A Biologically-Inspired Network for Generic Object Recognition Using CUDA View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2012

AUTHORS

Yuekai Wang , Xiaofeng Wu , Xiaoying Song , Wenqiang Zhang , Juyang Weng

ABSTRACT

Generic object recognition is one of the most important fields in the artificial intelligence. Some cortex-like networks for generic object recognition are proposed these years. But most of them concentrated on the discussion about the recognition performance (such as recognition rate, number of objects to be recognized), not the practicability, i.e., implementation with ubiquitous devices and application in real time. This paper reports a try on implementation of a biologically-inspired where-what network (WWN), which integrates object recognition and attention in a single network, via parallelizing the various stages of the network training with CUDA on GPU to shorten the training time. The experiment on HAIBAO Robot exhibited in 2010 Shanghai Expo shows that this optimization can achieve a speedup of almost 16 times compared to the C-based program on an Intel Core 2 DUO 3.00 GHZ CPU in real environments. More... »

PAGES

1-6

Book

TITLE

Recent Advances in Computer Science and Information Engineering

ISBN

978-3-642-25788-9
978-3-642-25789-6

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-25789-6_1

DOI

http://dx.doi.org/10.1007/978-3-642-25789-6_1

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1046051845


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": "Fudan University", 
          "id": "https://www.grid.ac/institutes/grid.8547.e", 
          "name": [
            "State Key Lab. of ASIC & System, Fudan University, Shanghai, 200433, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Yuekai", 
        "id": "sg:person.011445407563.91", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011445407563.91"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Fudan University", 
          "id": "https://www.grid.ac/institutes/grid.8547.e", 
          "name": [
            "State Key Lab. of ASIC & System, Fudan University, Shanghai, 200433, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wu", 
        "givenName": "Xiaofeng", 
        "id": "sg:person.014506670121.37", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014506670121.37"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Fudan University", 
          "id": "https://www.grid.ac/institutes/grid.8547.e", 
          "name": [
            "School of Computer Science, Fudan University, Shanghai, 200433, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Song", 
        "givenName": "Xiaoying", 
        "id": "sg:person.013040350563.30", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013040350563.30"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Fudan University", 
          "id": "https://www.grid.ac/institutes/grid.8547.e", 
          "name": [
            "School of Computer Science, Fudan University, Shanghai, 200433, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhang", 
        "givenName": "Wenqiang", 
        "id": "sg:person.010531241272.46", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010531241272.46"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Fudan University", 
          "id": "https://www.grid.ac/institutes/grid.8547.e", 
          "name": [
            "School of Computer Science, Fudan University, Shanghai, 200433, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Weng", 
        "givenName": "Juyang", 
        "id": "sg:person.01342604202.51", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01342604202.51"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1146/annurev.neuro.29.051605.112939", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004797113"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/14819", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035393709", 
          "https://doi.org/10.1038/14819"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/14819", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035393709", 
          "https://doi.org/10.1038/14819"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2007.56", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061743347"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/ijcnn.2010.5596778", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094413607"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/devlrn.2010.5578824", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095350495"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/devlrn.2008.4640806", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095541778"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.1999.790410", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095766209"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2012", 
    "datePublishedReg": "2012-01-01", 
    "description": "Generic object recognition is one of the most important fields in the artificial intelligence. Some cortex-like networks for generic object recognition are proposed these years. But most of them concentrated on the discussion about the recognition performance (such as recognition rate, number of objects to be recognized), not the practicability, i.e., implementation with ubiquitous devices and application in real time. This paper reports a try on implementation of a biologically-inspired where-what network (WWN), which integrates object recognition and attention in a single network, via parallelizing the various stages of the network training with CUDA on GPU to shorten the training time. The experiment on HAIBAO Robot exhibited in 2010 Shanghai Expo shows that this optimization can achieve a speedup of almost 16 times compared to the C-based program on an Intel Core 2 DUO 3.00 GHZ CPU in real environments.", 
    "editor": [
      {
        "familyName": "Qian", 
        "givenName": "Zhihong", 
        "type": "Person"
      }, 
      {
        "familyName": "Cao", 
        "givenName": "Lei", 
        "type": "Person"
      }, 
      {
        "familyName": "Su", 
        "givenName": "Weilian", 
        "type": "Person"
      }, 
      {
        "familyName": "Wang", 
        "givenName": "Tingkai", 
        "type": "Person"
      }, 
      {
        "familyName": "Yang", 
        "givenName": "Huamin", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-25789-6_1", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-642-25788-9", 
        "978-3-642-25789-6"
      ], 
      "name": "Recent Advances in Computer Science and Information Engineering", 
      "type": "Book"
    }, 
    "name": "A Biologically-Inspired Network for Generic Object Recognition Using CUDA", 
    "pagination": "1-6", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-25789-6_1"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "db5d9df0dadea5ced50d85445f17d9b3786813c863a7baf50f3f1121d5c74470"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1046051845"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-25789-6_1", 
      "https://app.dimensions.ai/details/publication/pub.1046051845"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T13:30", 
    "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_8664_00000271.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/978-3-642-25789-6_1"
  }
]
 

