Summary of the paper
| Title | Video Retrieval in Sign Language Videos : How to Model and Compare Signs? |
|---|---|
| Authors | François Lefebvre-Albaret and Patrice Dalle |
| Abstract | This paper deals with the problem of finding sign occurrences in a signlanguage (SL) video. It begins with an analysis of sign models and the way theycan take into account the sign variability. Then, we review the most populartechnics dedicated to automatic sign language processing and we focus on theiradaptation to model sign variability. We present a new method to provide aparametric description of the sign as a set of continuous and discreteparameters. Signs are classified according to there categories (ballisticmovements, circles ...), the symmetry between the hand movements, hand absoluteand relative locations. Membership grades to sign categories and continuousparameter comparisons can be combined to estimate the similarity between twosigns. We set out our system and we evaluate how much time can be saved whenlooking for a sign in a french sign language video. By now, our formalism onlyuses hand 2D locations, we finally discuss about the way of integrating otherparameters as hand shape or facial expression in our framework. |
| Language | Multimedia Document Processing |
| Topics | Sign Language Recognition/Generation, Language modelling, Multimedia Document Processing |
Full paper  |
Video Retrieval in Sign Language Videos : How to Model and Compare Signs? |
| Bibtex | @InProceedings{LEFEBVREALBARET10.176, author = {François Lefebvre-Albaret and Patrice Dalle}, title = {Video Retrieval in Sign Language Videos : How to Model and Compare Signs?}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |