Co-transduction for Shape Retrieval View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2010

AUTHORS

Xiang Bai , Bo Wang , Xinggang Wang , Wenyu Liu , Zhuowen Tu

ABSTRACT

In this paper, we propose a new shape/object retrieval algorithm, co-transduction. The performance of a retrieval system is critically decided by the accuracy of adopted similarity measures (distances or metrics). Different types of measures may focus on different aspects of the objects: e.g. measures computed based on contours and skeletons are often complementary to each other. Our goal is to develop an algorithm to fuse different similarity measures for robust shape retrieval through a semi-supervised learning framework. We name our method co-transduction which is inspired by the co-training algorithm [1]. Given two similarity measures and a query shape, the algorithm iteratively retrieves the most similar shapes using one measure and assigns them to a pool for the other measure to do a re-ranking, and vice-versa. Using co-transduction, we achieved a significantly improved result of 97.72% on the MPEG-7 dataset [2] over the state-of-the-art performances (91% in [3], 93.4% in [4]). Our algorithm is general and it works directly on any given similarity measures/metrics; it is not limited to object shape retrieval and can be applied to other tasks for ranking/retrieval. More... »

PAGES

328-341

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-15558-1_24

DOI

http://dx.doi.org/10.1007/978-3-642-15558-1_24

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1014976528


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/2008/17", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology and Cognitive Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1701", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China", 
          "id": "http://www.grid.ac/institutes/grid.33199.31", 
          "name": [
            "Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bai", 
        "givenName": "Xiang", 
        "id": "sg:person.0757422057.71", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0757422057.71"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China", 
          "id": "http://www.grid.ac/institutes/grid.33199.31", 
          "name": [
            "Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Bo", 
        "id": "sg:person.011762327072.22", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011762327072.22"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China", 
          "id": "http://www.grid.ac/institutes/grid.33199.31", 
          "name": [
            "Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Xinggang", 
        "id": "sg:person.01330457264.55", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01330457264.55"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China", 
          "id": "http://www.grid.ac/institutes/grid.33199.31", 
          "name": [
            "Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Liu", 
        "givenName": "Wenyu", 
        "id": "sg:person.016514632622.24", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016514632622.24"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Lab of Neuro Imaging, University of California, Los Angeles", 
          "id": "http://www.grid.ac/institutes/grid.19006.3e", 
          "name": [
            "Lab of Neuro Imaging, University of California, Los Angeles"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tu", 
        "givenName": "Zhuowen", 
        "id": "sg:person.0714050112.48", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0714050112.48"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2010", 
    "datePublishedReg": "2010-01-01", 
    "description": "In this paper, we propose a new shape/object retrieval algorithm, co-transduction. The performance of a retrieval system is critically decided by the accuracy of adopted similarity measures (distances or metrics). Different types of measures may focus on different aspects of the objects: e.g. measures computed based on contours and skeletons are often complementary to each other. Our goal is to develop an algorithm to fuse different similarity measures for robust shape retrieval through a semi-supervised learning framework. We name our method co-transduction which is inspired by the co-training algorithm [1]. Given two similarity measures and a query shape, the algorithm iteratively retrieves the most similar shapes using one measure and assigns them to a pool for the other measure to do a re-ranking, and vice-versa. Using co-transduction, we achieved a significantly improved result of 97.72% on the MPEG-7 dataset [2] over the state-of-the-art performances (91% in [3], 93.4% in [4]). Our algorithm is general and it works directly on any given similarity measures/metrics; it is not limited to object shape retrieval and can be applied to other tasks for ranking/retrieval.", 
    "editor": [
      {
        "familyName": "Daniilidis", 
        "givenName": "Kostas", 
        "type": "Person"
      }, 
      {
        "familyName": "Maragos", 
        "givenName": "Petros", 
        "type": "Person"
      }, 
      {
        "familyName": "Paragios", 
        "givenName": "Nikos", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-15558-1_24", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-642-15557-4", 
        "978-3-642-15558-1"
      ], 
      "name": "Computer Vision \u2013 ECCV 2010", 
      "type": "Book"
    }, 
    "keywords": [
      "co-training algorithm", 
      "measures/metrics", 
      "art performance", 
      "different aspects", 
      "retrieval", 
      "learning framework", 
      "measures", 
      "shape retrieval", 
      "task", 
      "performance", 
      "similarity measure", 
      "semi-supervised learning framework", 
      "query shape", 
      "MPEG-7 dataset", 
      "objects", 
      "different types", 
      "aspects", 
      "retrieval system", 
      "goal", 
      "vice", 
      "framework", 
      "similar shape", 
      "contours", 
      "different similarity measures", 
      "accuracy", 
      "results", 
      "datasets", 
      "types", 
      "shape", 
      "state", 
      "metrics", 
      "paper", 
      "system", 
      "algorithm", 
      "method", 
      "retrieval algorithm", 
      "pool", 
      "robust shape retrieval", 
      "skeleton", 
      "new shape/object retrieval algorithm", 
      "shape/object retrieval algorithm", 
      "object retrieval algorithm", 
      "similarity measures/metrics"
    ], 
    "name": "Co-transduction for Shape Retrieval", 
    "pagination": "328-341", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1014976528"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-15558-1_24"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-15558-1_24", 
      "https://app.dimensions.ai/details/publication/pub.1014976528"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-12-01T19:55", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211201/entities/gbq_results/chapter/chapter_109.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-642-15558-1_24"
  }
]
 

