schema:alternateName University of Illinois at Urbana Champaign
183 schema:name University of Illinois, Urbana-Champaign, USA
184 rdf:type schema:Organization
185 https://www.grid.ac/institutes/grid.410711.2 schema:alternateName University of North Carolina System
186 schema:name University of North Carolina, Chapel Hill, USA
187 rdf:type schema:Organization
 




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


...