Scene Classification: Chum et al

Overview

Two algorithms are developed here: The first is based on hidden Markov models (HMMs) and Gaussian mixture models (GMMs). The features that were used include short time Fourier transform, loudness, and spectral sparsity. The second algorithm applies a support vector machine (SVM) on a frame-based level.

Homepage:

https://github.com/csdev/scene-classification-aasp-2013

Related publications

M. Chum, A. Habshush, A. Rahman, and C. Sang, “IEEE AASP scene classification challenge using hidden Markov models and frame based classification,” 2013.: [More Details] [BIBT_EX] [URL (ext.)]; @techreport{may2013a, author = {May Chum and Ariel Habshush and Abrar Rahman and Christopher Sang}, title = {IEEE AASP scene classification challenge using hidden Markov models and frame based classification}, year = {2013} }

Members

Manager: Dan Stowell, Emmanouil Benetos, Mark Plumbley

IEEE AASP D-CASE Challenge Code Submissions »

Overview

Homepage:

Related publications

Members