SlideShare a Scribd company logo
1




                   Rich Unified Content
                   Description (RUCoD)

                             Vincenzo Croce
                    Research & Development
                          Laboratory


STAR 2013 Lausanne, 18-19 January 2013
Objectives                                             2


     To develop a formal description for each type of multimedia
      content (text, audio, image, video and 3D content)

     To develop formal descriptions for real world and social
      information

     To clearly specify the format of the Rich Unified Content
      Description (RUCoD)

     To represent in the same format, the actual content
      (multimedia information) along with the additional contextual
      information (real world, user-related)



STAR 2013 Lausanne, 18-19 January 2013
The Concept of Content                                         3

               Object
        “A Content Object is the representation of a specific
     instance of either a physical object or a physical entity (an
        entity that has physical existence), which might have
     multiple views (many images, videos, audio files, text, real-
                 world and user-related information).”

  Similar approaches:
   Multimedia Document (MMD): a set of co-occurring multimedia
     objects (e.g. images, audio and text) that are of different modalities
     but carry the same semantics. If two multimedia objects are in the
     same MMD, they can be regarded as context of each other.
   Multimedia Bag: defines a container including text instances, image
     instances and audio instances that share the shame semantic
     concepts

STAR 2013 Lausanne, 18-19 January 2013
The Concept of Content                                         4

               Object
                                            A CO may consist of several
                                             media types, user-related
                                             information and real-world
                                             information.
                                                  A CO can be the result of an
                                                   authoring process (e.g. using
                                                   an authoring tool).
                                                       RUCoD is a formal
                                                        representation of a CO
                                                        consisting of descriptions
                                                        of various media types
                                                        somehow associated to
                                                        each other.
STAR 2013 Lausanne, 18-19 January 2013
Example Content Object                                                 5




      Great (Cheops) –
                                             3D object
      Pyramid of Giza                                                     Image

                                               CO:
                                         Great (Cheops) –
                                         Pyramid of Giza




                                                Text:                 Real-world (location)
                               It is believed the pyramid was built
                                    as a tomb for Fourth dynasty
                                    Egyptian    pharaoh    Khufu(or
                                    Cheops) and constructed over a
                                    14 to 20 year period concluding
STAR 2013 Lausanne, 18-19 January 2013 2560 BC…
                                    around
RUCoD Specification                                                         6




                                              Real World Descriptors
                                              Position    Weather
                     Date       Time
                                             (GPS, etc) (temperature)
                                                                         Sensors   …
                               Header
CO ID Creator     Version CO Types Multimedia RW-info           U-Info      …

       Header    Low-Level Descriptors        Real World          User-related Descriptors
                                              Descriptors


                          Low-Level Descriptors
   Text-based        Image          Video         Audio        3D
   descriptors     descriptors   descriptors    descriptors descriptors       …
                                     User-related Descriptors
            Expressions   Emotions       Valence            Arousal         …
STAR 2013 Lausanne, 18-19 January 2013
RUCoD Structure                      7

          Header




                                            L_Descriptor:
                                             -“TextType”
                                             - “Object3D”
                                             - “ImageType”
                                             - “SoundType”
                                             - “VideoType”


                                          R_Descriptor:
                                           - “ContextType”
          Description




                                          U_Descriptor:
                                           - “Valence”
                                           - “Arousal”




STAR 2013 Lausanne, 18-19 January 2013
RUCoD Structure (Header)                                                        8


    <Header>
        <ContentObjectType>Physical Object</ContentObjectType>
        <ContentObjectName xml:lang="en-US">My Bulldog Barking</ContentObjectName>
        <ContentObjectID>3577B5EF-523F-4946-9734-C974CEA6C646</ContentObjectID>
        <ContentObjectVersion>1</ContentObjectVersion>
        <ContentObjectCreationInformation>
              <Creator> <Name>CERTH</Name></Creator>
        </ContentObjectCreationInformation>
        <ContentObjectTypes>
              <MultimediaContent type="Text">
                        <FreeText>It is the image, video and 3D representation… </FreeText>
              </MultimediaContent>
              <MultimediaContent type="Object3D">
                        <MediaName>Bulldog</MediaName>
                        <FileFormat>x-world/x-vrml</FileFormat>
                        <MediaLocator>
                                   <MediaUri>http://3d-test.iti.gr/dog.wrl</MediaUri>
                                   <MediaPreview>http://3d-test.iti.gr/dog.jpg</MediaPreview>
                        </MediaLocator>
              </MultimediaContent>
              <MultimediaContent type="ImageType">
    …
    </Header>


STAR 2013 Lausanne, 18-19 January 2013
RUCoD Structure (L-Descriptor)                                              9


