Select, Attend, and Transfer: Light, Learnable Skip Connections View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2019-10-10

AUTHORS

Saeid Asgari Taghanaki , Aicha Bentaieb , Anmol Sharma , S. Kevin Zhou , Yefeng Zheng , Bogdan Georgescu , Puneet Sharma , Zhoubing Xu , Dorin Comaniciu , Ghassan Hamarneh

ABSTRACT

Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures and reducing the risks for vanishing gradients. The skip connections equip encoder-decoder like networks with richer feature representations, but at the cost of higher memory usage, computation, and possibly resulting in transferring non-discriminative feature maps. In this paper, we focus on improving the skip connections used in segmentation networks. We propose light, learnable skip connections which learn to first select the most discriminative channels, and then aggregate the selected ones as single channel attending to the most discriminative regions of input. We evaluate the proposed method on 3 different 2D and volumetric datasets and demonstrate that the proposed skip connections can outperform the traditional heavy skip connections of 4 different models in terms of segmentation accuracy (2% Dice), memory usage (at least 50%), and the number of network parameters (up to 70%). More... »

PAGES

417-425

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-030-32692-0_48

DOI

http://dx.doi.org/10.1007/978-3-030-32692-0_48

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1121621807


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": "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Image Analysis Lab, School of Computing Science, Simon Fraser University, Burnaby, Canada", 
            "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Taghanaki", 
        "givenName": "Saeid Asgari", 
        "id": "sg:person.013754250667.08", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013754250667.08"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Image Analysis Lab, School of Computing Science, Simon Fraser University, Burnaby, Canada", 
          "id": "http://www.grid.ac/institutes/grid.61971.38", 
          "name": [
            "Medical Image Analysis Lab, School of Computing Science, Simon Fraser University, Burnaby, Canada"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bentaieb", 
        "givenName": "Aicha", 
        "id": "sg:person.012771740525.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012771740525.65"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Image Analysis Lab, School of Computing Science, Simon Fraser University, Burnaby, Canada", 
          "id": "http://www.grid.ac/institutes/grid.61971.38", 
          "name": [
            "Medical Image Analysis Lab, School of Computing Science, Simon Fraser University, Burnaby, Canada"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Sharma", 
        "givenName": "Anmol", 
        "id": "sg:person.07537734265.49", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07537734265.49"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhou", 
        "givenName": "S. Kevin", 
        "id": "sg:person.01372425362.30", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01372425362.30"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zheng", 
        "givenName": "Yefeng", 
        "id": "sg:person.0767211426.21", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0767211426.21"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Georgescu", 
        "givenName": "Bogdan", 
        "id": "sg:person.0703547214.37", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0703547214.37"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Sharma", 
        "givenName": "Puneet", 
        "id": "sg:person.01154725330.99", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01154725330.99"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Xu", 
        "givenName": "Zhoubing", 
        "id": "sg:person.013364364655.13", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013364364655.13"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Comaniciu", 
        "givenName": "Dorin", 
