• Publications
  • Influence
TensorLy: Tensor Learning in Python
TLDR
We have developed TensorLy, a Python library that provides a high-level API for tensor methods and deep tensorized neural networks. Expand
Non-Negative Multilinear Principal Component Analysis of Auditory Temporal Modulations for Music Genre Classification
TLDR
Non-negative multilinear principal component analysis (NMPCA) is proposed for the unsupervised dimensionality reduction of the third-order tensors. Expand
Music Genre Classification Using Locality Preserving Non-Negative Tensor Factorization and Sparse Representations
TLDR
A robust music genre classification framework is proposed that combines the rich, psycho-physiologically grounded properties of auditory cortical representations of music recordings and the power of sparse representation-based classifiers. Expand
SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild
TLDR
We introduce the SEWA database of more than 2,000 minutes of audio-visual data of 398 people coming from six cultures, 50 percent female, and uniformly spanning the age range of 18 to 65 years old. Expand
Music genre classification via sparse representations of auditory temporal modulations
TLDR
A robust music genre classification framework is proposed that combines the rich, psycho-physiologically grounded properties of slow temporal modulations of music recordings and the power of sparse representation-based classifiers. Expand
3D Face Morphable Models "In-the-Wild"
TLDR
In this paper, we propose the first, to the best of our knowledge, in- the-wild 3DMM by combining a powerful statistical model of facial shape, which describes both identity and expression, with an in-the-wild texture model. Expand
Music genre classification via Topology Preserving Non-Negative Tensor Factorization and sparse representations
TLDR
We propose a robust music genre classification framework that reduces the dimensionality of cortical representations of music signals, while preserving the topology of the cortical representations. Expand
Music Genre Classification via Joint Sparse Low-Rank Representation of Audio Features
TLDR
A novel framework for music genre classification, namely the joint sparse low-rank representation (JSLRR) is proposed in order to smooth the noise in the test samples, and a novel classifier is developed, which is referred to as the JSLRR-based classifier. Expand
Elastic Net subspace clustering applied to pop/rock music structure analysis
TLDR
A novel homogeneity-based method for music structure analysis is proposed. Expand
Robust Canonical Correlation Analysis: Audio-visual fusion for learning continuous interest
TLDR
We propose a robust variant of Canonical Correlation Analysis (RCCA) for performing audio-visual fusion, which we apply to the prediction of interest. Expand
...
1
2
3
4
5
...