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.10.1007/978-3-642-15558-1_24'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15558-1_24'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15558-1_24'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15558-1_24'


 

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

144 TRIPLES      23 PREDICATES      69 URIs      62 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-15558-1_24 schema:about anzsrc-for:17
2 anzsrc-for:1701
3 schema:author N7c01f6ed4ac94133bffcf14a13e7f943
4 schema:datePublished 2010
5 schema:datePublishedReg 2010-01-01
6 schema:description In this paper, we propose a new shape/object retrieval algorithm, co-transduction. The performance of a retrieval system is critically decided by the accuracy of adopted similarity measures (distances or metrics). Different types of measures may focus on different aspects of the objects: e.g. measures computed based on contours and skeletons are often complementary to each other. Our goal is to develop an algorithm to fuse different similarity measures for robust shape retrieval through a semi-supervised learning framework. We name our method co-transduction which is inspired by the co-training algorithm [1]. Given two similarity measures and a query shape, the algorithm iteratively retrieves the most similar shapes using one measure and assigns them to a pool for the other measure to do a re-ranking, and vice-versa. Using co-transduction, we achieved a significantly improved result of 97.72% on the MPEG-7 dataset [2] over the state-of-the-art performances (91% in [3], 93.4% in [4]). Our algorithm is general and it works directly on any given similarity measures/metrics; it is not limited to object shape retrieval and can be applied to other tasks for ranking/retrieval.
7 schema:editor Necac404d4adf462688de70184cf24f0b
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf N6a5ef1e8868f4ef8b8f22304d4100aa2
12 schema:keywords MPEG-7 dataset
13 accuracy
14 algorithm
15 art performance
16 aspects
17 co-training algorithm
18 contours
19 datasets
20 different aspects
21 different similarity measures
22 different types
23 framework
24 goal
25 learning framework
26 measures
27 measures/metrics
28 method
29 metrics
30 new shape/object retrieval algorithm
31 object retrieval algorithm
32 objects
33 paper
34 performance
35 pool
36 query shape
37 results
38 retrieval
39 retrieval algorithm
40 retrieval system
41 robust shape retrieval
42 semi-supervised learning framework
43 shape
44 shape retrieval
45 shape/object retrieval algorithm
46 similar shape
47 similarity measure
48 similarity measures/metrics
49 skeleton
50 state
51 system
52 task
53 types
54 vice
55 schema:name Co-transduction for Shape Retrieval
56 schema:pagination 328-341
57 schema:productId Nbe931923a1bf4fe2af95766457a04ec2
58 Ndc42ec677de44ad0ae86da75d65aef4a
59 schema:publisher Nf62947442a004765b6eb6a43ffb8783e
60 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014976528
61 https://doi.org/10.1007/978-3-642-15558-1_24
62 schema:sdDatePublished 2021-12-01T19:55
63 schema:sdLicense https://scigraph.springernature.com/explorer/license/
64 schema:sdPublisher N5813520314744ca9a5dffcdb37a57d7c
65 schema:url https://doi.org/10.1007/978-3-642-15558-1_24
66 sgo:license sg:explorer/license/
67 sgo:sdDataset chapters
68 rdf:type schema:Chapter
69 N131f32481ef14d7ba59b6d2e96961fa6 rdf:first sg:person.0714050112.48
70 rdf:rest rdf:nil
71 N44eafd3a37984cc08dc1600abbc3b99b schema:familyName Paragios
72 schema:givenName Nikos
73 rdf:type schema:Person
