Rodrigo Benenson

Publications
Influence

The Cityscapes Dataset for Semantic Urban Scene Understanding

Marius Cordts, Mohamed Omran, +6 authors B. Schiele
Computer Science
IEEE Conference on Computer Vision and Pattern…
6 April 2016

We introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Expand

3,863
1010
PDF

CityPersons: A Diverse Dataset for Pedestrian Detection

Shanshan Zhang, Rodrigo Benenson, B. Schiele
Computer Science
IEEE Conference on Computer Vision and Pattern…
19 February 2017

We introduce CityPersons, a new set of high quality bounding box annotations for pedestrian detection on the Cityscapes dataset (train, validation, and test sets). Expand

Learning Video Object Segmentation from Static Images

Federico Perazzi, A. Khoreva, Rodrigo Benenson, B. Schiele, Alexander Sorkine-Hornung
Computer Science
IEEE Conference on Computer Vision and Pattern…
8 December 2016

We demonstrate that highly accurate object segmentation in videos can be enabled by using a convolutional neural network trained with static images only. Expand

Face Detection without Bells and Whistles

Markus Mathias, Rodrigo Benenson, M. Pedersoli, L. Gool
Computer Science
ECCV
6 September 2014

Face detection is a mature problem in computer vision. While diverse high performing face detectors have been proposed in the past, we present two surprising new top performance results. First, we… Expand

What Makes for Effective Detection Proposals?

J. Hosang, Rodrigo Benenson, Piotr Dollár, B. Schiele
Computer Science, Medicine
IEEE Transactions on Pattern Analysis and Machine…
17 February 2015

We introduce a novel metric, the average recall (AR), which rewards both high recall and good localisation and correlates surprisingly well with detection performance. Expand

Ten Years of Pedestrian Detection, What Have We Learned?

Rodrigo Benenson, Mohamed Omran, J. Hosang, B. Schiele
Computer Science
ECCV Workshops
6 September 2014

We analyse the remarkable progress of the last decade by dis- cussing the main ideas explored in the 40+ detectors currently present in the Caltech pedestrian detection benchmark. Expand

Simple Does It: Weakly Supervised Instance and Semantic Segmentation

A. Khoreva, Rodrigo Benenson, J. Hosang, M. Hein, B. Schiele
Computer Science
IEEE Conference on Computer Vision and Pattern…
24 March 2016

We show that when carefully designing the input labels from given bounding boxes, even a single round of training is enough to improve over previously reported weakly supervised results. Expand

Filtered channel features for pedestrian detection

Shanshan Zhang, Rodrigo Benenson, B. Schiele
Computer Science
IEEE Conference on Computer Vision and Pattern…
23 January 2015

This paper starts from the observation that multiple top performing pedestrian detectors can be modelled by using an intermediate layer filtering low-level features in combination with a boosted decision forest. Expand

Pedestrian detection at 100 frames per second

Rodrigo Benenson, Markus Mathias, R. Timofte, L. Gool
Computer Science
IEEE Conference on Computer Vision and Pattern…
16 June 2012

We present a new pedestrian detector that improves both in speed and quality over state-of-the-art. Expand

Traffic sign recognition — How far are we from the solution?

Markus Mathias, R. Timofte, Rodrigo Benenson, L. Gool
Computer Science
The International Joint Conference on Neural…
2013

We show that, without any application specific modification, existing methods for pedestrian detection, and for digit and face classification; can reach performances in the range of 95% ~ 99% of the perfect solution. Expand

Recommended Authors