%0 Conference Proceedings
%T Seeing and Hearing Egocentric Actions: How Much Can We Learn?
%A Alejandro Cartas
%A Jordi Luque
%A Petia Radeva
%A Carlos Segura
%A Mariella Dimiccoli
%B IEEE International Conference on Computer Vision Workshops
%D 2019
%F Alejandro Cartas2019
%O MILAB; no proj
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3385), last updated on Tue, 31 Mar 2020 11:56:39 +0200
%X Our interaction with the world is an inherently multimodal experience. However, the understanding of human-to-object interactions has historically been addressed focusing on a single modality. In particular, a limited number of works have considered to integrate the visual and audio modalities for this purpose. In this work, we propose a multimodal approach for egocentric action recognition in a kitchen environment that relies on audio and visual information. Our model combines a sparse temporal sampling strategy with a late fusion of audio, spatial, and temporal streams. Experimental results on the EPIC-Kitchens dataset show that multimodal integration leads to better performance than unimodal approaches. In particular, we achieved a 5.18% improvement over the state of the art on verb classification.
%U https://ieeexplore.ieee.org/document/9022020
%U http://dx.doi.org/10.1109/ICCVW.2019.00548
%P 4470-4480