Action recognition based on efficient deep feature learning in the spatio-temporal domain

Hand-crafted feature functions are usually designed based on the domain knowledge of a presumably controlled environment and often fail to generalize, as the statistics of real-world data cannot always be modeled correctly. Data-driven feature learning methods, on the other hand, have emerged as an...

Descripción completa

Detalles Bibliográficos
Autores: Husain, Farzad, Dellen, Babette, Torras, Carme
Tipo de recurso: artículo
Estado:Versión enviada para evaluación y publicación
Fecha de publicación:2016
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/166274
Acceso en línea:http://hdl.handle.net/10261/166274
Access Level:acceso abierto
Palabra clave:Computer vision for automation
Visual learning
Recognition
Descripción
Sumario:Hand-crafted feature functions are usually designed based on the domain knowledge of a presumably controlled environment and often fail to generalize, as the statistics of real-world data cannot always be modeled correctly. Data-driven feature learning methods, on the other hand, have emerged as an alternative that often generalize better in uncontrolled environments. We present a simple, yet robust, 2-D convolutional neural network extended to a concatenated 3-D network that learns to extract features from the spatio-temporal domain of raw video data. The resulting network model is used for content-based recognition of videos. Relying on a 2-D convolutional neural network allows us to exploit a pretrained network as a descriptor that yielded the best results on the largest and challenging ILSVRC-2014 dataset. Experimental results on commonly used benchmarking video datasets demonstrate that our results are state-of-the-art in terms of accuracy and computational time without requiring any preprocessing (e.g., optic flow) or a priori knowledge on data capture (e.g., camera motion estimation), which makes it more general and flexible than other approaches. Our implementation is made available.