Your browser doesn't support javascript.
loading
Montrer: 20 | 50 | 100
Résultats 1 - 1 de 1
Filtrer
Plus de filtres










Base de données
Gamme d'année
1.
Neural Netw ; 105: 356-370, 2018 Sep.
Article de Anglais | MEDLINE | ID: mdl-29936360

RÉSUMÉ

Video image recognition has been extensively studied with rapid progress recently. However, most methods focus on short-term rather than long-term (contextual) video recognition. Convolutional recurrent neural networks (ConvRNNs) provide robust spatio-temporal information processing capabilities for contextual video recognition, but require extensive computation that slows down training. Inspired by normalization and detrending methods, in this paper we propose "adaptive detrending" (AD) for temporal normalization in order to accelerate the training of ConvRNNs, especially of convolutional gated recurrent unit (ConvGRU). For each neuron in a recurrent neural network (RNN), AD identifies the trending change within a sequence and subtracts it, removing the internal covariate shift. In experiments testing for contextual video recognition with ConvGRU, results show that (1) ConvGRU clearly outperforms feed-forward neural networks, (2) AD consistently and significantly accelerates training and improves generalization, (3) performance is further improved when AD is coupled with other normalization methods, and most importantly, (4) the more long-term contextual information is required, the more AD outperforms existing methods.


Sujet(s)
Apprentissage machine , Reconnaissance automatique des formes/méthodes , , Reconnaissance automatique des formes/normes , Enregistrement sur magnétoscope/méthodes
SÉLECTION CITATIONS
DÉTAIL DE RECHERCHE
...