Research on Image Semantic Modeling Based on Network Knowledge and Artificial Knowledge View Homepage


Ontology type: schema:MonetaryGrant     


Grant Info

YEARS

2013-2015

FUNDING AMOUNT

270000 CNY

ABSTRACT

With the rapid development of Internet techniques, the amount of digital images on the Internet increases dramatically. How we can leverage the rich Web image resources to benefit image semantic modeling in order to realize semantic based image retrieval and management becomes an increasingly important problem. In this proposal we target to address the key problems in image semantic understanding by leveraging the knowledge mined from Web images as well as obtained from human beings. Firstly, as the Web knowledge is highly noisy, we propose an Web knowledge quality assessment method by analyzing the images from both textual and visual cues. In addition, we propose to further improve the quality of the Web knowledge, based on two methods: image search visual reranking and multi-source Web knowledge fusion. Then, to model the semantic concepts better, light human supervision is introduced as complementary to automatically-collected Web knowledge. To obtain the human labeling information efficiently, we propose an active learning based sample selection method to select the most informative images for labeling. Finally, with the collected Web knowledge and human knowledge, we discuss the methods to employ them for learning semantic concept specific visual features and to develop novel machine learning methods which More... »

URL

http://npd.nsfc.gov.cn/projectDetail.action?pid=61201413

Related SciGraph Publications

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/2008/2208", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2208", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "amount": {
      "currency": "CNY", 
      "type": "MonetaryAmount", 
      "value": "270000"
    }, 
    "description": "With the rapid development of Internet techniques, the amount of digital images on the Internet increases dramatically. How we can leverage the rich Web image resources to benefit image semantic modeling in order to realize semantic based image retrieval and management becomes an increasingly important problem. In this proposal we target to address the key problems in image semantic understanding by leveraging the knowledge mined from Web images as well as obtained from human beings. Firstly, as the Web knowledge is highly noisy, we propose an Web knowledge quality assessment method by analyzing the images from both textual and visual cues. In addition, we propose to further improve the quality of the Web knowledge, based on two methods: image search visual reranking and multi-source Web knowledge fusion. Then, to model the semantic concepts better, light human supervision is introduced as complementary to automatically-collected Web knowledge. To obtain the human labeling information efficiently, we propose an active learning based sample selection method to select the most informative images for labeling. Finally, with the collected Web knowledge and human knowledge, we discuss the methods to employ them for learning semantic concept specific visual features and to develop novel machine learning methods which", 
    "endDate": "2015-12-31T00:00:00Z", 
    "funder": {
      "id": "https://www.grid.ac/institutes/grid.419696.5", 
      "type": "Organization"
    }, 
    "id": "sg:grant.7000894", 
    "identifier": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "7000894"
        ]
      }, 
      {
        "name": "nsfc_id", 
        "type": "PropertyValue", 
        "value": [
          "61201413"
        ]
      }
    ], 
    "inLanguage": [
      "zh"
    ], 
    "keywords": [
      "METHODS", 
      "labeling", 
      "human labeling information", 
      "informative images", 
      "semantic concepts", 
      "key problem", 
      "image retrieval", 
      "novel machine learning method", 
      "order", 
      "proposal", 
      "active learning", 
      "research", 
      "human beings", 
      "rapid development", 
      "network knowledge", 
      "digital images", 
      "specific visual features", 
      "visual cues", 
      "rich Web image resources", 
      "image search", 
      "web knowledge", 
      "web images", 
      "knowledge", 
      "sample selection method", 
      "important problem", 
      "images", 
      "quality", 
      "Internet", 
      "semantic understanding", 
      "multi-source Web knowledge fusion", 
      "Image Semantic Modeling Based", 
      "semantic modeling", 
      "human knowledge", 
      "Web knowledge quality assessment method", 
      "Visual reranking", 
      "light human supervision", 
      "management", 
      "amount", 
      "artificial knowledge", 
      "Internet techniques", 
      "addition"
    ], 
    "name": "Research on Image Semantic Modeling Based on Network Knowledge and Artificial Knowledge", 
    "recipient": [
      {
        "id": "https://www.grid.ac/institutes/grid.59053.3a", 
        "type": "Organization"
      }, 
      {
        "affiliation": {
          "id": "https://www.grid.ac/institutes/grid.59053.3a", 
          "name": "University of Science and Technology of China", 
          "type": "Organization"
        }, 
        "familyName": "Tian", 
        "givenName": "Xin Mei", 
        "id": "sg:person.015162133213.49", 
        "type": "Person"
      }, 
      {
        "member": "sg:person.015162133213.49", 
        "roleName": "PI", 
        "type": "Role"
      }
    ], 
    "sameAs": [
      "https://app.dimensions.ai/details/grant/grant.7000894"
    ], 
    "sdDataset": "grants", 
    "sdDatePublished": "2019-03-07T12:44", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com.uberresearch.data.processor/core_data/20181219_192338/projects/base/nsfc_projects_6.xml.gz", 
    "startDate": "2013-01-01T00:00:00Z", 
    "type": "MonetaryGrant", 
    "url": "http://npd.nsfc.gov.cn/projectDetail.action?pid=61201413"
  }
]
 

