People

Piotr Bojanowski

Postdoctoral Researcher

I am a Post Doctoral Researcher at Facebook AI Research. Before Facebook, I worked on my PhD on Willow team at INRIA Paris and was supervised by Jean Ponce, Cordelia Schmid, Ivan Laptev and Josef Sivic. I graduated from Ecole polytechnique in 2013 and received a Masters Degree in Mathematics, Machine Learning and Computer Vision (MVA). My work focuses on automatic video understanding and related learning problems. More recently, I also started working on sequence modeling and recurrent networks, with applications to language modeling.

Interests

Computer vision, and machine learning

Latest Publications

Unsupervised Pre-Training of Image Features on Non-Curated Data

Mathilde Caron, Piotr Bojanowski, Julien Mairal, Armand Joulin

ICCV - October 28, 2019

Training Hybrid Language Models by Marginalizing over Segmentations

Edouard Grave, Sainbayar Sukhbaatar, Piotr Bojanowski, Armand Joulin

ACL - July 28, 2019

Adaptive Attention Span in Transformers

Sainbayar Sukhbaatar, Edouard Grave, Piotr Bojanowski, Armand Joulin

ACL - July 27, 2019

Learning Word Vectors for 157 Languages

Edouard Grave, Piotr Bojanowski, Prakhar Gupta, Armand Joulin, Tomas Mikolov

LREC - April 30, 2019

Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion

Armand Joulin, Piotr Bojanowski, Tomas Mikolov, Hervé Jégou, Edouard Grave

EMNLP 2018 - October 30, 2018

Deep Clustering for Unsupervised Learning of Visual Features

Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze

ECCV 2018 - September 9, 2018

Optimizing the Latent Space of Generative Networks

Piotr Bojanowski, Armand Joulin, David Lopez-Paz, Arthur Szlam

ICML 2018 - July 10, 2018

Colorless Green Recurrent Networks Dream Hierarchically

Kristina Gulordava, Piotr Bojanowski, Edouard Grave, Tal Linzen, Marco Baroni

NAACL 2018 - June 1, 2018

Advances in Pre-Training Distributed Word Representations

Tomas Mikolov, Edouard Grave, Piotr Bojanowski, Christian Puhrsch, Armand Joulin

LREC 2018 - May 7, 2018

Unsupervised Learning by Predicting Noise

Piotr Bojanowski, Armand Joulin

ICML 2017 - August 6, 2017

Enriching Word Vectors with Subword Information

Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov

TACL - July 31, 2017

Bag of Tricks for Efficient Text Classification

Armand Joulin, Edouard Grave, Piotr Bojanowski, Tomas Mikolov

EACL 2017 - April 3, 2017

Alternative Structures for Character-Level RNNs

Piotr Bojanowski, Armand Joulin, Tomas Mikolov

ArXiv - November 19, 2015