    <L_Descriptor type="Object3D">
        <MediaName>BulldogLR</MediaName>
        <Shape3DDescription type="CMVD" matching="MultiViewL2">
              <LowLevelDescriptor totalNumOfViews="18" totalNumOfDescriptors="212"
        descriptorType="xsd:float" descriptorSize="3816">
                 <Store type="Text">
                    <DescriptorLocator>
                        <DescriptorUri>http://3d-test.iti.gr/CMVD.descr</DescriptorUri>
                    </DescriptorLocator>
                 </Store>
                        </LowLevelDescriptor>
        </Shape3DDescription>
    </L_Descriptor>
    <L_Descriptor type="SoundType">
        <MediaName>BulldogSound2</MediaName>
        <AudioDescription type="BarkBands" matching="BrayCurtis">
              <LowLevelDescriptor totalNumOfDescriptors="216" descriptorType="xsd:float"
        descriptorSize="8 27">
              <DescriptorValues>
                        2.31510340412e-12 3.04525744899e-11 2.56972665369e-10
                        6.54444409776e-09 2.40772557447e-09 2.14078905714e-08 …
              </DescriptorValues>
              </LowLevelDescriptor>
        </AudioDescription>
    </L_Descriptor>
STAR 2013 Lausanne, 18-19 January 2013
RUCoD Structure (R-Descriptor)                                     10


    <R_Descriptor>
        <RealWorldDescription type="ContextType">
              <ContextSlice>
                        <Importance>1</Importance>
                        <DateTime>
                                   <Date>1997-07-16T19:20:30.45+01:00</Date>
                                   <Length>100</Length>
                        </DateTime>
                        <SubjectPosition>
                                   <gml:CircleByCenterPoint numArc="1">
                                       <gml:pos>45.8419444 13.4002778</gml:pos>
                                       <gml:radius uom="M">10</gml:radius>
                                   </gml:CircleByCenterPoint>
                        </SubjectPosition>
                        <Weather>
                                   <Condition>OVC RA</Condition>
                                   <Temperature>20</Temperature>
                                   <WindSpeed>2</WindSpeed>
                                   <Humidity>94</Humidity>
                        </Weather>
              </ContextSlice>
        </RealWorldDescription>
    </R_Descriptor>




STAR 2013 Lausanne, 18-19 January 2013
RUCoD Structure (U-Descriptor)                                 11


    <U_Descriptor type="UserType">
        <MediaName>aerosmith-Aerosmith-01-Make_It.mp3</MediaName>
        <UserDescription matching="L2Distance" type="AvgValenceArousal">
           <LowLevelDescriptor descriptorSize="1 1“
                      descriptorType="xsd:float" totalNumOfDescriptors="2">
                    <DescriptorValues>-0.4898 0.42857</DescriptorValues>
           </LowLevelDescriptor>
        </UserDescription>
    </U_Descriptor>




STAR 2013 Lausanne, 18-19 January 2013
RUCoD Schema                                12




    •    RUCoD Schema Final Version (1.4.1) released in
         November 2011:
        •   The RUCoD.xsd Schema file
        •   The RUCoD_Descriptors.xsd Schema file


            http://www.isearch-project.eu/isearch/RUCoD/




STAR 2013 Lausanne, 18-19 January 2013
Block diagram of the I-SEARCH framework   13




STAR 2013 Lausanne, 18-19 January 2013
Authoring & Content Analytics
                                                               14
               Architecture
        Authoring




                                          Content Analytics




STAR 2013 Lausanne, 18-19 January 2013   Indexing triggering
RUCoD in I-SEARCH Use                                                        15

                Cases Social retrieval
                   UC2:                UC3: Furniture retrieval
                        of music                    •Text
                        •Audio (music)              •3D objects
                        •Text                       •Images
                        •Video clip                 •Real-world (location, time)
 UC1: Music retrieval   •Real-world (location)
•Audio (music)          •Emotions
•Text                                                              UC4: Search for Multimedia
                                                                   using smartphone
•Images
                                               Rich               •Text
•Real-world
                                              Unified             •3D objects
(location, time)                              Content             •Images
•Emotions
                                             Description          •Real-world (location, time)
 UC7: Game avatar retrieval
 •3D objects                                                  UC5: Search for specific
 •Images                                                      product
                                                              •Text
 •Video                      UC6: 3D game component           •3D objects
 •Emotions                   retrieval
                                                              •Images
                            •Text
                                                              •Video
                            •3D objects
                                                              •Audio (sounds)
                            •Images
                                                              •Real-world (location, time)
                            •Audio (sounds)
                                                              •Emotions
                            •Real-world
STAR 2013 Lausanne, 18-19 January 2013 (location, time)
Comparison with MPEG-7                                  16




    What we use:
        •   MediaLocator and MediaUri are used to describe the link
            to a specific media item.
        •   Creator is used for description of the author of a media
            item.
        •   Annotation as a part of RUCoD represents textual
            information of a media item or CO.
        •   Image/Video/Audio Descriptors are used for the low-level
            descriptions of the separate media items within a CO.
        •   Segment is used to describe a temporal video segment.




