Dictionary based action video classification with action bank

Wilson, S and Mettu, Srinivas and C, Krishna Mohan (2014) Dictionary based action video classification with action bank. In: 19th International Conference on Digital Singal Processing, 20-23 August, 2014, Hong Kong.

manuscript.pdf - Accepted Version

Download (167kB) | Preview


Classifying action videos became challenging problem in computer vision community. In this work, action videos are represented by dictionaries which are learned by online dictionary learning (ODL). Here, we have used two simple measures to classify action videos, reconstruction error and projection. Sparse approximation algorithm LASSO is used to reconstruct test video and reconstruction error is calculated for each of the dictionaries. To get another discriminative measure projection, the test vector is projected onto the atoms in the dictionary. Minimum reconstruction error and maximum projection give information regarding the action category of the test vector. With action bank as a feature vector, our best performance is 59.3% on UCF50 (benchmark is 57.9%), 97.7% on KTH (benchmark is 98.2%)and 23.63% on HMDB51 (benchmark is 26.9%).

[error in script]
IITH Creators:
IITH CreatorsORCiD
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Dictionary learning; Reconstruction error; Action videos
Subjects: Computer science > Big Data Analytics
Divisions: Department of Computer Science & Engineering
Depositing User: Team Library
Date Deposited: 22 Jun 2015 07:23
Last Modified: 01 Sep 2017 09:22
URI: http://raiith.iith.ac.in/id/eprint/1587
Publisher URL: https://doi.org/10.1109/ICDSP.2014.6900734
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 1587 Statistics for this ePrint Item