Action recognition with deep neural networks

In this work, we have invesigated the action recognition problem using the Charades Action Recognition Dataset with 157 action classes. We have compared the results of different techniques such as extreme learning machines, support vector machines, and decision trees, applied on the features extracted with deep neural networks and the scene-action conditional probabilities.

[1]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[2]  Ali Farhadi,et al.  Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding , 2016, ECCV.

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  Lorenzo Torresani,et al.  Learning Spatiotemporal Features with 3D Convolutional Networks , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[5]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.

[6]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[7]  Mehrtash Tafazzoli Harandi,et al.  Going deeper into action recognition: A survey , 2016, Image Vis. Comput..

[8]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[9]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Ling Shao,et al.  From handcrafted to learned representations for human action recognition: A survey , 2016, Image Vis. Comput..