Procedural Generation of Videos to Train Deep Action Recognition Networks

Cesar Roberto de Souza, Adrien Gaidon, Yohann Cabon, Antonio Manuel Lopez

Producció científica: Contribució a una revistaArticleRecercaAvaluat per experts

83 Cites (Scopus)

Resum

Deep learning for human action recognition in videos is making significant progress, but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for "Procedural Human Action Videos". It contains a total of 39, 982 videos, with more than 1, 000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We introduce a deep multi-task representation learning architecture to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF101 and HMDB51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, significantly outperforming fine-tuning state-of-the-art unsupervised generative models of videos.
Idioma originalEnglish
Pàgines (de-a)2594-2604
Nombre de pàgines11
RevistaProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
Estat de la publicacióPublicada - 2017

Fingerprint

Navegar pels temes de recerca de 'Procedural Generation of Videos to Train Deep Action Recognition Networks'. Junts formen un fingerprint únic.

Com citar-ho