Paper Info
Title
DCAR: A Discriminative and Compact Audio Representation to Improve Event Detection.
Abstract
This paper presents a novel two-phase method for audio representation, Discriminative and Compact Audio Representation (DCAR), and evaluates its performance at detecting events in consumer-produced videos. In the first phase of DCAR, each audio track is modeled using a Gaussian mixture model (GMM) that includes several components to capture the variability within that track. The second phase takes into account both global structure and local structure. In this phase, the components are rendered more discriminative and compact by formulating an optimization problem on Grassmannian manifolds, which we found represents the structure of audio effectively. Our experiments used the YLI-MED dataset (an open TRECVID-style video corpus based on YFCC100M), which includes ten events. The results show that the proposed DCAR representation consistently outperforms state-of-the-art audio representations. DCARu0027s advantage over i-vector, mv-vector, and GMM representations is significant for both easier and harder discrimination tasks. We discuss how these performance differences across easy and hard cases follow from how each type of model leverages (or doesnu0027t leverage) the intrinsic structure of the data. Furthermore, DCAR shows a particularly notable accuracy advantage on events where humans have more difficulty classifying the videos, i.e., events with lower mean annotator confidence.
Year
Venue
Field
2016
arXiv: Sound
Global structure,Pattern recognition,Computer science,Local structure,Speech recognition,Grassmannian,Artificial intelligence,Discriminative model,Optimization problem,Manifold,Machine learning,Mixture model
DocType
Volume
Citations 
Journal
abs/1607.04378
1
PageRank 
References 
Authors
0.38
11
7
Name
Order
Citations
PageRank
Liping Jing155047.13
Bo Liu252184.67
Jae-Young Choi3783110.19
Adam Janin425034.11
Julia Bernd5194.98
Michael W. Mahoney63297218.10
Gerald Friedland7112796.23