        "id": "sg:person.01066111014.77", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01066111014.77"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Medical Image Analysis Lab, School of Computing Science, Simon Fraser University, Burnaby, Canada", 
          "id": "http://www.grid.ac/institutes/grid.61971.38", 
          "name": [
            "Medical Image Analysis Lab, School of Computing Science, Simon Fraser University, Burnaby, Canada"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hamarneh", 
        "givenName": "Ghassan", 
        "id": "sg:person.0642774233.16", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0642774233.16"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2019-10-10", 
    "datePublishedReg": "2019-10-10", 
    "description": "Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures and reducing the risks for vanishing gradients. The skip connections equip encoder-decoder like networks with richer feature representations, but at the cost of higher memory usage, computation, and possibly resulting in transferring non-discriminative feature maps. In this paper, we focus on improving the skip connections used in segmentation networks. We propose light, learnable skip connections which learn to first select the most discriminative channels, and then aggregate the selected ones as single channel attending to the most discriminative regions of input. We evaluate the proposed method on 3 different 2D and volumetric datasets and demonstrate that the proposed skip connections can outperform the traditional heavy skip connections of 4 different models in terms of segmentation accuracy (2% Dice), memory usage (at least 50%), and the number of network parameters (up\u00a0to 70%).", 
    "editor": [
      {
        "familyName": "Suk", 
        "givenName": "Heung-Il", 
        "type": "Person"
      }, 
      {
        "familyName": "Liu", 
        "givenName": "Mingxia", 
        "type": "Person"
      }, 
      {
        "familyName": "Yan", 
        "givenName": "Pingkun", 
        "type": "Person"
      }, 
      {
        "familyName": "Lian", 
        "givenName": "Chunfeng", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-030-32692-0_48", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-030-32691-3", 
        "978-3-030-32692-0"
      ], 
      "name": "Machine Learning in Medical Imaging", 
      "type": "Book"
    }, 
    "keywords": [
      "skip connections", 
      "memory usage", 
      "deep network architecture", 
      "high memory usage", 
      "rich feature representations", 
      "deep network", 
      "segmentation network", 
      "feature representation", 
      "network architecture", 
      "feature maps", 
      "segmentation accuracy", 
      "classification performance", 
      "volumetric datasets", 
      "discriminative regions", 
      "network parameters", 
      "discriminative channels", 
      "network", 
      "usage", 
      "segmentation", 
      "architecture", 
      "dataset", 
      "single channel", 
      "computation", 
      "different models", 
      "representation", 
      "accuracy", 
      "connection", 
      "performance", 
      "input", 
      "cost", 
      "channels", 
      "maps", 
      "equip", 
      "training", 
      "model", 
      "method", 
      "one", 
      "terms", 
      "number", 
      "parameters", 
      "transfer", 
      "gradient", 
      "region", 
      "light", 
      "risk", 
      "paper"
    ], 
    "name": "Select, Attend, and Transfer: Light, Learnable Skip Connections", 
    "pagination": "417-425", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1121621807"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-030-32692-0_48"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-030-32692-0_48", 
      "https://app.dimensions.ai/details/publication/pub.1121621807"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-05-20T07:43", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220519/entities/gbq_results/chapter/chapter_226.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-030-32692-0_48"
  }
]
 

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.10.1007/978-3-030-32692-0_48'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-32692-0_48'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-32692-0_48'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-32692-0_48'


 

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

188 TRIPLES      23 PREDICATES      71 URIs      64 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-030-32692-0_48 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N2069b3eb54f94b74ae916c34de465e16
4 schema:datePublished 2019-10-10
5 schema:datePublishedReg 2019-10-10
6 schema:description Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures and reducing the risks for vanishing gradients. The skip connections equip encoder-decoder like networks with richer feature representations, but at the cost of higher memory usage, computation, and possibly resulting in transferring non-discriminative feature maps. In this paper, we focus on improving the skip connections used in segmentation networks. We propose light, learnable skip connections which learn to first select the most discriminative channels, and then aggregate the selected ones as single channel attending to the most discriminative regions of input. We evaluate the proposed method on 3 different 2D and volumetric datasets and demonstrate that the proposed skip connections can outperform the traditional heavy skip connections of 4 different models in terms of segmentation accuracy (2% Dice), memory usage (at least 50%), and the number of network parameters (up to 70%).
7 schema:editor N300881721d714cf7b13198c405d9fa91
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf N56a0973946634033bf208b1974d7f595
12 schema:keywords accuracy
13 architecture
14 channels
15 classification performance
16 computation
17 connection
18 cost
19 dataset
20 deep network
21 deep network architecture
22 different models
23 discriminative channels
24 discriminative regions
25 equip
26 feature maps
27 feature representation
28 gradient
29 high memory usage
30 input
31 light
32 maps
33 memory usage
34 method
35 model
36 network
37 network architecture
38 network parameters
39 number
40 one
41 paper
42 parameters
43 performance
44 region
45 representation
46 rich feature representations
47 risk
48 segmentation
49 segmentation accuracy
50 segmentation network
51 single channel
52 skip connections
53 terms
54 training
55 transfer
56 usage
57 volumetric datasets
58 schema:name Select, Attend, and Transfer: Light, Learnable Skip Connections
59 schema:pagination 417-425
60 schema:productId N2447e6577aa0405cbd6c6782d9b47158
61 N2c059f0dd498412e97cc3674588cb713
62 schema:publisher N4965b5aeaecb44359586e9c9b44d0b11
63 schema:sameAs https://app.dimensions.ai/details/publication/pub.1121621807
64 https://doi.org/10.1007/978-3-030-32692-0_48
65 schema:sdDatePublished 2022-05-20T07:43
66 schema:sdLicense https://scigraph.springernature.com/explorer/license/
67 schema:sdPublisher N543ba2034ae5430b98bee09eb87e0c7a
68 schema:url https://doi.org/10.1007/978-3-030-32692-0_48
69 sgo:license sg:explorer/license/
70 sgo:sdDataset chapters
71 rdf:type schema:Chapter
72 N018b3c1397f74498b18c496ba6a6abd1 rdf:first sg:person.013364364655.13
73 rdf:rest N528accf2cb1e4ab3804da7528ce17e31
74 N2069b3eb54f94b74ae916c34de465e16 rdf:first sg:person.013754250667.08
75 rdf:rest N43b0b5e7767b4186bceeaf031215a498
76 N2447e6577aa0405cbd6c6782d9b47158 schema:name doi
77 schema:value 10.1007/978-3-030-32692-0_48
78 rdf:type schema:PropertyValue
79 N2c059f0dd498412e97cc3674588cb713 schema:name dimensions_id
80 schema:value pub.1121621807
81 rdf:type schema:PropertyValue
82 N300881721d714cf7b13198c405d9fa91 rdf:first Ne2635c9171b84e7092e53cdc9cb8f381
83 rdf:rest Nabf1003f92504e058889969d544f0abe
84 N390d66ed32714fe2bbdd66f16f51c08d schema:familyName Liu
85 schema:givenName Mingxia
86 rdf:type schema:Person
87 N39fef20df4994ab2834c77292f20d003 rdf:first sg:person.0642774233.16
88 rdf:rest rdf:nil
89 N43b0b5e7767b4186bceeaf031215a498 rdf:first sg:person.012771740525.65
90 rdf:rest Nd45728d813b1421caabafdb248b6b9f4
91 N486861f4a8354ad7aa693a29201ef663 rdf:first sg:person.01372425362.30
92 rdf:rest N644cc9a4f285430db733e9c63a3870f0
93 N4965b5aeaecb44359586e9c9b44d0b11 schema:name Springer Nature
94 rdf:type schema:Organisation
95 N528accf2cb1e4ab3804da7528ce17e31 rdf:first sg:person.01066111014.77
96 rdf:rest N39fef20df4994ab2834c77292f20d003
97 N543ba2034ae5430b98bee09eb87e0c7a schema:name Springer Nature - SN SciGraph project
98 rdf:type schema:Organization
99 N56a0973946634033bf208b1974d7f595 schema:isbn 978-3-030-32691-3