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/grant.7000894'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/grant.7000894'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/grant.7000894'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/grant.7000894'


 

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

85 TRIPLES      19 PREDICATES      63 URIs      55 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:grant.7000894 schema:about anzsrc-for:2208
2 schema:amount N05b1bef848ea4f6b9145d441b79be026
3 schema:description With the rapid development of Internet techniques, the amount of digital images on the Internet increases dramatically. How we can leverage the rich Web image resources to benefit image semantic modeling in order to realize semantic based image retrieval and management becomes an increasingly important problem. In this proposal we target to address the key problems in image semantic understanding by leveraging the knowledge mined from Web images as well as obtained from human beings. Firstly, as the Web knowledge is highly noisy, we propose an Web knowledge quality assessment method by analyzing the images from both textual and visual cues. In addition, we propose to further improve the quality of the Web knowledge, based on two methods: image search visual reranking and multi-source Web knowledge fusion. Then, to model the semantic concepts better, light human supervision is introduced as complementary to automatically-collected Web knowledge. To obtain the human labeling information efficiently, we propose an active learning based sample selection method to select the most informative images for labeling. Finally, with the collected Web knowledge and human knowledge, we discuss the methods to employ them for learning semantic concept specific visual features and to develop novel machine learning methods which
4 schema:endDate 2015-12-31T00:00:00Z
5 schema:funder https://www.grid.ac/institutes/grid.419696.5
6 schema:identifier N62be5441bf3b409ab2589803f7f6e65e
7 N6ec9b0b543aa4f69a95637dd7c04ffda
8 schema:inLanguage zh
9 schema:keywords Image Semantic Modeling Based
10 Internet
11 Internet techniques
12 METHODS
13 Visual reranking
14 Web knowledge quality assessment method
15 active learning
16 addition
17 amount
18 artificial knowledge
19 digital images
20 human beings
21 human knowledge
22 human labeling information
23 image retrieval
24 image search
25 images
26 important problem
27 informative images
28 key problem
29 knowledge
30 labeling
31 light human supervision
32 management
33 multi-source Web knowledge fusion
34 network knowledge
35 novel machine learning method
36 order
37 proposal
38 quality
39 rapid development
40 research
41 rich Web image resources
42 sample selection method
43 semantic concepts
44 semantic modeling
45 semantic understanding
46 specific visual features
47 visual cues
48 web images
49 web knowledge
50 schema:name Research on Image Semantic Modeling Based on Network Knowledge and Artificial Knowledge
51 schema:recipient N85ca76448b8246d1a4bc230e791dbcb2
52 sg:person.015162133213.49
53 https://www.grid.ac/institutes/grid.59053.3a
54 schema:sameAs https://app.dimensions.ai/details/grant/grant.7000894
55 schema:sdDatePublished 2019-03-07T12:44
56 schema:sdLicense https://scigraph.springernature.com/explorer/license/
57 schema:sdPublisher Nc78c65d5b0794871a4882a8a8ee8674d
58 schema:startDate 2013-01-01T00:00:00Z
59 schema:url http://npd.nsfc.gov.cn/projectDetail.action?pid=61201413
60 sgo:license sg:explorer/license/
61 sgo:sdDataset grants
62 rdf:type schema:MonetaryGrant
63 N05b1bef848ea4f6b9145d441b79be026 schema:currency CNY
64 schema:value 270000
65 rdf:type schema:MonetaryAmount
66 N62be5441bf3b409ab2589803f7f6e65e schema:name dimensions_id
67 schema:value 7000894
68 rdf:type schema:PropertyValue
69 N6ec9b0b543aa4f69a95637dd7c04ffda schema:name nsfc_id
70 schema:value 61201413
71 rdf:type schema:PropertyValue
72 N85ca76448b8246d1a4bc230e791dbcb2 schema:member sg:person.015162133213.49
73 schema:roleName PI
74 rdf:type schema:Role
75 Nc78c65d5b0794871a4882a8a8ee8674d schema:name Springer Nature - SN SciGraph project
76 rdf:type schema:Organization
77 anzsrc-for:2208 schema:inDefinedTermSet anzsrc-for:
78 rdf:type schema:DefinedTerm
79 sg:person.015162133213.49 schema:affiliation https://www.grid.ac/institutes/grid.59053.3a
80 schema:familyName Tian
81 schema:givenName Xin Mei
82 rdf:type schema:Person
83 https://www.grid.ac/institutes/grid.419696.5 schema:Organization
84 https://www.grid.ac/institutes/grid.59053.3a schema:name University of Science and Technology of China
85 rdf:type schema:Organization
 




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


...