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.

Preview

Text
Action-Vectors_ Unsupervised movement modeling_for action recognition.pdf - Accepted Version
Download (440kB) | Preview

Abstract

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: