ontology for multimedia applications
play

Ontology for Multimedia Applications Hiranmay Ghosh TCS Innovation - PowerPoint PPT Presentation

Ontology for Multimedia Applications Hiranmay Ghosh TCS Innovation Labs, Delhi Contributors Santanu Chaudhury IIT Delhi Anupama Mallik IIT Delhi Hiranmay Ghosh TCS / IIT Delhi ... and many other students 2 November 19, 2013 Tutorial:


  1. Ontology for Multimedia Applications Hiranmay Ghosh TCS Innovation Labs, Delhi

  2. Contributors Santanu Chaudhury IIT Delhi Anupama Mallik IIT Delhi Hiranmay Ghosh TCS / IIT Delhi ... and many other students 2 November 19, 2013 Tutorial: Web Intelligence 2013

  3. Agenda Part I ● Introduction ● Semantic Web and Ontology ● Multimedia Content Processing ● Ontology for Multimedia Data Interpretation Part II ● Multimedia Web Ontology Language ● Application Examples ● Distributed Multimedia Applications ● Conclusion 3 November 19, 2013 Tutorial: Web Intelligence 2013

  4. Part I 4 November 19, 2013 Tutorial: Web Intelligence 2013

  5. Agenda Part I ● Introduction ● Semantic Web and Ontology ● Semantic Multimedia Content Processing ● Ontology for Multimedia Data Interpretation Part II ● Multimedia Web Ontology Language ● Application Examples ● Distributed Multimedia Applications ● Conclusion 5 November 19, 2013 Tutorial: Web Intelligence 2013

  6. Multimedia for infotainment 6 November 19, 2013 Tutorial: Web Intelligence 2013

  7. Some statistics [2012] Source: pingdom.com 7 November 19, 2013 Tutorial: Web Intelligence 2013

  8. How do we Deal effectively with the large volume of distributed multimedia data? Organize Retrieve Navigate Correlate 8 November 19, 2013 Tutorial: Web Intelligence 2013

  9. News aggregation ● TV Channels ● TV Channels ● Newspapers ● Newspapers ● Social Media ● Social Media ● Maps ● Maps ● Aggregate ● Aggregate ● Summarize ● Summarize ● Present ● Present ● Navigate ● Navigate ● Speech ● Speech ● Video ● Video ● Overlay Text ● Overlay Text ● Image ● Image ● Text ● Text 9 November 19, 2013 Tutorial: Web Intelligence 2013

  10. Digital Heritage ● Dance forms ● Dance forms ● Music genres ● Music genres ● Instruments ● Instruments ● Myth ● Myth ● Scripture ● Scripture ● Artistes ● Artistes ● Schools … ● Schools … ● Videos ● Videos ● Still images ● Still images ● Retrieve ● Retrieve ● Document images ● Document images ● Navigate ● Navigate ● Text ● Text 10 November 19, 2013 Tutorial: Web Intelligence 2013

  11. Agenda Part I ● Introduction ● Semantic Web and Ontology ● Multimedia Content Processing ● Ontology for Multimedia Data Interpretation Part II ● Multimedia Web Ontology Language ● Application Examples ● Distributed Multimedia Applications ● Conclusion 11 November 19, 2013 Tutorial: Web Intelligence 2013

  12. The Semantic Web ● Semantic data modeling – Concepts represented through symbols – Relations between the concepts ● Common reference for interpretation of data from multiple sources ● Layers for – Syntactic compatibility (XML) W3C Standards – Semantic interoperability (RDF, OWL) 12 November 19, 2013 Tutorial: Web Intelligence 2013

  13. Ontology ● A formal representation of a domain ● An artiste is a person ● A person has name [string] String ● A dancer is an artiste Has name ● A dancer performs dance ● DancerX is a dancer ● Bharatnatyam is a Dance Person ● DancerX performs Bharatnatyam ● DancerX has name “Yamini Krishnamurthy” Artiste Dance Dancer Performs Bharat- Natyam Performs DancerX “Yamini Krishnamurthy” Has name 13 November 19, 2013 Tutorial: Web Intelligence 2013

  14. Why use ontology? ● Template for information extraction <dancer><name><dance-type> ● Reasoning to find new facts (not explicitly stated) ● DancerX is a person ● DancerX performs Dance ● At least one dancer performs Bharatnatyam ● Separation of knowledge from program logic facilitates – Knowledge Engineering – Reuse and maintenance 14 November 19, 2013 Tutorial: Web Intelligence 2013

  15. Agenda Part I ● Introduction ● Semantic Web and Ontology ● Multimedia Content Processing ● Ontology for Multimedia Data Interpretation Part II ● Multimedia Web Ontology Language ● Application Examples ● Distributed Multimedia Applications ● Conclusion 15 November 19, 2013 Tutorial: Web Intelligence 2013

