Technical Gestures Recognition by Set-Valued Hidden Markov Models with Prior Knowledge - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Technical Gestures Recognition by Set-Valued Hidden Markov Models with Prior Knowledge

Résumé

Hidden Markov models are popular tools for gesture recognition. Once the generative processes of gestures have been identified, an observation sequence is usually classified as the gesture having the highest likelihood, thus ignoring possible prior information. In this paper, we consider two potential improvements of such methods: the inclusion of prior information, and the possibility of considering convex sets of probabilities (in the likelihoods and the prior) to infer imprecise, but more reliable, predictions when information is insufficient. We apply the proposed approach to technical gestures, typically characterized by severe class imbalance. By modelling such imbalances as a prior information, we achieve more accurate results, while the imprecise quantification is shown to produce more reliable estimates.
Fichier non déposé

Dates et versions

hal-01380411 , version 1 (13-10-2016)

Identifiants

Citer

Yann Soullard, Alessandro Antonucci, Sébastien Destercke. Technical Gestures Recognition by Set-Valued Hidden Markov Models with Prior Knowledge. Soft Methods in Probability and Statistics (SMPS 2016), Maria Brigida Ferraro, Paolo Giordani, Barbara Vantaggi, Sep 2016, Rome, Italy. pp.455--462, ⟨10.1007/978-3-319-42972-4_56⟩. ⟨hal-01380411⟩
69 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More