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.10.1007/978-3-642-25789-6_1'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-25789-6_1'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-25789-6_1'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-25789-6_1'


 

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

136 TRIPLES      23 PREDICATES      34 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-25789-6_1 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nae89473c30a342c49fadda65db91e31f
4 schema:citation sg:pub.10.1038/14819
5 https://doi.org/10.1109/devlrn.2008.4640806
6 https://doi.org/10.1109/devlrn.2010.5578824
7 https://doi.org/10.1109/iccv.1999.790410
8 https://doi.org/10.1109/ijcnn.2010.5596778
9 https://doi.org/10.1109/tpami.2007.56
10 https://doi.org/10.1146/annurev.neuro.29.051605.112939
11 schema:datePublished 2012
12 schema:datePublishedReg 2012-01-01
13 schema:description Generic object recognition is one of the most important fields in the artificial intelligence. Some cortex-like networks for generic object recognition are proposed these years. But most of them concentrated on the discussion about the recognition performance (such as recognition rate, number of objects to be recognized), not the practicability, i.e., implementation with ubiquitous devices and application in real time. This paper reports a try on implementation of a biologically-inspired where-what network (WWN), which integrates object recognition and attention in a single network, via parallelizing the various stages of the network training with CUDA on GPU to shorten the training time. The experiment on HAIBAO Robot exhibited in 2010 Shanghai Expo shows that this optimization can achieve a speedup of almost 16 times compared to the C-based program on an Intel Core 2 DUO 3.00 GHZ CPU in real environments.
14 schema:editor N87de5386b1904f438cf791c9ebc710b5
15 schema:genre chapter
16 schema:inLanguage en
17 schema:isAccessibleForFree false
18 schema:isPartOf N1e89e8e24f324ef88d2460efeac5dded
19 schema:name A Biologically-Inspired Network for Generic Object Recognition Using CUDA
20 schema:pagination 1-6
21 schema:productId N014c0e1112ef4fb0bd94cdd7566e4a3a
22 N11419b3440b0444fb91f1fa66f901006
23 Ncd1433fa07b04913bc648255cc62076d
24 schema:publisher Nc87bd2a829d04f0abffb6ee64a6ec427
25 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046051845
26 https://doi.org/10.1007/978-3-642-25789-6_1
27 schema:sdDatePublished 2019-04-15T13:30
28 schema:sdLicense https://scigraph.springernature.com/explorer/license/
29 schema:sdPublisher Nfa9d5a047ea24dbe926480b0f3834293
30 schema:url http://link.springer.com/10.1007/978-3-642-25789-6_1
31 sgo:license sg:explorer/license/
32 sgo:sdDataset chapters
33 rdf:type schema:Chapter
34 N014c0e1112ef4fb0bd94cdd7566e4a3a schema:name doi
35 schema:value 10.1007/978-3-642-25789-6_1
36 rdf:type schema:PropertyValue
37 N0966abb090ce4ea29c22a3d28d9858f8 schema:familyName Su
38 schema:givenName Weilian
39 rdf:type schema:Person
40 N11419b3440b0444fb91f1fa66f901006 schema:name readcube_id
41 schema:value db5d9df0dadea5ced50d85445f17d9b3786813c863a7baf50f3f1121d5c74470
42 rdf:type schema:PropertyValue
43 N164b79139b674ff3bc5e993c9b06cadc schema:familyName Wang
44 schema:givenName Tingkai
45 rdf:type schema:Person
46 N1e89e8e24f324ef88d2460efeac5dded schema:isbn 978-3-642-25788-9
47 978-3-642-25789-6
48 schema:name Recent Advances in Computer Science and Information Engineering
49 rdf:type schema:Book
50 N45138ea195184722ad4e4ac4d871be9e rdf:first sg:person.01342604202.51
51 rdf:rest rdf:nil
52 N4c80c2eb85054c828cb793455e983dbe schema:familyName Qian
53 schema:givenName Zhihong
54 rdf:type schema:Person
55 N4e20dc58515d40d2acd0d1c3a4ba36ba rdf:first sg:person.013040350563.30
56 rdf:rest Nde0ec17bbb1b4f819162c45d7b956fff
57 N5174f66b5dea45378463cd5a5341ccdb rdf:first Nad5bfce1261a487e8f3a8640062b34c2
58 rdf:rest N809ede37d4b049d3820d54661ddfdbc7
59 N809ede37d4b049d3820d54661ddfdbc7 rdf:first N0966abb090ce4ea29c22a3d28d9858f8
60 rdf:rest Ncca7551f32004b85ab1a7ba38f6f3b1c
61 N834bde3a4cfc4296b10c025f94c61dcb schema:familyName Yang