  16. Content, Concept & Context ● Content based retrieval (early 1990's) – Low level image features, e.g. Color & texture ● Concept based (late 1990's – still evolving) – Features conveying more semantics, e.g. SIFT Sky – Machine Learning techniques (Blue) ● Contextual reasoning ● Granularity of semantics Water (Blue) – Scene recognition – Object recognition A beach scene ● Generic & Specific Sand 16 November 19, 2013 Tutorial: Web Intelligence 2013 (Brown)

  17. Current state of content understanding ● Significant progress in visual data understanding – Document images, Surveillance, Medical / Satellite imagery, Scene understanding, Action recognition, ... ● Audio & Speech – Good progress ● Domain specific solutions – Implicit domain knowledge 17 November 19, 2013 Tutorial: Web Intelligence 2013

  18. Semantic gap: still an unsolved problem Semantic World J o y a n d f r e e d o m S T OP ! Bharatnatyam Red Light Bananas Semantic Gap Media World 18 November 19, 2013 Tutorial: Web Intelligence 2013

  19. Agenda Part I ● Introduction ● Semantic Web and Ontology ● Multimedia Content Processing ● Ontology for Multimedia Data Interpretation Part II ● Multimedia Web Ontology Language ● Application Examples ● Distributed Multimedia Applications ● Conclusion 19 November 19, 2013 Tutorial: Web Intelligence 2013

  20. Multimedia Data Integration ● Different Media types ● Diversity in descriptors ● Difference in indexing schemes Can we do semantic modeling of multimedia data? 20 November 19, 2013 Tutorial: Web Intelligence 2013

  21. Working with the annotations ● Multimedia data is often associated with annotation – Structured metadata, User tags, HTML <ALT> tag, surrounding text, ... ● We can use ontology to interpret them? ● A set of collaborating museums CIDOC: Early 2000's – Well-curated media archives – Controlled metadata associated with media artifacts ● OWL-based domain ontology for information integration ● Unfortunately, it does not work with any arbitrary media collection 21 November 19, 2013 Tutorial: Web Intelligence 2013

  22. Crowd-sourced data and knowledge (2008 onwards) ● Semantics extracted – From Crowd-sourced tags – With Crowd-sourced knowledge (Wikipedia) – A new line of research ● But ... – Estimated 70% of social media contents are without tags – Automatic tagging 22 November 19, 2013 Tutorial: Web Intelligence 2013

  23. “Qualities” of concepts Different Source: shades of red Gangemi (2002) “Qualities”: perceptible/measurable ● Physical (color, size …) – Relations (Spatial and temporal) – Relation between and quality regions (qualia) ● “Red” is opposite to “green” – “Red” is close to “brown” – 23 November 19, 2013 Tutorial: Web Intelligence 2013

  24. Multimedia Content Description Scheme ISO Standard: MPEG-7: Early 2000's ● Flexible language to describe multimedia contents – Representations (tools) for common audio and visual features ● Color, texture, shape, frequency spectrum, etc. – Scene description ● Structural and semantic description – Extensible ● Possible to define new descriptors 24 November 19, 2013 Tutorial: Web Intelligence 2013

  25. Description of still image 25 November 19, 2013 Tutorial: Web Intelligence 2013

  26. Video segments Video segments and regions 26 November 19, 2013 Tutorial: Web Intelligence 2013 Segment-Relationship Graph

  27. Comments on MPEG-7 ● Accomplishes syntactic interoperability for multimedia ● Describes multimedia document content – XML based schema – Lots of flexibility (same scene can be described in many different ways) – No semantics, no support for reasoning ● Quite a few MM Information system built with MPEG-7 – Template matching (query by example paradigm) – 27 November 19, 2013 Tutorial: Web Intelligence 2013

  28. Ontology for multimedia “concepts” IBM + CMU Mid 2000's ● Controlled vocabulary for MPEG-7 semantic description – Utility – Coverage – Feasibility – Observability Source: Naphade (2006) 28 November 19, 2013 Tutorial: Web Intelligence 2013

  29. MPEG-7 Ontologies Early-Mid 2000's ● To provide semantic rigor to MPEG-7 descriptors ● Several research projects – Harmony – AceMedia – DS-MIRF – COMM – Boemie – ... ● Converts MPEG-7 constructs to RDF / OWL constructs ● Different coverage to MPEG-7 parts 29 November 19, 2013 Tutorial: Web Intelligence 2013

  30. MPEG-7 Ontology: Class hierarchies Multimedia Multimedia Segment Contents Contents Still Video Moving Image Audio Video region segment region ... ... ... ... Video Image Mosaic Still Audio Video text text region segment segment Top level content entities Segment classes 30 November 19, 2013 Tutorial: Web Intelligence 2013

  31. MPEG-7 Ontology: Media Properties Still Vedio region segment Domain Visual Color subclass of Descriptor Range MPEG-7 Color Tools subclass of Color Scalable Dominant Layout Color Color 31 November 19, 2013 Tutorial: Web Intelligence 2013

Recommend


More recommend