System and method for semantic video segmentation based on joint audiovisual and text analysis


Ontology type: sgo:Patent     


Patent Info

DATE

2008-06-03T00:00

AUTHORS

Chitra Dorai , Ying Li , Youngja Park

ABSTRACT

System and method for partitioning a video into a series of semantic units where each semantic unit relates to a generally complete thematic topic. A computer implemented method for partitioning a video into a series of semantic units wherein each semantic unit relates to a theme or a topic, comprises dividing a video into a plurality of homogeneous segments, analyzing audio and visual content of the video, extracting a plurality of keywords from the speech content of each of the plurality of homogeneous segments of the video, and detecting and merging a plurality of groups of semantically related and temporally adjacent homogeneous segments into a series of semantic units in accordance with the results of both the audio and visual analysis and the keyword extraction. The present invention can be applied to generate important table-of-contents as well as index tables for videos to facilitate efficient video topic searching and browsing. More... »

Related SciGraph Publications

  • 1993-01. Automatic partitioning of full-motion video in MULTIMEDIA SYSTEMS
  • 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/2008/2746", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "name": "Chitra Dorai", 
            "type": "Person"
          }, 
          {
            "name": "Ying Li", 
            "type": "Person"
          }, 
          {
            "name": "Youngja Park", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/bf01210504", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040339826", 
              "https://doi.org/10.1007/bf01210504"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf01210504", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040339826", 
              "https://doi.org/10.1007/bf01210504"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2008-06-03T00:00", 
        "description": "

    System and method for partitioning a video into a series of semantic units where each semantic unit relates to a generally complete thematic topic. A computer implemented method for partitioning a video into a series of semantic units wherein each semantic unit relates to a theme or a topic, comprises dividing a video into a plurality of homogeneous segments, analyzing audio and visual content of the video, extracting a plurality of keywords from the speech content of each of the plurality of homogeneous segments of the video, and detecting and merging a plurality of groups of semantically related and temporally adjacent homogeneous segments into a series of semantic units in accordance with the results of both the audio and visual analysis and the keyword extraction. The present invention can be applied to generate important table-of-contents as well as index tables for videos to facilitate efficient video topic searching and browsing.

    ", "id": "sg:patent.US-7382933-B2", "keywords": [ "method", "segmentation", "joint", "text analysis", "video", "semantics", "computer", "theme", "plurality", "segment", "visual content", "keywords", "content", "accordance", "visual analysis", "extraction", "invention", "index", "browsing" ], "name": "System and method for semantic video segmentation based on joint audiovisual and text analysis", "recipient": [ { "id": "https://www.grid.ac/institutes/grid.410484.d", "type": "Organization" } ], "sameAs": [ "https://app.dimensions.ai/details/patent/US-7382933-B2" ], "sdDataset": "patents", "sdDatePublished": "2019-04-18T10:31", "sdLicense": "https://scigraph.springernature.com/explorer/license/", "sdPublisher": { "name": "Springer Nature - SN SciGraph project", "type": "Organization" }, "sdSource": "s3://com-uberresearch-data-patents-target-20190320-rc/data/sn-export/402f166718b70575fb5d4ffe01f064d1/0000100128-0000352499/json_export_03596.jsonl", "type": "Patent" } ]
     

    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/patent.US-7382933-B2'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/patent.US-7382933-B2'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/patent.US-7382933-B2'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/patent.US-7382933-B2'


     

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

    53 TRIPLES      15 PREDICATES      34 URIs      27 LITERALS      2 BLANK NODES

    Subject Predicate Object
    1 sg:patent.US-7382933-B2 schema:about anzsrc-for:2746
    2 schema:author Nddc1c3c645b34605840a8799877adab7
    3 schema:citation sg:pub.10.1007/bf01210504
    4 schema:datePublished 2008-06-03T00:00
    5 schema:description <p num="p-0001">System and method for partitioning a video into a series of semantic units where each semantic unit relates to a generally complete thematic topic. A computer implemented method for partitioning a video into a series of semantic units wherein each semantic unit relates to a theme or a topic, comprises dividing a video into a plurality of homogeneous segments, analyzing audio and visual content of the video, extracting a plurality of keywords from the speech content of each of the plurality of homogeneous segments of the video, and detecting and merging a plurality of groups of semantically related and temporally adjacent homogeneous segments into a series of semantic units in accordance with the results of both the audio and visual analysis and the keyword extraction. The present invention can be applied to generate important table-of-contents as well as index tables for videos to facilitate efficient video topic searching and browsing.</p>
    6 schema:keywords accordance
    7 browsing
    8 computer
    9 content
    10 extraction
    11 index
    12 invention
    13 joint
    14 keywords
    15 method
    16 plurality
    17 segment
    18 segmentation
    19 semantics
    20 text analysis
    21 theme
    22 video
    23 visual analysis
    24 visual content
    25 schema:name System and method for semantic video segmentation based on joint audiovisual and text analysis
    26 schema:recipient https://www.grid.ac/institutes/grid.410484.d
    27 schema:sameAs https://app.dimensions.ai/details/patent/US-7382933-B2
    28 schema:sdDatePublished 2019-04-18T10:31
    29 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    30 schema:sdPublisher N2a02809672804f7a9f77dbbafe6031e1
    31 sgo:license sg:explorer/license/
    32 sgo:sdDataset patents
    33 rdf:type sgo:Patent
    34 N04104803f18f4716b6983470fbe8ff1a schema:name Chitra Dorai
    35 rdf:type schema:Person
    36 N09884bf2f0f54e10af08fad3e75d6f61 schema:name Youngja Park
    37 rdf:type schema:Person
    38 N2a02809672804f7a9f77dbbafe6031e1 schema:name Springer Nature - SN SciGraph project
    39 rdf:type schema:Organization
    40 N5e9029f3fcc44734a112ae62acad9b53 schema:name Ying Li
    41 rdf:type schema:Person
    42 Nb89efc3d6d5d46478ee7edef3ecf8431 rdf:first N5e9029f3fcc44734a112ae62acad9b53
    43 rdf:rest Nf2fa2998a2bd4f20a008cd34b8030a77
    44 Nddc1c3c645b34605840a8799877adab7 rdf:first N04104803f18f4716b6983470fbe8ff1a
    45 rdf:rest Nb89efc3d6d5d46478ee7edef3ecf8431
    46 Nf2fa2998a2bd4f20a008cd34b8030a77 rdf:first N09884bf2f0f54e10af08fad3e75d6f61
    47 rdf:rest rdf:nil
    48 anzsrc-for:2746 schema:inDefinedTermSet anzsrc-for:
    49 rdf:type schema:DefinedTerm
    50 sg:pub.10.1007/bf01210504 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040339826
    51 https://doi.org/10.1007/bf01210504
    52 rdf:type schema:CreativeWork
    53 https://www.grid.ac/institutes/grid.410484.d schema:Organization
     




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


    ...