Using grammar induction to discover the structure of recurrent TV programs

Bingqing Qu 1, 2 Félicien Vallet 2 Jean Carrive 2 Guillaume Gravier 1
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Video structuring, in particular applied to TV programs which have strong editing structures, mostly relies on supervised approaches either to retrieve a known structure for which a model has been obtained or to detect key elements from which a known structure is inferred. In this paper, we propose an unsupervised approach to recurrent TV program structuring, exploiting the repetitiveness of key structural elements across episodes of the same show. We cast the problem of structure discovery as a grammatical inference problem and show that a suited symbolic representation can be obtained by filtering generic events based on their reoccurring property. The method follows three steps: i) generic event detection, ii) selection of events relevant to the structure and iii) grammatical inference from a symbolic representation. Experimental evaluation is performed on three types of shows, viz., game shows, news and magazines, demonstrating that grammatical inference can be used to discover the structure of recurrent programs with very limited supervision.
Document type :
Conference papers
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download
Contributor : Guillaume Gravier <>
Submitted on : Monday, July 21, 2014 - 1:50:31 PM
Last modification on : Friday, November 16, 2018 - 1:23:50 AM
Long-term archiving on : Monday, November 24, 2014 - 9:02:32 PM


Files produced by the author(s)


  • HAL Id : hal-01026331, version 1


Bingqing Qu, Félicien Vallet, Jean Carrive, Guillaume Gravier. Using grammar induction to discover the structure of recurrent TV programs. International Conferences on Advances in Multimedia, Feb 2014, Nice, France. pp.112-117. ⟨hal-01026331⟩



Record views


Files downloads