STAR 2013 Lausanne, 18-19 January 2013
Comparison with MPEG-7                                  17




    What we adapted:
    •    ContentObjectName, ContentObjectCreationInformation
         instead of name and CreationInformation to represent the
         name and creators of COs.
    •    TextDescription, Shape3DDescription, ImageDescription and
         VideoDescription, similar to MPEG-7 ContentDescription to
         distinguish between the descriptors of different modalities
         inside the same RUCoD.




STAR 2013 Lausanne, 18-19 January 2013
Comparison with MPEG-7                                              18


    What is new:
    •    Cross-modal & multimodal retrieval are not entirely supported by the
         standards.
    •    New types of information describing the COs are introduced, such as real-
         world descriptors and user-related descriptors. These enrich the CO
         description and improve the retrieval performance, by introducing new
         querying capabilities.
    •    With respect to low-level descriptor extraction for media items, novel
         descriptors are introduced. As an example, for 3D content description, new
         state-of-the-art descriptors are introduced, which achieve higher retrieval
         performance than those included in MPEG-7. Similarly, new descriptors are
         introduced for image, video and audio content.
    •    The low-level description of media items is also accompanied by
         specification of the matching scheme for each descriptor. In this case, the
         description scheme does not leave the responsibility for choosing the
         appropriate matching method to the search engine.


STAR 2013 Lausanne, 18-19 January 2013
Comparison with JPSearch

    What is similar/different:
    • JPSearch is designed in a way that decouples the
      components of image search and provides a standard
      interface between these components. Its aim is to build a
      standard for interoperability among image search and
      retrieval systems
    • RUCoD specification is focused on the description of
      COs and it addresses a broad range of media (apart
      from images), real-world and user-related information




STAR 2013 Lausanne, 18-19 January 2013
Comparison with MPEG-21


     What we use:
     • A multimodal approach to media (which can be of any type)
     • Allowing the creation and attachment of rich metadata to
       digital objects




STAR 2013 Lausanne, 18-19 January 2013
Comparison with MPEG-21


    What is similar:
    • Ability to create multimedia content objects (Digital Items in
      MPEG-21)
    • Ability for content adaptation, although achieved differently
      (e.g. through FileFormat elements in the RUCoD)
    • L-Descriptors and R-Descriptors of RUCoD could be attached
      to MPEG-21 objects although not directly foreseen by the
      standard




STAR 2013 Lausanne, 18-19 January 2013
Comparison with MPEG-21

    What is different/new:
    • The CO broadens the concept of Digital Item making it more
      general and flexible
    • Unification of the actual metadata and descriptors (e.g. L-
      Descriptors) together with real world and user-related parts in
      the same format.
    • RUCoD is particularly targeted at indexing, sharing, search
      and retrieval
    • RUCoD overcomes the traditional hierarchical object model
      (also foreseen in MPEG-21) allowing for more flexible and
      user-centric 'connections' (e.g. RelatedSemanticConcepts
      field)


STAR 2013 Lausanne, 18-19 January 2013
Ongoing Work
    • RUCoD initially designed to serve the needs of the I-
      SEARCH framework
    • However, it is not mature enough to be used in a wider
      range of applications.
    • RUCoD will be extended within the EU-funded project
      CUbRIK (CERTH and ENG are participants).
    • RUCoD will be adopted in CUbRIK.
    • A first attempt: SMILA Hackathlon, November 2011,
      Keiserslautern.
        •   RUCoD was presented in the workshop
        •   RUCoD was used as descriptor scheme to check indexing and search
            within the SMILA engine



STAR 2013 Lausanne, 18-19 January 2013
24




                                 Questions?




