Action-vectors: Unsupervised movement modeling for action recognition

Roy, D and Kodukula, Sri Rama Murty and C, Krishna Mohan (2017) Action-vectors: Unsupervised movement modeling for action recognition. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP, 5-9 March 2017, Hilton New Orleans RiversideNew Orleans; United States.

Action-Vectors_ Unsupervised movement modeling_for action recognition.pdf - Accepted Version

Download (440kB) | Preview


Representation and modelling of movements play a significant role in recognising actions in unconstrained videos. However, explicit segmentation and labelling of movements are non-trivial because of the variability associated with actors, camera viewpoints, duration etc. Therefore, we propose to train a GMM with a large number of components termed as a universal movement model (UMM). This UMM is trained using motion boundary histograms (MBH) which capture the motion trajectories associated with the movements across all possible actions. For a particular action video, the MAP adapted mean vectors of the UMM are concatenated to form a fixed dimensional representation referred to as 'super movement vector' (SMV). However, SMV is still high dimensional and hence, Baum-Welch statistics extracted from the UMM are used to arrive at a compact representation for each action video, which we refer to as an 'action-vector'. It is shown that even without the use of class labels, action-vectors provide a more discriminatory representation of action classes translating to a 8 % relative improvement in classification accuracy for action-vectors based on MBH features over naïve MBH features on the UCF101 dataset. Furthermore, action-vectors projected with LDA achieve 93% accuracy on the UCF101 dataset which rivals state-of-the-art deep learning techniques.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Kodukula, Sri Rama Murty
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: action recognition; fixed-dimensional representation; unsupervised learning
Subjects: Computer science > Special computer methods
Electrical Engineering
Divisions: Department of Computer Science & Engineering
Department of Electrical Engineering
Depositing User: Team Library
Date Deposited: 08 Aug 2017 09:10
Last Modified: 15 Jun 2018 06:29
Publisher URL:
Related URLs:

    Actions (login required)

    View Item View Item
    Statistics for RAIITH ePrint 3470 Statistics for this ePrint Item