100 978-3-030-32692-0
101 schema:name Machine Learning in Medical Imaging
102 rdf:type schema:Book
103 N56b9e9f055504db4a9ad42b78714e8fa rdf:first sg:person.0703547214.37
104 rdf:rest N79f86e4a543f4018a6d5b5eea8f4e8a5
105 N644cc9a4f285430db733e9c63a3870f0 rdf:first sg:person.0767211426.21
106 rdf:rest N56b9e9f055504db4a9ad42b78714e8fa
107 N6c16e2150237453987f797241c4a18ed rdf:first Nbbbf53bc98144281a9382a866d55562c
108 rdf:rest N7ce32337c26e4cc485d3f77fa6b9a38b
109 N79f86e4a543f4018a6d5b5eea8f4e8a5 rdf:first sg:person.01154725330.99
110 rdf:rest N018b3c1397f74498b18c496ba6a6abd1
111 N7ce32337c26e4cc485d3f77fa6b9a38b rdf:first Ncbb4b8d7088f46cf845dd086f3d5e133
112 rdf:rest rdf:nil
113 Nabf1003f92504e058889969d544f0abe rdf:first N390d66ed32714fe2bbdd66f16f51c08d
114 rdf:rest N6c16e2150237453987f797241c4a18ed
115 Nbbbf53bc98144281a9382a866d55562c schema:familyName Yan
116 schema:givenName Pingkun
117 rdf:type schema:Person
118 Ncbb4b8d7088f46cf845dd086f3d5e133 schema:familyName Lian
119 schema:givenName Chunfeng
120 rdf:type schema:Person
121 Nd45728d813b1421caabafdb248b6b9f4 rdf:first sg:person.07537734265.49
122 rdf:rest N486861f4a8354ad7aa693a29201ef663
123 Ne2635c9171b84e7092e53cdc9cb8f381 schema:familyName Suk
124 schema:givenName Heung-Il
125 rdf:type schema:Person
126 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
127 schema:name Information and Computing Sciences
128 rdf:type schema:DefinedTerm
129 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
130 schema:name Artificial Intelligence and Image Processing
131 rdf:type schema:DefinedTerm
132 sg:person.01066111014.77 schema:affiliation grid-institutes:grid.415886.6
133 schema:familyName Comaniciu
134 schema:givenName Dorin
135 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01066111014.77
136 rdf:type schema:Person
137 sg:person.01154725330.99 schema:affiliation grid-institutes:grid.415886.6
138 schema:familyName Sharma
139 schema:givenName Puneet
140 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01154725330.99
141 rdf:type schema:Person
142 sg:person.012771740525.65 schema:affiliation grid-institutes:grid.61971.38
143 schema:familyName Bentaieb
144 schema:givenName Aicha
145 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012771740525.65
146 rdf:type schema:Person
147 sg:person.013364364655.13 schema:affiliation grid-institutes:grid.415886.6
148 schema:familyName Xu
149 schema:givenName Zhoubing
150 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013364364655.13
151 rdf:type schema:Person
152 sg:person.01372425362.30 schema:affiliation grid-institutes:grid.415886.6
153 schema:familyName Zhou
154 schema:givenName S. Kevin
155 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01372425362.30
156 rdf:type schema:Person
157 sg:person.013754250667.08 schema:affiliation grid-institutes:grid.415886.6
158 schema:familyName Taghanaki
159 schema:givenName Saeid Asgari
160 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013754250667.08
161 rdf:type schema:Person
162 sg:person.0642774233.16 schema:affiliation grid-institutes:grid.61971.38
163 schema:familyName Hamarneh
164 schema:givenName Ghassan
165 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0642774233.16
166 rdf:type schema:Person
167 sg:person.0703547214.37 schema:affiliation grid-institutes:grid.415886.6
168 schema:familyName Georgescu
169 schema:givenName Bogdan
170 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0703547214.37
171 rdf:type schema:Person
172 sg:person.07537734265.49 schema:affiliation grid-institutes:grid.61971.38
173 schema:familyName Sharma
174 schema:givenName Anmol
175 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07537734265.49
176 rdf:type schema:Person
177 sg:person.0767211426.21 schema:affiliation grid-institutes:grid.415886.6
178 schema:familyName Zheng
179 schema:givenName Yefeng
180 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0767211426.21
181 rdf:type schema:Person
182 grid-institutes:grid.415886.6 schema:alternateName Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA
183 schema:name Medical Image Analysis Lab, School of Computing Science, Simon Fraser University, Burnaby, Canada
184 Medical Imaging Technologies, Siemens Healthineers, Princeton, NJ, USA
185 rdf:type schema:Organization
186 grid-institutes:grid.61971.38 schema:alternateName Medical Image Analysis Lab, School of Computing Science, Simon Fraser University, Burnaby, Canada
187 schema:name Medical Image Analysis Lab, School of Computing Science, Simon Fraser University, Burnaby, Canada
188 rdf:type schema:Organization
 




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


...