activity
20172020
most citedUnsupervised Temporal Feature Aggregation for Event Detection in Unstructured Sports Videos

4 citations · 12 across the 6 of their papers we have counts for

collaborators

9 papers

eess.AS2020

Learning Multiple Sound Source 2D Localization

Guillaume Le Moing, Phongtharin Vinayavekhin, Tadanobu Inoue +4

In this paper, we propose novel deep learning based algorithms for multiple sound source localization. Specifically, we aim to find the 2D Cartesian coordinates of multiple sound s…

eess.AS20201 cited

Ensemble of Discriminators for Domain Adaptation in Multiple Sound Source 2D Localization

Guillaume Le Moing, Don Joven Agravante, Tadanobu Inoue +4

This paper introduces an ensemble of discriminators that improves the accuracy of a domain adaptation technique for the localization of multiple sound sources. Recently, deep neura…

eess.AS20203 cited

Data-Efficient Framework for Real-world Multiple Sound Source 2D Localization

Guillaume Le Moing, Phongtharin Vinayavekhin, Don Joven Agravante +4

Deep neural networks have recently led to promising results for the task of multiple sound source localization. Yet, they require a lot of training data to cover a variety of acous…

cs.CV20204 cited

Unsupervised Temporal Feature Aggregation for Event Detection in Unstructured Sports Videos

Subhajit Chaudhury, Daiki Kimura, Phongtharin Vinayavekhin +7

Image-based sports analytics enable automatic retrieval of key events in a game to speed up the analytics process for human experts. However, most existing methods focus on structu…

cs.CV20193 cited

Unifying Heterogeneous Classifiers with Distillation

Jayakorn Vongkulbhisal, Phongtharin Vinayavekhin, Marco Visentini-Scarzanella

In this paper, we study the problem of unifying knowledge from a set of classifiers with different architectures and target classes into a single classifier, given only a generic s…

cs.RO2018

Deep Learning with Predictive Control for Human Motion Tracking

Don Joven Agravante, Giovanni De Magistris, Asim Munawar +2

We propose to combine model predictive control with deep learning for the task of accurate human motion tracking with a robot. We design the MPC to allow switching between the lear…