STAR 2013 Lausanne, 18-19 January 2013

More Related Content

More from CUbRIK Project

Building a social graph for the history of Europe: the CUbRIK histoGraph
Building a social graph for the history of Europe: the CUbRIK histoGraphBuilding a social graph for the history of Europe: the CUbRIK histoGraph
Building a social graph for the history of Europe: the CUbRIK histoGraph
CUbRIK Project
 
The CUbRIK histoGraph Factsheet
The CUbRIK histoGraph FactsheetThe CUbRIK histoGraph Factsheet
The CUbRIK histoGraph Factsheet
CUbRIK Project
 
CUbRIK Fashion Trend Analysis: a Business Intelligence Application
CUbRIK Fashion Trend Analysis: a Business Intelligence ApplicationCUbRIK Fashion Trend Analysis: a Business Intelligence Application
CUbRIK Fashion Trend Analysis: a Business Intelligence Application
CUbRIK Project
 
CUbRIK Social Graph Visual Interface
CUbRIK Social Graph Visual InterfaceCUbRIK Social Graph Visual Interface
CUbRIK Social Graph Visual Interface
CUbRIK Project
 
Mining Emotions in Short Films: User Comments or Crowdsourcing?
Mining Emotions in Short Films: User Comments or Crowdsourcing?Mining Emotions in Short Films: User Comments or Crowdsourcing?
Mining Emotions in Short Films: User Comments or Crowdsourcing?
CUbRIK Project
 
CUbRIK and gaming experience@Qualinet
CUbRIK and gaming experience@QualinetCUbRIK and gaming experience@Qualinet
CUbRIK and gaming experience@Qualinet
CUbRIK Project
 
CUbRIK: Open Box. Multimedia and Human Computation approach
CUbRIK: Open Box. Multimedia and Human Computation approachCUbRIK: Open Box. Multimedia and Human Computation approach
CUbRIK: Open Box. Multimedia and Human Computation approach
CUbRIK Project
 
ICT 2013: Better Society: empowering Horizon 2020 with trustable social media
ICT 2013: Better Society: empowering Horizon 2020 with trustable social mediaICT 2013: Better Society: empowering Horizon 2020 with trustable social media
ICT 2013: Better Society: empowering Horizon 2020 with trustable social media
CUbRIK Project
 
How Do We Deep-Link? Leveraging User-Contributed Time-Links for Non-Linear Vi...
How Do We Deep-Link? Leveraging User-Contributed Time-Links for Non-Linear Vi...How Do We Deep-Link? Leveraging User-Contributed Time-Links for Non-Linear Vi...
How Do We Deep-Link? Leveraging User-Contributed Time-Links for Non-Linear Vi...
CUbRIK Project
 
CUbRIK Research at CIKM 2012: Efficient Jaccard-based Diversity Analysis of L...
CUbRIK Research at CIKM 2012: Efficient Jaccard-based Diversity Analysis of L...CUbRIK Research at CIKM 2012: Efficient Jaccard-based Diversity Analysis of L...
CUbRIK Research at CIKM 2012: Efficient Jaccard-based Diversity Analysis of L...
CUbRIK Project
 
CUbRIK Tutorial at ICWE 2013: part 2 - Introduction to Games with a Purpose
CUbRIK Tutorial at ICWE 2013: part 2 - Introduction to Games with a PurposeCUbRIK Tutorial at ICWE 2013: part 2 - Introduction to Games with a Purpose
CUbRIK Tutorial at ICWE 2013: part 2 - Introduction to Games with a Purpose
CUbRIK Project
 
CUbRIK tutorial at ICWE 2013: part 1 Introduction to Human Computation
CUbRIK tutorial at ICWE 2013: part 1 Introduction to Human ComputationCUbRIK tutorial at ICWE 2013: part 1 Introduction to Human Computation
CUbRIK tutorial at ICWE 2013: part 1 Introduction to Human Computation
CUbRIK Project
 
Semantic schema for geonames
Semantic schema for geonamesSemantic schema for geonames
Semantic schema for geonames
CUbRIK Project
 
Exploiting User Generated Content for Mountain Peak Detection
Exploiting User Generated Content for Mountain Peak DetectionExploiting User Generated Content for Mountain Peak Detection
Exploiting User Generated Content for Mountain Peak Detection
CUbRIK Project
 
CUbRIK and History of Europe
CUbRIK and History of EuropeCUbRIK and History of Europe
CUbRIK and History of Europe
CUbRIK Project
 
Prof. Fraternali about Human computation
Prof. Fraternali about Human computationProf. Fraternali about Human computation
Prof. Fraternali about Human computation
CUbRIK Project
 
CUbRIK research presented at SSMS 2012
CUbRIK research presented at SSMS 2012CUbRIK research presented at SSMS 2012
CUbRIK research presented at SSMS 2012
CUbRIK Project
 
CUbRIK research at CIKM 2012: Pic Alert
CUbRIK research at CIKM 2012: Pic AlertCUbRIK research at CIKM 2012: Pic Alert
CUbRIK research at CIKM 2012: Pic Alert
CUbRIK Project
 
CUbRIK research at CIKM 2012: Map to Humans and Reduce Error
CUbRIK research at CIKM 2012: Map to Humans and Reduce ErrorCUbRIK research at CIKM 2012: Map to Humans and Reduce Error
CUbRIK research at CIKM 2012: Map to Humans and Reduce Error
CUbRIK Project
 
