2019

DualDis: Dual-Branch Disentangling with Adversarial Learning

Thomas Robert, Nicolas Thome, Matthieu Cord

Preprint. Under review at Advances in Neural Information Processing Systems (NIPS) (2019)

Paper

Exploiting Negative Evidence for Deep Latent Structured Models

Thibaut Durand, Nicolas Thome, Matthieu Cord

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2019)

Paper

2018

Probabilistic Video Generation using Holistic Attribute Control

J. He and A. Lehrmann and J. Marino and G. Mori and L. Sigal

European Conference on Computer Vision (ECCV) (2018)

Human Activity Recognition by attending to RGB frames from deep pose features

F. Baradel and C. Wolf and J. Mille

BMVC (2018)

Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points

F. Baradel and C. Wolf and J. Mille and G.W. Taylor

CVPR (2018)

Learning to recognize touch gestures: recurrent vs. convolutional features and dynamic sampling

Q. Debard and C. Wolf and S. Canu and J. Arne

Automatic Face and Gesture Recognition (FG) (2018)

CLIP-Q: Deep network compression learning by in-parallel pruning-quantization

F. Tung and G. Mori

IEEE Computer Vision and Pattern Recognition (CVPR) (2018)

Hierarchical Relational Networks for Group Activity Recognition and Retrieval

M. Ibrahim and G. Mori

European Conference on Computer Vision (ECCV) (2018)

Constraints Matter in Deep Neural Network Compression

C. Chen and F. Tung and N. Vedula and and G. Mori

European Conference on Computer Vision (ECCV) (2018)

Object Level Visual Reasoning in Videos

Fabien Baradel, Natalia Neverova, Christian Wolf, Julien Mille Greg Mori

IEEE European Conference on Computer Vision (ECCV) (2018)

Papier Project page Code Poster

@InProceedings{Baradel_2018_ECCV,
author = {Baradel, Fabien and Neverova, Natalia and Wolf, Christian and Mille, Julien and Mori, Greg},
title = {Object Level Visual Reasoning in Videos},
booktitle = {ECCV},
month = {June},
year = {2018}
}

SHADE: Information-Based Regularization for Deep Learning

Michael Blot, Thomas Robert, Nicolas Thome, Matthieu Cord

IEEE International Conference on Image Processing (ICIP) (2018)

Paper

HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning

Thomas Robert, Nicolas Thome, Matthieu Cord

IEEE European Conference on Computer Vision (ECCV) (2018)

Paper

Stochastic Layer-Wise Precision in Deep Neural Networks

G. Lacey and G.W. Taylor and S. Areibi

Uncertainty in Artificial Intelligence (UAI) (2018)

Real-Time End-to-End Action Detection with Two-Stream Networks

A. El-Nouby and G.W. Taylor

Conference on Computer and Robot Vision (CRV) (2018)

Generalized Hadamard-Product Fusion Operators for Visual Question Answering

B. Duke and G.W. Taylor

Conference on Computer and Robot Vision (CRV) (2018)

Convolutional Neural Networks Regularized by Correlated Noise

S. Dutta and B. Tripp and G.W.Taylor

Conference on Computer and Robot Vision (CRV) (2018)

Attacking Binarized Neural Networks

A. Galloway and G.W. Taylor and M. Moussa

International Conference on Learning Representations (ICLR) (2018)

Understanding Anatomy Classification through Attentive Response Maps

D. Kumar and V. Menkovski and G. W. Taylor and A. Wong

International Symposium on Biomedical Imaging (2018)

Distributed optimization for deep learning with gossip exchange

Michael Blot, David Picard, Matthieu Cord, Nicolas Thome

Neurocomputing (2018)

Paper

SyMIL: MinMax Latent SVM for Weakly Labeled Data

Thibaut Durand, Nicolas Thome, Matthieu Cord

IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (2018)

Paper

End-to-End Learning of Latent Deformable Part-Based Representations for Object Detection

Taylor Mordan, Nicolas Thome, Gilles Henaff, Matthieu Cord

International Journal of Computer Vision (IJCV) (2018)

Paper

Bayesian optimization on graph-structured search spaces: Optimizing deep multimodal fusion architectures

D. Ramachandram and M. Lisicki and T. J. Shields and M. R. Amera and G. Taylor

Neurocomputing (2018)

2017

Attending to Distinctive Moments: Weakly-supervised Attention Models for Action Localization in Video

L. Chen and M. Zhai and G. Mori

5th Workshop on Web-scale Vision and Social Media (at ICCV) (2017)

Pose-conditioned Spatio-Temporal Attention for Human Action Recognition

Fabien Baradel, Christian Wolf, Julien Mille

ArXiv (2017)

Paper Video and details

Deformable Part-based Fully Convolutional Network for Object Detection

Taylor Mordan, Nicolas Thome, Matthieu Cord, Gilles Henaff

British Machine Vision Conference (BMVC) (2017)

Paper

Modout: Learning to Fuse Face and Gesture Modalities with Stochastic Regularization

F. Li and N. Neverova and C. Wolf and G.W. Taylor

FG (2017)

Hand Pose Estimation through Weakly-Supervised Learning of a Rich Intermediate Representation

N. Neverova and C. Wolf and G.W. Taylor and F. Nebout

Computer Vision and Image Understanding (2017)

Interactive Example-Based Terrain Authoring with Conditional Generative Adversarial Networks

E. Guerin and E. Galin and J. Digne and A. Peytavie and C. Wolf and B. Benes and B. Martinez

Transactions on Graphics (proceedings of ACM Siggraph Asia) (2017)

Discovery Radiomics with CLEAR-DR: Interpretable Computer Aided Diagnosis of Diabetic Retinopathy

D. Kumar and G.W. Taylor and A. Wong

Neural Information Processing Systems (NIPS) Workshop on Transparent and Interpretable Machine Learning in Safety Critical Environments (2017) Best paper award

Human Action Recognition: Pose-based Attention draws focus to Hands

F. Baradel and C. Wolf and J. Mille

ICCV Workshop on Hands in Action (2017)

2016

Gossip training for deep learning

Michael Blot, David Picard, Matthieu Cord, Nicolas Thome

Advances in Neural Information Processing Systems (NIPS) Workshop (2016)

Paper