74 N45203db428244bddb58fcafbb739fabf rdf:first sg:person.011762327072.22
75 rdf:rest Nd8e728aecff6440fa244761634209cc4
76 N5813520314744ca9a5dffcdb37a57d7c schema:name Springer Nature - SN SciGraph project
77 rdf:type schema:Organization
78 N5a5413c25117412e8df09e71c9674ca9 schema:familyName Maragos
79 schema:givenName Petros
80 rdf:type schema:Person
81 N6a5ef1e8868f4ef8b8f22304d4100aa2 schema:isbn 978-3-642-15557-4
82 978-3-642-15558-1
83 schema:name Computer Vision – ECCV 2010
84 rdf:type schema:Book
85 N7c01f6ed4ac94133bffcf14a13e7f943 rdf:first sg:person.0757422057.71
86 rdf:rest N45203db428244bddb58fcafbb739fabf
87 N7c2d18e3e70c416b9372d48b0fd27529 schema:familyName Daniilidis
88 schema:givenName Kostas
89 rdf:type schema:Person
90 N970e4e9b0af644a3902d35474115badc rdf:first N5a5413c25117412e8df09e71c9674ca9
91 rdf:rest Nf23a0bb06c8c41e48c386a0038cd2071
92 Nb3c0bb16eee64d20ac1f798e37635068 rdf:first sg:person.016514632622.24
93 rdf:rest N131f32481ef14d7ba59b6d2e96961fa6
94 Nbe931923a1bf4fe2af95766457a04ec2 schema:name doi
95 schema:value 10.1007/978-3-642-15558-1_24
96 rdf:type schema:PropertyValue
97 Nd8e728aecff6440fa244761634209cc4 rdf:first sg:person.01330457264.55
98 rdf:rest Nb3c0bb16eee64d20ac1f798e37635068
99 Ndc42ec677de44ad0ae86da75d65aef4a schema:name dimensions_id
100 schema:value pub.1014976528
101 rdf:type schema:PropertyValue
102 Necac404d4adf462688de70184cf24f0b rdf:first N7c2d18e3e70c416b9372d48b0fd27529
103 rdf:rest N970e4e9b0af644a3902d35474115badc
104 Nf23a0bb06c8c41e48c386a0038cd2071 rdf:first N44eafd3a37984cc08dc1600abbc3b99b
105 rdf:rest rdf:nil
106 Nf62947442a004765b6eb6a43ffb8783e schema:name Springer Nature
107 rdf:type schema:Organisation
108 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
109 schema:name Psychology and Cognitive Sciences
110 rdf:type schema:DefinedTerm
111 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
112 schema:name Psychology
113 rdf:type schema:DefinedTerm
114 sg:person.011762327072.22 schema:affiliation grid-institutes:grid.33199.31
115 schema:familyName Wang
116 schema:givenName Bo
117 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011762327072.22
118 rdf:type schema:Person
119 sg:person.01330457264.55 schema:affiliation grid-institutes:grid.33199.31
120 schema:familyName Wang
121 schema:givenName Xinggang
122 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01330457264.55
123 rdf:type schema:Person
124 sg:person.016514632622.24 schema:affiliation grid-institutes:grid.33199.31
125 schema:familyName Liu
126 schema:givenName Wenyu
127 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016514632622.24
128 rdf:type schema:Person
129 sg:person.0714050112.48 schema:affiliation grid-institutes:grid.19006.3e
130 schema:familyName Tu
131 schema:givenName Zhuowen
132 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0714050112.48
133 rdf:type schema:Person
134 sg:person.0757422057.71 schema:affiliation grid-institutes:grid.33199.31
135 schema:familyName Bai
136 schema:givenName Xiang
137 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0757422057.71
138 rdf:type schema:Person
139 grid-institutes:grid.19006.3e schema:alternateName Lab of Neuro Imaging, University of California, Los Angeles
140 schema:name Lab of Neuro Imaging, University of California, Los Angeles
141 rdf:type schema:Organization
142 grid-institutes:grid.33199.31 schema:alternateName Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China
143 schema:name Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China
144 rdf:type schema:Organization
 




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


...