The INRIA-LIM-VocR and AXES submissions to Trecvid 2014 Multimedia Event Detection
Résumé
This paper describes our participation to the 2014 edition of the TrecVid Multimedia Event Detection task. Our system is based on a collection of local visual and audio descriptors, which are aggregated to global descriptors, one for each type of low-level descriptor, using Fisher vectors. Besides these features, we use two features based on convolutional networks: one for the visual channel, and one for the audio channel. Additional high-level featuresare extracted using ASR and OCR features. Finally, we used mid-level attribute features based on object and action detectors trained on external datasets. Our two submissions (INRIA-LIM-VocR and AXES) are identical interms of all the components, except for the ASR system that is used. We present an overview of the features andthe classification techniques, and experimentally evaluate our system on TrecVid MED 2011 data.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|