Human Action Recognition Based on Recognition of Linear Patterns in Action Bank Features Using Convolutional Neural Networks

Ijjina, E P and C, Krishna Mohan (2014) Human Action Recognition Based on Recognition of Linear Patterns in Action Bank Features Using Convolutional Neural Networks. In: 13th International Conference on Machine Learning and Applications (ICMLA), 3-6 December, 2014, Detroit, MI.

Full text not available from this repository. (Request a copy)

Abstract

In this paper, we proposed a deep convolutional network architecture for recognizing human actions in videos using action bank features. Action bank features computed against of a predefined set of videos known as an action bank, contain linear patterns representing the similarity of the video against the action bank videos. Due to the independence of the patterns across action bank features, a convolutional neural network with linear masks is considered to capture the local patterns associated with each action. The knowledge gained through training is used to assign an action label to videos during testing. Experiments conducted on UCF50 dataset demonstrates the effectiveness of the proposed approach in capturing and recognizing these linear local patterns.

[error in script]
IITH Creators:
IITH CreatorsORCiD
C, Krishna MohanUNSPECIFIED
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: action bank features; deep convolutional network; human action recognition
Subjects: Computer science > Computer programming, programs, data
Divisions: Department of Computer Science & Engineering
Depositing User: Team Library
Date Deposited: 30 Nov 2015 09:57
Last Modified: 01 Sep 2017 09:24
URI: http://raiithold.iith.ac.in/id/eprint/2044
Publisher URL: https://doi.org/10.1109/ICMLA.2014.33
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 2044 Statistics for this ePrint Item