CUbRIK research at RecSys 2012
CUbRIK research at RecSys 2012CUbRIK research at RecSys 2012
CUbRIK research at RecSys 2012
CUbRIK Project
 

More from CUbRIK Project (20)

Building a social graph for the history of Europe: the CUbRIK histoGraph
Building a social graph for the history of Europe: the CUbRIK histoGraphBuilding a social graph for the history of Europe: the CUbRIK histoGraph
Building a social graph for the history of Europe: the CUbRIK histoGraph
 
The CUbRIK histoGraph Factsheet
The CUbRIK histoGraph FactsheetThe CUbRIK histoGraph Factsheet
The CUbRIK histoGraph Factsheet
 
CUbRIK Fashion Trend Analysis: a Business Intelligence Application
CUbRIK Fashion Trend Analysis: a Business Intelligence ApplicationCUbRIK Fashion Trend Analysis: a Business Intelligence Application
CUbRIK Fashion Trend Analysis: a Business Intelligence Application
 
CUbRIK Social Graph Visual Interface
CUbRIK Social Graph Visual InterfaceCUbRIK Social Graph Visual Interface
CUbRIK Social Graph Visual Interface
 
Mining Emotions in Short Films: User Comments or Crowdsourcing?
Mining Emotions in Short Films: User Comments or Crowdsourcing?Mining Emotions in Short Films: User Comments or Crowdsourcing?
Mining Emotions in Short Films: User Comments or Crowdsourcing?
 
CUbRIK and gaming experience@Qualinet
CUbRIK and gaming experience@QualinetCUbRIK and gaming experience@Qualinet
CUbRIK and gaming experience@Qualinet
 
CUbRIK: Open Box. Multimedia and Human Computation approach
CUbRIK: Open Box. Multimedia and Human Computation approachCUbRIK: Open Box. Multimedia and Human Computation approach
CUbRIK: Open Box. Multimedia and Human Computation approach
 
ICT 2013: Better Society: empowering Horizon 2020 with trustable social media
ICT 2013: Better Society: empowering Horizon 2020 with trustable social mediaICT 2013: Better Society: empowering Horizon 2020 with trustable social media
ICT 2013: Better Society: empowering Horizon 2020 with trustable social media
 
How Do We Deep-Link? Leveraging User-Contributed Time-Links for Non-Linear Vi...
How Do We Deep-Link? Leveraging User-Contributed Time-Links for Non-Linear Vi...How Do We Deep-Link? Leveraging User-Contributed Time-Links for Non-Linear Vi...
How Do We Deep-Link? Leveraging User-Contributed Time-Links for Non-Linear Vi...
 
CUbRIK Research at CIKM 2012: Efficient Jaccard-based Diversity Analysis of L...
CUbRIK Research at CIKM 2012: Efficient Jaccard-based Diversity Analysis of L...CUbRIK Research at CIKM 2012: Efficient Jaccard-based Diversity Analysis of L...
CUbRIK Research at CIKM 2012: Efficient Jaccard-based Diversity Analysis of L...
 
CUbRIK Tutorial at ICWE 2013: part 2 - Introduction to Games with a Purpose
CUbRIK Tutorial at ICWE 2013: part 2 - Introduction to Games with a PurposeCUbRIK Tutorial at ICWE 2013: part 2 - Introduction to Games with a Purpose
CUbRIK Tutorial at ICWE 2013: part 2 - Introduction to Games with a Purpose
 
CUbRIK tutorial at ICWE 2013: part 1 Introduction to Human Computation
CUbRIK tutorial at ICWE 2013: part 1 Introduction to Human ComputationCUbRIK tutorial at ICWE 2013: part 1 Introduction to Human Computation
CUbRIK tutorial at ICWE 2013: part 1 Introduction to Human Computation
 
Semantic schema for geonames
Semantic schema for geonamesSemantic schema for geonames
Semantic schema for geonames
 
Exploiting User Generated Content for Mountain Peak Detection
Exploiting User Generated Content for Mountain Peak DetectionExploiting User Generated Content for Mountain Peak Detection
Exploiting User Generated Content for Mountain Peak Detection
 
CUbRIK and History of Europe
CUbRIK and History of EuropeCUbRIK and History of Europe
CUbRIK and History of Europe
 
Prof. Fraternali about Human computation
Prof. Fraternali about Human computationProf. Fraternali about Human computation
Prof. Fraternali about Human computation
 
CUbRIK research presented at SSMS 2012
CUbRIK research presented at SSMS 2012CUbRIK research presented at SSMS 2012
CUbRIK research presented at SSMS 2012
 
