Hi! I'm Remi Cadene

I am studying Artificial Intelligence at the french University Pierre and Marie Curie (UPMC) in Paris. After a Master’s Degree on Big Data, Machine Learning and Knowledge Representation (DAC), I am currently doing a PhD in Deep Learning at LIP6 lab. In this frame, I am teaching bachelor and master students at UPMC and PolyTech as a Teaching Assistant.

Having graduated in Computer Science, I also studied Economics, Business and Financial Management at the University Sorbonne Abu Dhabi.

I am really excited about the upcoming academical, industrial and social challenges such as AI, a multi-disciplinary field, has to offer.

Ask for CV

Research

I am working on different subjects related to Machine Learning in the Computer Vision team supervised by my Professors Matthieu Cord et Nicolas Thome within the MLIA team. My PhD is funded by the SMART Labex (laboratory of excellence).

My primary research interests are in the fields of Machine Learning, Computer Vision and Natural Language Processing. I was working on Weakly-Supervised models to learn discriminative regions to perform robust image categorization. I am currently working on Multimodal models to learn joint embeddings of visual and textual data.

Recent publications

Cross-modal retrieval in the cooking context: Learning semantic text-image embeddings

R. Cadene*, M. Carvalho*, D. Picard, L. Soulier, N. Thome, M. Cord

SIGIR (2018)

Arxiv Code

@InProceedings{Carvalho_2018_SIGIR,
author = {Carvalho, Micael and Cadene, Remi and Picard, David and Soulier, Laure and Thome, Nicolas and Cord, Matthieu},
title = {Cross-modal retrieval in the cooking context: {L}earning semantic text-image embeddings},
booktitle = {The ACM Conference on Research and Development in Information Retrieval (SIGIR)},
year = {2017},
url = {https://arxiv.org/abs/1804.11146}
}

Images & Recipes: Retrieval in the cooking context

R. Cadene*, M. Carvalho*, D. Picard, L. Soulier, M. Cord

DECOR Workshop (ICDE) (2018)

Arxiv Slides Code

MUTAN: Multimodal Tucker Fusion for Visual Question Answering

R. Cadene*, H. Ben-Younes*, N. Thome, M. Cord

ICCV (2017)

Arxiv Slides Code

@InProceedings{Ben-younes_2017_ICCV,
author = {Ben-younes, Hedi and Cadene, Remi and Cord, Matthieu and Thome, Nicolas},
title = {{MUTAN}: {M}ultimodal {T}ucker {F}usion for {V}isual {Q}uestion {A}nswering},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017},
url = {http://arxiv.org/abs/1705.06676}
}

VQA Challenge Workshop: MUTAN 2.0

R. Cadene*, H. Ben-Younes*, N. Thome, M. Cord

VQA Workshop (CVPR) (2017)

Poster Code

Master's Thesis - Deep Learning for Visual Recognition

R. Cadene, N. Thome, M. Cord

(2016)

Arxiv Slides Code

@article{DBLP:journals/corr/CadeneTC16,
author = {R{\'{e}}mi Cad{\`{e}}ne and
Nicolas Thome and
Matthieu Cord},
title = {Master's Thesis : Deep Learning for Visual Recognition},
journal = {CoRR},
volume = {abs/1610.05567},
year = {2016},
url = {http://arxiv.org/abs/1610.05567},
timestamp = {Wed, 02 Nov 2016 09:51:26 +0100},
biburl = {http://dblp.uni-trier.de/rec/bib/journals/corr/CadeneTC16},
bibsource = {dblp computer science bibliography, http://dblp.org}
}

M2CAI Workflow Challenge: Convolutional Neural Networks for Video Frames Classification

R. Cadene, T. Robert, N. Thome, M. Cord

M2CAI Workshop (MICCAI) (2016)

Arxiv Poster Code

@article{DBLP:journals/corr/CadeneRTC16,
author = {R{\'{e}}mi Cad{\`{e}}ne and
Thomas Robert and
Nicolas Thome and
Matthieu Cord},
title = {{M2CAI} Workflow Challenge: Convolutional Neural Networks with Time
Smoothing and Hidden Markov Model for Video Frames Classification},
journal = {CoRR},
volume = {abs/1610.05541},
year = {2016},
url = {http://arxiv.org/abs/1610.05541},
timestamp = {Wed, 02 Nov 2016 09:51:26 +0100},
biburl = {http://dblp.uni-trier.de/rec/bib/journals/corr/CadeneRTC16},
bibsource = {dblp computer science bibliography, http://dblp.org}
}
* means equal contribution (order on paper decided with torch.rand(1) )

News, talks and awards

  • 16th july 2017: paper accepted at ICCV2017

  • 12-15th june 2017: participated to the UCA Deep Learning School as a speaker in the frame of Deep in France and the collaboration with Nvidia slides on RNNs slides on VQA

  • 6th june 2017: talked about AI and its impact on society at Nova Meetup

  • 30th may 2017: poster accepted at CVPR2017 (VQA workshop)

  • 6th february 2017: talked about the subject of my PhD for the scientific committe in the frame of Labex SMART slides poster

  • 3th november 2016: talked about convolutional neural networks and fine tuning at Heuritech for the paris deep learning meetup #7 blog post

  • 21th october 2016: ranked 2th (/5 research teams) at the M2CAI workflow competition, introduced a poster and talked about our solutions at the M2CAI workshop in Athens in the frame of the MICCAI 2016 conference workshop poster

  • 21th september 2016: interviewed for the RSNL blog of Microsoft blog post

  • 14th september 2016: talked about our winning solution for the data science game online competition at DojoCrea for the paris machine learning meetup #1S4 blog post video

  • 13th september 2016: appeared in the Challenges magazine blog post

  • 12th september 2016: appeared in a blog post of LesEchos START blog post

  • 15th october 2016: ranked 4th (/20 best teams) at the data science game final competition (1st french team) leaderboard

  • 26th july 2016: interviewed for the Zelros AI blog blog post

  • 10th july 2016: ranked 1th (/120 teams) at the data science game online competition leaderboard

  • 13th june 2016: received the precious (and prestigious) 3 years fundings for my PhD given by the SMART Labex (laboratory of excellence) slides

  • june 2016: received my master’s degree with the highest qualification of “very good”

Recent projects

Djlu

2016-today

DjLu (pronounce DéjàLu, with a French accent) is a simple and free tool to organize research papers.

Website Code

VISIIR

2013-2016

VIsual Seek for Interactive Image Retrieval (VISIIR) is a project aiming at exploring new methods for semantic image annotation. I designed and trained the convolutional neural networks behind the image classification engine.

Website & Demo Related publication

OpeningStage

2015

Social networks for artists and musicians. I built the back-end with CakePHP.

Website

Teaching

Java and Object-Oriented Programming

2016-2017 Semester 1 & 2

2I002 Course, L2 students

Course page

Neural Networks and Deep Learning for Pattern Recognition

2016-2017 Semester 1

RDFIA Course, M2 students

Course page

Practical Introduction to Deep Learning for Image Classification

2016-2017 Semester 1

Multimedia Course, Polytech M2 students

Course page