62 schema:givenName Huamin
63 rdf:type schema:Person
64 N87de5386b1904f438cf791c9ebc710b5 rdf:first N4c80c2eb85054c828cb793455e983dbe
65 rdf:rest N5174f66b5dea45378463cd5a5341ccdb
66 Nad5bfce1261a487e8f3a8640062b34c2 schema:familyName Cao
67 schema:givenName Lei
68 rdf:type schema:Person
69 Nae89473c30a342c49fadda65db91e31f rdf:first sg:person.011445407563.91
70 rdf:rest Nc25e2500c190484ba57b3e705db2362d
71 Nc25e2500c190484ba57b3e705db2362d rdf:first sg:person.014506670121.37
72 rdf:rest N4e20dc58515d40d2acd0d1c3a4ba36ba
73 Nc87bd2a829d04f0abffb6ee64a6ec427 schema:location Berlin, Heidelberg
74 schema:name Springer Berlin Heidelberg
75 rdf:type schema:Organisation
76 Ncca7551f32004b85ab1a7ba38f6f3b1c rdf:first N164b79139b674ff3bc5e993c9b06cadc
77 rdf:rest Ndb2be178c5664fad865726d8c5faab4f
78 Ncd1433fa07b04913bc648255cc62076d schema:name dimensions_id
79 schema:value pub.1046051845
80 rdf:type schema:PropertyValue
81 Ndb2be178c5664fad865726d8c5faab4f rdf:first N834bde3a4cfc4296b10c025f94c61dcb
82 rdf:rest rdf:nil
83 Nde0ec17bbb1b4f819162c45d7b956fff rdf:first sg:person.010531241272.46
84 rdf:rest N45138ea195184722ad4e4ac4d871be9e
85 Nfa9d5a047ea24dbe926480b0f3834293 schema:name Springer Nature - SN SciGraph project
86 rdf:type schema:Organization
87 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
88 schema:name Information and Computing Sciences
89 rdf:type schema:DefinedTerm
90 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
91 schema:name Artificial Intelligence and Image Processing
92 rdf:type schema:DefinedTerm
93 sg:person.010531241272.46 schema:affiliation https://www.grid.ac/institutes/grid.8547.e
94 schema:familyName Zhang
95 schema:givenName Wenqiang
96 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010531241272.46
97 rdf:type schema:Person
98 sg:person.011445407563.91 schema:affiliation https://www.grid.ac/institutes/grid.8547.e
99 schema:familyName Wang
100 schema:givenName Yuekai
101 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011445407563.91
102 rdf:type schema:Person
103 sg:person.013040350563.30 schema:affiliation https://www.grid.ac/institutes/grid.8547.e
104 schema:familyName Song
105 schema:givenName Xiaoying
106 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013040350563.30
107 rdf:type schema:Person
108 sg:person.01342604202.51 schema:affiliation https://www.grid.ac/institutes/grid.8547.e
109 schema:familyName Weng
110 schema:givenName Juyang
111 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01342604202.51
112 rdf:type schema:Person
113 sg:person.014506670121.37 schema:affiliation https://www.grid.ac/institutes/grid.8547.e
114 schema:familyName Wu
115 schema:givenName Xiaofeng
116 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014506670121.37
117 rdf:type schema:Person
118 sg:pub.10.1038/14819 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035393709
119 https://doi.org/10.1038/14819
120 rdf:type schema:CreativeWork
121 https://doi.org/10.1109/devlrn.2008.4640806 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095541778
122 rdf:type schema:CreativeWork
123 https://doi.org/10.1109/devlrn.2010.5578824 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095350495
124 rdf:type schema:CreativeWork
125 https://doi.org/10.1109/iccv.1999.790410 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095766209
126 rdf:type schema:CreativeWork
127 https://doi.org/10.1109/ijcnn.2010.5596778 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094413607
128 rdf:type schema:CreativeWork
129 https://doi.org/10.1109/tpami.2007.56 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743347
130 rdf:type schema:CreativeWork
131 https://doi.org/10.1146/annurev.neuro.29.051605.112939 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004797113
132 rdf:type schema:CreativeWork
133 https://www.grid.ac/institutes/grid.8547.e schema:alternateName Fudan University
134 schema:name School of Computer Science, Fudan University, Shanghai, 200433, China
135 State Key Lab. of ASIC & System, Fudan University, Shanghai, 200433, China
136 rdf:type schema:Organization
 




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


...