CUbRIK research at CIKM 2012: Pic Alert
CUbRIK research at CIKM 2012: Pic AlertCUbRIK research at CIKM 2012: Pic Alert
CUbRIK research at CIKM 2012: Pic Alert
 
CUbRIK research at CIKM 2012: Map to Humans and Reduce Error
CUbRIK research at CIKM 2012: Map to Humans and Reduce ErrorCUbRIK research at CIKM 2012: Map to Humans and Reduce Error
CUbRIK research at CIKM 2012: Map to Humans and Reduce Error
 
CUbRIK research at RecSys 2012
CUbRIK research at RecSys 2012CUbRIK research at RecSys 2012
CUbRIK research at RecSys 2012
 

Recently uploaded

TrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
SOFTTECHHUB
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
Alpen-Adria-Universität
 
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
panagenda
 
Full-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalizationFull-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalization
Zilliz
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Paige Cruz
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
Neo4j
 
Removing Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software FuzzingRemoving Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software Fuzzing
Aftab Hussain
 
Mind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AIMind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AI
Kumud Singh
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
Octavian Nadolu
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Malak Abu Hammad
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
Tomaz Bratanic
 
Best 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERPBest 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERP
Pixlogix Infotech
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
Zilliz
 
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
SOFTTECHHUB
 
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
Speck&Tech
 
GenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizationsGenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizations
kumardaparthi1024
 
20240609 QFM020 Irresponsible AI Reading List May 2024
20240609 QFM020 Irresponsible AI Reading List May 202420240609 QFM020 Irresponsible AI Reading List May 2024
20240609 QFM020 Irresponsible AI Reading List May 2024
Matthew Sinclair
 
Microsoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdfMicrosoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdf
Uni Systems S.M.S.A.
 
UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6
DianaGray10
 

Recently uploaded (20)

TrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy Survey
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
 
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
 
Full-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalizationFull-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalization
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
 
Removing Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software FuzzingRemoving Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software Fuzzing
 
Mind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AIMind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AI
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
 
Best 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERPBest 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERP
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
 
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
 
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
 
GenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizationsGenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizations
 
20240609 QFM020 Irresponsible AI Reading List May 2024
20240609 QFM020 Irresponsible AI Reading List May 202420240609 QFM020 Irresponsible AI Reading List May 2024
20240609 QFM020 Irresponsible AI Reading List May 2024
 
Microsoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdfMicrosoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdf
 
UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6
 

RUCoD in CUbRIK at Star2013

  • 1. 1 Rich Unified Content Description (RUCoD) Vincenzo Croce Research & Development Laboratory STAR 2013 Lausanne, 18-19 January 2013
  • 2. Objectives 2  To develop a formal description for each type of multimedia content (text, audio, image, video and 3D content)  To develop formal descriptions for real world and social information  To clearly specify the format of the Rich Unified Content Description (RUCoD)  To represent in the same format, the actual content (multimedia information) along with the additional contextual information (real world, user-related) STAR 2013 Lausanne, 18-19 January 2013
  • 3. The Concept of Content 3 Object “A Content Object is the representation of a specific instance of either a physical object or a physical entity (an entity that has physical existence), which might have multiple views (many images, videos, audio files, text, real- world and user-related information).” Similar approaches:  Multimedia Document (MMD): a set of co-occurring multimedia objects (e.g. images, audio and text) that are of different modalities but carry the same semantics. If two multimedia objects are in the same MMD, they can be regarded as context of each other.  Multimedia Bag: defines a container including text instances, image instances and audio instances that share the shame semantic concepts STAR 2013 Lausanne, 18-19 January 2013
  • 4. The Concept of Content 4 Object  A CO may consist of several media types, user-related information and real-world information.  A CO can be the result of an authoring process (e.g. using an authoring tool).  RUCoD is a formal representation of a CO consisting of descriptions of various media types somehow associated to each other. STAR 2013 Lausanne, 18-19 January 2013
  • 5. Example Content Object 5 Great (Cheops) – 3D object Pyramid of Giza Image CO: Great (Cheops) – Pyramid of Giza Text: Real-world (location) It is believed the pyramid was built as a tomb for Fourth dynasty Egyptian pharaoh Khufu(or Cheops) and constructed over a 14 to 20 year period concluding STAR 2013 Lausanne, 18-19 January 2013 2560 BC… around
  • 6. RUCoD Specification 6 Real World Descriptors Position Weather Date Time (GPS, etc) (temperature) Sensors … Header CO ID Creator Version CO Types Multimedia RW-info U-Info … Header Low-Level Descriptors Real World User-related Descriptors Descriptors Low-Level Descriptors Text-based Image Video Audio 3D descriptors descriptors descriptors descriptors descriptors … User-related Descriptors Expressions Emotions Valence Arousal … STAR 2013 Lausanne, 18-19 January 2013
  • 7. RUCoD Structure 7 Header L_Descriptor: -“TextType” - “Object3D” - “ImageType” - “SoundType” - “VideoType” R_Descriptor: - “ContextType” Description U_Descriptor: - “Valence” - “Arousal” STAR 2013 Lausanne, 18-19 January 2013
  • 8. RUCoD Structure (Header) 8 <Header> <ContentObjectType>Physical Object</ContentObjectType> <ContentObjectName xml:lang="en-US">My Bulldog Barking</ContentObjectName> <ContentObjectID>3577B5EF-523F-4946-9734-C974CEA6C646</ContentObjectID> <ContentObjectVersion>1</ContentObjectVersion> <ContentObjectCreationInformation> <Creator> <Name>CERTH</Name></Creator> </ContentObjectCreationInformation> <ContentObjectTypes> <MultimediaContent type="Text"> <FreeText>It is the image, video and 3D representation… </FreeText> </MultimediaContent> <MultimediaContent type="Object3D"> <MediaName>Bulldog</MediaName> <FileFormat>x-world/x-vrml</FileFormat> <MediaLocator> <MediaUri>http://3d-test.iti.gr/dog.wrl</MediaUri> <MediaPreview>http://3d-test.iti.gr/dog.jpg</MediaPreview> </MediaLocator> </MultimediaContent> <MultimediaContent type="ImageType"> … </Header> STAR 2013 Lausanne, 18-19 January 2013
  • 9. RUCoD Structure (L-Descriptor) 9 <L_Descriptor type="Object3D"> <MediaName>BulldogLR</MediaName> <Shape3DDescription type="CMVD" matching="MultiViewL2"> <LowLevelDescriptor totalNumOfViews="18" totalNumOfDescriptors="212" descriptorType="xsd:float" descriptorSize="3816"> <Store type="Text"> <DescriptorLocator> <DescriptorUri>http://3d-test.iti.gr/CMVD.descr</DescriptorUri> </DescriptorLocator> </Store> </LowLevelDescriptor> </Shape3DDescription> </L_Descriptor> <L_Descriptor type="SoundType"> <MediaName>BulldogSound2</MediaName> <AudioDescription type="BarkBands" matching="BrayCurtis"> <LowLevelDescriptor totalNumOfDescriptors="216" descriptorType="xsd:float" descriptorSize="8 27"> <DescriptorValues> 2.31510340412e-12 3.04525744899e-11 2.56972665369e-10 6.54444409776e-09 2.40772557447e-09 2.14078905714e-08 … </DescriptorValues> </LowLevelDescriptor> </AudioDescription> </L_Descriptor> STAR 2013 Lausanne, 18-19 January 2013
  • 10. RUCoD Structure (R-Descriptor) 10 <R_Descriptor> <RealWorldDescription type="ContextType"> <ContextSlice> <Importance>1</Importance> <DateTime> <Date>1997-07-16T19:20:30.45+01:00</Date> <Length>100</Length> </DateTime> <SubjectPosition> <gml:CircleByCenterPoint numArc="1"> <gml:pos>45.8419444 13.4002778</gml:pos> <gml:radius uom="M">10</gml:radius> </gml:CircleByCenterPoint> </SubjectPosition> <Weather> <Condition>OVC RA</Condition> <Temperature>20</Temperature> <WindSpeed>2</WindSpeed> <Humidity>94</Humidity> </Weather> </ContextSlice> </RealWorldDescription> </R_Descriptor> STAR 2013 Lausanne, 18-19 January 2013
  • 11. RUCoD Structure (U-Descriptor) 11 <U_Descriptor type="UserType"> <MediaName>aerosmith-Aerosmith-01-Make_It.mp3</MediaName> <UserDescription matching="L2Distance" type="AvgValenceArousal"> <LowLevelDescriptor descriptorSize="1 1“ descriptorType="xsd:float" totalNumOfDescriptors="2"> <DescriptorValues>-0.4898 0.42857</DescriptorValues> </LowLevelDescriptor> </UserDescription> </U_Descriptor> STAR 2013 Lausanne, 18-19 January 2013
