Nam Le - RankMe

Year	Rank	Type	Title / Venue / Authors
2019	J	`jnl`	Improving speech embedding using crossmodal transfer learning with audio-visual data. Multim. Tools Appl. Nam Le, Jean-Marc Odobez
2018	A	`conf`	Robust and Discriminative Speaker Embedding via Intra-Class Distance Variance Regularization. INTERSPEECH Nam Le, Jean-Marc Odobez
2018	J	`jnl`	Theoretical Guarantees of Deep Embedding Losses Under Label Noise. CoRR Nam Le, Jean-Marc Odobez
2017	B	`conf`	A domain adaptation approach to improve speaker turn embedding using face representation. ICMI Nam Le, Jean-Marc Odobez
2017	—	`conf`	Improving Speaker Turn Embedding by Crossmodal Transfer Learning from Face Embedding. ICCV Workshops Nam Le, Jean-Marc Odobez
2017	J	`jnl`	Improving speaker turn embedding by crossmodal transfer learning from face embedding. CoRR Nam Le, Jean-Marc Odobez
2017	C	`conf`	Towards large scale multimedia indexing: A case study on person discovery in broadcast news. CBMI Nam Le, Hervé Bredin, Gabriel Sargent, Miquel India, Paula Lopez-Otero, Claude Barras, Camille Guinaudeau, Guillaume Gravier, Gabriel Barbosa da Fonseca, Izabela Lyon Freire, Zenilton K. G. Patrocínio Jr., Silvio Jamil Ferzoli Guimarães, Gerard Martí, Josep Ramon Morros, Javier Hernando, Laura Docío Fernández, Carmen García-Mateo, Sylvain Meignier, Jean-Marc Odobez
2016	—	`conf`	EUMSSI Team at the MediaEval Person Discovery Challenge 2016. MediaEval Nam Le, Sylvain Meignier, Jean-Marc Odobez
2016	—	`conf`	Long-Term Time-Sensitive Costs for CRF-Based Tracking by Detection. ECCV Workshops (2) Nam Le, Alexandre Heili, Jean-Marc Odobez
2016	B	`conf`	Temporally subsampled detection for accurate and efficient face tracking and diarization. ICPR Nam Le, Alexandre Heili, Di Wu, Jean-Marc Odobez
2016	—	`conf`	The EUMSSI Project - Event Understanding through Multimodal Social Stream Interpretation. MMDA@ECAI Jens Grivolla, Yannick Estève, Eelco Herder, Nam Le, Kay Macquarrie, Raúl Marín, Sylvain Meignier, Maite Melero, Jean-Marc Odobez, Susanne Preuß

Year

Rank

Type

Title / Venue / Authors

2019

jnl

Improving speech embedding using crossmodal transfer learning with audio-visual data.

Multim. Tools Appl.

Nam Le, Jean-Marc Odobez

2018

conf

Robust and Discriminative Speaker Embedding via Intra-Class Distance Variance Regularization.

INTERSPEECH

Nam Le, Jean-Marc Odobez

2018

jnl

Theoretical Guarantees of Deep Embedding Losses Under Label Noise.

CoRR

Nam Le, Jean-Marc Odobez

2017

conf

A domain adaptation approach to improve speaker turn embedding using face representation.

ICMI

Nam Le, Jean-Marc Odobez

2017

—

conf

Improving Speaker Turn Embedding by Crossmodal Transfer Learning from Face Embedding.

ICCV Workshops

Nam Le, Jean-Marc Odobez

2017

jnl

Improving speaker turn embedding by crossmodal transfer learning from face embedding.

CoRR

Nam Le, Jean-Marc Odobez

2017

conf

Towards large scale multimedia indexing: A case study on person discovery in broadcast news.

CBMI

Nam Le, Hervé Bredin, Gabriel Sargent, Miquel India, Paula Lopez-Otero, Claude Barras, Camille Guinaudeau, Guillaume Gravier, Gabriel Barbosa da Fonseca, Izabela Lyon Freire, Zenilton K. G. Patrocínio Jr., Silvio Jamil Ferzoli Guimarães, Gerard Martí, Josep Ramon Morros, Javier Hernando, Laura Docío Fernández, Carmen García-Mateo, Sylvain Meignier, Jean-Marc Odobez

2016

—

conf

EUMSSI Team at the MediaEval Person Discovery Challenge 2016.

MediaEval

Nam Le, Sylvain Meignier, Jean-Marc Odobez

2016

—

conf

Long-Term Time-Sensitive Costs for CRF-Based Tracking by Detection.

ECCV Workshops (2)

Nam Le, Alexandre Heili, Jean-Marc Odobez