Paper Info
Title
A LDA-based method for automatic tagging of Youtube videos
Abstract
This article presents a method for automatic tagging of Youtube videos. The proposed method combines an automatic speech recognition (ASR) system, that extracts the spoken contents, and a keyword extraction component that aims at finding a small set of tags representing a video. In order to improve the robustness of the tagging system to the recognition errors, a video transcription is represented in a topic space obtained by a Latent Dirichlet Allocation (LDA), in which each dimension is automatically characterized by a list of weighted terms. Tags are extracted by combining the weighted word list of the best LDA classes. We evaluate this method by employing the user-provided tags of Youtube videos as reference and we investigate the impact of the topic model granularity. The obtained results demonstrate the interest of such model to improve the robustness of the tagging system.
Year
DOI
Venue
2013
10.1109/WIAMIS.2013.6616126
WIAMIS
Keywords
Field
DocType
weighted word list,lda based method,video signal processing,multimedia systems,speech recognition,weighted term,spoken content extraction,video transcription,keyword extraction,structuring multimedia collection,youtube video,recognition error,tagging system,automatic speech recognition system,audio categorization,social networking (online),video retrieval,latent dirichlet allocation,automatic tagging,robustness,speech,semantics,acoustics
Latent Dirichlet allocation,Pattern recognition,Video retrieval,Computer science,Keyword extraction,Speech recognition,Robustness (computer science),Artificial intelligence,Granularity,Topic model,Small set,Tag system
Conference
ISSN
Citations 
PageRank 
2158-5873
0
0.34
References 
Authors
6
2
Name
Order
Citations
PageRank
Mohamed Morchid18422.79
Georges Linares28719.73