Jakob Verbeek

Publications
Influence

Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning

Ramazan Gokberk Cinbis, Jakob Verbeek, C. Schmid
Computer Science, Medicine
IEEE Transactions on Pattern Analysis and Machine…
3 March 2015

We propose a weakly supervised learning method to learn object detectors from image-wide labels, which improves the localization accuracy by incorporating an objectness prior. Expand

Semantic Segmentation using Adversarial Networks

Pauline Luc, C. Couprie, Soumith Chintala, Jakob Verbeek
Computer Science
NIPS
25 November 2016

We present, to the best of our knowledge, the first application of adversarial training to semantic segmentation. Expand

FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis

Nitika Verma, E. Boyer, Jakob Verbeek
Computer Science
IEEE/CVF Conference on Computer Vision and…
16 June 2017

We propose a novel graph-convolution operator to establish correspondences between filter weights and graph neighborhoods with arbitrary connectivity. Expand

Heterogeneous Face Recognition with CNNs

Shreyas Saxena, Jakob Verbeek
Computer Science
ECCV Workshops
8 October 2016

Heterogeneous face recognition aims to recognize faces across different sensor modalities. Expand

Predicting Future Instance Segmentations by Forecasting Convolutional Features

Pauline Luc, C. Couprie, Y. LeCun, Jakob Verbeek
Computer Science
ECCV
30 March 2018

We develop a predictive model in the space of fixed-sized convolutional features of the Mask R-CNN instance segmentation model. Expand

Convolutional Neural Fabrics

Shreyas Saxena, Jakob Verbeek
Computer Science
NIPS
8 June 2016

We propose a "fabric" that embeds an exponentially large number of architectures. Expand

The LEAR submission at Thumos 2014

Dan Oneata, Jakob Verbeek, C. Schmid
Computer Science
2014

We describe the submission of the INRIA LEAR team to the THU-MOS workshop in conjunction with ECCV 2014. Expand

Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction

Maha Elbayad, L. Besacier, Jakob Verbeek
Computer Science
CoNLL
11 August 2018

We propose an alternative neural MT architecture which instead relies on a single 2D convolutional neural network across both sequences, while being conceptually simpler and having fewer parameters. Expand

Scene Coordinate Regression with Angle-Based Reprojection Loss for Camera Relocalization

X. Li, Juha Ylioinas, Jakob Verbeek, Juho Kannala
Computer Science
ECCV Workshops
15 August 2018

In this paper, we present a new angle-based reprojection loss, which resolves the issues of the original reproject loss, and the system achieves more accurate results. Expand

Frankenstein: Learning Deep Face Representations Using Small Data

Guosheng Hu, Xiaojiang Peng, Yongxin Yang, Timothy M. Hospedales, Jakob Verbeek
Computer Science, Medicine
IEEE Transactions on Image Processing
21 March 2016

We propose a method to generate very large training data sets of synthetic images by compositing real face images in a given data set. Expand

Recommended Authors