Time-Sensitive Topic Models for Action Recognition in Videos - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Time-Sensitive Topic Models for Action Recognition in Videos

Romain Tavenard
Rémi Emonet

Résumé

In this paper, we postulate that temporal information is important for action recognition in videos. Keeping temporal information, videos are represented as word time documents. We propose to use time-sensitive probabilistic topic models and we extend them for the context of supervised learning. Our time-sensitive approach is compared to both PLSA and Bag-of-Words. Our approach is shown to both capture semantics from data and yield classification performance comparable to other methods, outperforming them when the amount of training data is low.
Fichier principal
Vignette du fichier
hal-00872048.pdf (602.24 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00872048 , version 1 (21-02-2017)

Identifiants

  • HAL Id : hal-00872048 , version 1

Citer

Romain Tavenard, Rémi Emonet, Jean-Marc Odobez. Time-Sensitive Topic Models for Action Recognition in Videos. ICIP - International Conference on Image Processing, Sep 2013, Melbourne, Australia. ⟨hal-00872048⟩
75 Consultations
115 Téléchargements

Partager

Gmail Facebook X LinkedIn More