Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Cultural event recognition with visual ConvNets and temporal models

Autor
Salvador, A.; Manchon, D.; Calafell, A.; Giro, X.; Zeppelzauer, M.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
Challenge and Workshop on Pose Recovery, Action Recognition, and Cultural Event Recognition 2015
Any de l'edició
2015
Data de presentació
2015-06-12
Llibre d'actes
Proceedings of ChaLearn 2015: Challenge and Workshop on Pose Recovery, Action Recognition, and Cultural Event Recognition
Pàgina inicial
36
Pàgina final
44
Repositori
http://hdl.handle.net/2117/81947 Obrir en finestra nova
URL
http://www.cv-foundation.org/openaccess/CVPR2015_workshops/menu.py Obrir en finestra nova
Resum
This paper presents our contribution to the ChaLearn Challenge 2015 on Cultural Event Classification. The challenge in this task is to automatically classify images from 50 different cultural events. Our solution is based on the combination of visual features extracted from convolutional neural networks with temporal information using a hierarchical classifier scheme. We extract visual features from the last three fully connected layers of both CaffeNet (pretrained with ImageNet) and our fine tu...
Citació
Salvador, A., Manchon, D., Calafell, A., Giro, X., Zeppelzauer, M. Cultural event recognition with visual ConvNets and temporal models. A: Challenge and Workshop on Pose Recovery, Action Recognition, and Cultural Event Recognition. "Proceedings of ChaLearn 2015: Challenge and Workshop on Pose Recovery, Action Recognition, and Cultural Event Recognition". Boston: 2015, p. 36-44.
Grup de recerca
GPI - Grup de Processament d'Imatge i Vídeo

Participants