Nam Le

Orcid: 0000-0002-0616-0158

Affiliations:
  • Idiap Research Institute, Martigny, Switzerland
  • École Polytechnique Fédérale de Lausanne, Switzerland
  • LIUM, University of Maine, Le Mans, France


According to our database1, Nam Le authored at least 10 papers between 2016 and 2019.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2019
Improving speech embedding using crossmodal transfer learning with audio-visual data.
Multim. Tools Appl., 2019

2018
Theoretical Guarantees of Deep Embedding Losses Under Label Noise.
CoRR, 2018

Robust and Discriminative Speaker Embedding via Intra-Class Distance Variance Regularization.
Proceedings of the Interspeech 2018, 2018

2017
A domain adaptation approach to improve speaker turn embedding using face representation.
Proceedings of the 19th ACM International Conference on Multimodal Interaction, 2017

Improving Speaker Turn Embedding by Crossmodal Transfer Learning from Face Embedding.
Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops, 2017


2016
EUMSSI Team at the MediaEval Person Discovery Challenge 2016.
Proceedings of the Working Notes Proceedings of the MediaEval 2016 Workshop, 2016

Temporally subsampled detection for accurate and efficient face tracking and diarization.
Proceedings of the 23rd International Conference on Pattern Recognition, 2016

Long-Term Time-Sensitive Costs for CRF-Based Tracking by Detection.
Proceedings of the Computer Vision - ECCV 2016 Workshops, 2016

The EUMSSI Project - Event Understanding through Multimodal Social Stream Interpretation.
Proceedings of the 1st International Workshop on Multimodal Media Data Analytics co-located with the 22nd European Conference on Artificial Intelligence, 2016


  Loading...