  • 12. RUCoD Schema 12 • RUCoD Schema Final Version (1.4.1) released in November 2011: • The RUCoD.xsd Schema file • The RUCoD_Descriptors.xsd Schema file http://www.isearch-project.eu/isearch/RUCoD/ STAR 2013 Lausanne, 18-19 January 2013
  • 13. Block diagram of the I-SEARCH framework 13 STAR 2013 Lausanne, 18-19 January 2013
  • 14. Authoring & Content Analytics 14 Architecture Authoring Content Analytics STAR 2013 Lausanne, 18-19 January 2013 Indexing triggering
  • 15. RUCoD in I-SEARCH Use 15 Cases Social retrieval UC2: UC3: Furniture retrieval of music •Text •Audio (music) •3D objects •Text •Images •Video clip •Real-world (location, time) UC1: Music retrieval •Real-world (location) •Audio (music) •Emotions •Text UC4: Search for Multimedia using smartphone •Images Rich •Text •Real-world Unified •3D objects (location, time) Content •Images •Emotions Description •Real-world (location, time) UC7: Game avatar retrieval •3D objects UC5: Search for specific •Images product •Text •Video UC6: 3D game component •3D objects •Emotions retrieval •Images •Text •Video •3D objects •Audio (sounds) •Images •Real-world (location, time) •Audio (sounds) •Emotions •Real-world STAR 2013 Lausanne, 18-19 January 2013 (location, time)
  • 16. Comparison with MPEG-7 16 What we use: • MediaLocator and MediaUri are used to describe the link to a specific media item. • Creator is used for description of the author of a media item. • Annotation as a part of RUCoD represents textual information of a media item or CO. • Image/Video/Audio Descriptors are used for the low-level descriptions of the separate media items within a CO. • Segment is used to describe a temporal video segment. STAR 2013 Lausanne, 18-19 January 2013
  • 17. Comparison with MPEG-7 17 What we adapted: • ContentObjectName, ContentObjectCreationInformation instead of name and CreationInformation to represent the name and creators of COs. • TextDescription, Shape3DDescription, ImageDescription and VideoDescription, similar to MPEG-7 ContentDescription to distinguish between the descriptors of different modalities inside the same RUCoD. STAR 2013 Lausanne, 18-19 January 2013
  • 18. Comparison with MPEG-7 18 What is new: • Cross-modal & multimodal retrieval are not entirely supported by the standards. • New types of information describing the COs are introduced, such as real- world descriptors and user-related descriptors. These enrich the CO description and improve the retrieval performance, by introducing new querying capabilities. • With respect to low-level descriptor extraction for media items, novel descriptors are introduced. As an example, for 3D content description, new state-of-the-art descriptors are introduced, which achieve higher retrieval performance than those included in MPEG-7. Similarly, new descriptors are introduced for image, video and audio content. • The low-level description of media items is also accompanied by specification of the matching scheme for each descriptor. In this case, the description scheme does not leave the responsibility for choosing the appropriate matching method to the search engine. STAR 2013 Lausanne, 18-19 January 2013
  • 19. Comparison with JPSearch What is similar/different: • JPSearch is designed in a way that decouples the components of image search and provides a standard interface between these components. Its aim is to build a standard for interoperability among image search and retrieval systems • RUCoD specification is focused on the description of COs and it addresses a broad range of media (apart from images), real-world and user-related information STAR 2013 Lausanne, 18-19 January 2013
  • 20. Comparison with MPEG-21 What we use: • A multimodal approach to media (which can be of any type) • Allowing the creation and attachment of rich metadata to digital objects STAR 2013 Lausanne, 18-19 January 2013
  • 21. Comparison with MPEG-21 What is similar: • Ability to create multimedia content objects (Digital Items in MPEG-21) • Ability for content adaptation, although achieved differently (e.g. through FileFormat elements in the RUCoD) • L-Descriptors and R-Descriptors of RUCoD could be attached to MPEG-21 objects although not directly foreseen by the standard STAR 2013 Lausanne, 18-19 January 2013
  • 22. Comparison with MPEG-21 What is different/new: • The CO broadens the concept of Digital Item making it more general and flexible • Unification of the actual metadata and descriptors (e.g. L- Descriptors) together with real world and user-related parts in the same format. • RUCoD is particularly targeted at indexing, sharing, search and retrieval • RUCoD overcomes the traditional hierarchical object model (also foreseen in MPEG-21) allowing for more flexible and user-centric 'connections' (e.g. RelatedSemanticConcepts field) STAR 2013 Lausanne, 18-19 January 2013
  • 23. Ongoing Work • RUCoD initially designed to serve the needs of the I- SEARCH framework • However, it is not mature enough to be used in a wider range of applications. • RUCoD will be extended within the EU-funded project CUbRIK (CERTH and ENG are participants). • RUCoD will be adopted in CUbRIK. • A first attempt: SMILA Hackathlon, November 2011, Keiserslautern. • RUCoD was presented in the workshop • RUCoD was used as descriptor scheme to check indexing and search within the SMILA engine STAR 2013 Lausanne, 18-19 January 2013
  • 24. 24 Questions? STAR 2013 Lausanne, 18-19 January 2013