1 / 27

Concept-based Image and Video Retrieval

Concept-based Image and Video Retrieval. Wei-Chen Chiu Vision Lab, NCTU 20090511. Why concept-based Retrieval? – User Expectation. Need of Image/Video Search

Download Presentation

Concept-based Image and Video Retrieval

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Concept-based Image and Video Retrieval Wei-Chen Chiu Vision Lab, NCTU 20090511

  2. Why concept-based Retrieval? – User Expectation • Need of Image/Video Search • “[User expects to] type in a few words at most. Then expect the engine to bring back the perfect results. More than 95 percent of us never use the advanced search features most engines include,…” - The Search. J. Battelle, 2003 • Keyword query is the primary search method.

  3. Why concept-based Retrieval? – Limitation for Content-Based Retrieval • Content-based retrieval: query-by-example • Difficult to find appropriate query examples as initial queries. • Difficult to get detailed visual descriptions • Difficult to get user feedback for refined search • Less efficient than text retrieval

  4. Content-based retrieval: example

  5. From Content-Based Retrieval to Concept-Based Retrieval

  6. Concept-Based Retrieval – For Image • For Image - One picture is worth one thousand words- Images → bag of “words” or “semantic concepts”- Retrieve images by matching queries and semantic concepts

  7. Concept-Based Retrieval – For Video • Semantic concepts can be extracted from video with more information- Multimedia content, e.g., audio, text and visual, are available- Temporal relation between video shots People: Kofi Annan Scene: Studio Event: Un Meeting Object: Tank, Jet … …

  8. What are (Multimedia)Semantic Concepts? • An intermediate layer of multimedia descriptors that aim to bridge the gap between user information need and low-level multimedia content. • Wide coverage- People (face, tourists, …)- Objects (building, animals, …) - Locations (indoor, studio, …)- Events (meeting, trip, …) - Genres (weather, sports, …)- …

  9. Why is Concept-based Retrieval Important? • Growing multimedia content • Semantics need from users- Increasing expectation of accessibility and search-ability of media content

  10. Three Main Issues for Concept-Based Retrieval

  11. Concept Vocabulary Design • Concept Vocabulary != Text Vocabulary • Dimensions in evaluating/design concept vocabulary:- Detectability: observed from data (not abstract like “happy”)- Utility: useful for retrieval, categorization or others- Generality: sufficiently frequent across data- Specificity: not too frequent (exist in most of data)- Clarity: no definition ambiguity- Domains: application/adaptable to multiple data domains

  12. Example: Standardized Concept Lexicon in LTRECVID A. Program CategoryB. Setting/Scene/SiteC. PeopleD. ObjectsE. ActivitiesF. EventsG. Graphics

  13. Example: MediaMill Challenge Sample Images from MediaMill-101 Lexicon

  14. Example: Large Scale Concept Ontology for Multimedia Understanding (LSCOM) Up to 449 Concepts!

  15. Three Main Issues for Concept-Based Retrieval

  16. Semantic Concept Extraction – Manual • Tagging (Widely used) • Browsing (specific domains)- Associate multiple image/video with single keyword

  17. Limitations of Manual Approaches • Time consuming and labor intensive- Tagging: 5-6 seconds per keyword- Browsing: 1.5 seconds per relevant keyword, 0.2 per irrelevant • Subjective and inaccurate for social tagging

  18. Semantic Concept Extraction – Automatic Concept Detection • Typical approaches for large scale of semantic concept (for images)- feature extraction, model learning, fusion

  19. Semantic Concept Extraction – Multi-Concept Relational Modeling • Semantic concept are not isolated, e.g., “car”&”road”- feature extraction, model learning, fusion • Jointly model the relationship across multiple concepts- Ontology-based learning [Wu et al., ICME’04]- Prob. Graphical models [Yan et al., ICME’06]- Graph-based learning [Qi et al., MM’07]- Boosted conditional fields [Jiang et al., ICASSP’07]

  20. Semantic Concept Extraction – Spatial-Temporal Context Modeling • Temporal context: constraints based on temporal relationship (e.g. for events)- Model the evolution of concept in time, e.g., “airplane landing”: sky → grass → runway • Spatial context: constraints based on spatial relationship (e.g. for images)- Assume closer image blocks share more similar concepts • Common modeling choices: probabilistic graphical models- Basic: HMM, MRF, CRF- Advance: Hier-HMM, 2D-HMM…

  21. Semantic Concept Extraction – Many other methods… • Include:- Active Learning- Cross-Domain Adaption/Transfer Learning- Semi-Supervised Learning- Learning with Side Information- …. • Still a challenging research problem!

  22. Example: IBM Multimedia Analysis and Retrieval System (iMARS)

  23. Example: IBM Multimedia Analysis and Retrieval System (iMARS)

  24. Three Main Issues for Concept-Based Retrieval

  25. Retrieval by Semantic Concepts • Match text queries with a fixed set of semantic concepts

  26. MediaMill System

  27. Columbia Video Search System

More Related