DCAR: A Discriminative and Compact Audio Representation to Improve Event Detection

TL;DR

This paper introduces DCAR, a novel two-phase audio representation method that enhances event detection in videos by making features more discriminative and compact, outperforming existing representations on a large dataset.

Contribution

The paper proposes a new two-phase approach for audio representation that combines GMM modeling with Grassmannian manifold optimization, improving event detection accuracy.

Findings

DCAR outperforms state-of-the-art audio representations.

Significant improvements in both easy and hard discrimination tasks.

Notable accuracy gains on events with lower human annotator confidence.

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. DCAR's 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 doesn't 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.