217 citations · 875 across the 53 of their papers we have counts for
8 papers · 1 filter
A Computer Vision System to Localize and Classify Wastes on the Streets
Mohammad Saeed Rad, Andreas von Kaenel, Andre Droux +4
Littering quantification is an important step for improving cleanliness of cities. When human interpretation is too cumbersome or in some cases impossible, an objective index of cl…
Visual Speech Recognition Using PCA Networks and LSTMs in a Tandem GMM-HMM System
Marina Zimmermann, Mostafa Mehdipour Ghazi, Hazım Kemal Ekenel +1
Automatic visual speech recognition is an interesting problem in pattern recognition especially when audio data is noisy or not readily available. It is also a very challenging tas…
Combining LiDAR Space Clustering and Convolutional Neural Networks for Pedestrian Detection
Damien Matti, Hazım Kemal Ekenel, Jean-Philippe Thiran
Pedestrian detection is an important component for safety of autonomous vehicles, as well as for traffic and street surveillance. There are extensive benchmarks on this topic and i…
Strengths and Weaknesses of Deep Learning Models for Face Recognition Against Image Degradations
Klemen Grm, Vitomir Štruc, Anais Artiges +2
Deep convolutional neural networks (CNNs) based approaches are the state-of-the-art in various computer vision tasks, including face recognition. Considerable research effort is cu…
Combining Multiple Views for Visual Speech Recognition
Marina Zimmermann, Mostafa Mehdipour Ghazi, Hazım Kemal Ekenel +1
Visual speech recognition is a challenging research problem with a particular practical application of aiding audio speech recognition in noisy scenarios. Multiple camera setups ca…
Exploiting Convolution Filter Patterns for Transfer Learning
Mehmet Aygün, Yusuf Aytar, Hazım Kemal Ekenel
In this paper, we introduce a new regularization technique for transfer learning. The aim of the proposed approach is to capture statistical relationships among convolution filters…
The Unconstrained Ear Recognition Challenge
Žiga Emeršič, Dejan Štepec, Vitomir Štruc +11
In this paper we present the results of the Unconstrained Ear Recognition Challenge (UERC), a group benchmarking effort centered around the problem of person recognition from ear i…
Face Deidentification with Generative Deep Neural Networks
Blaž Meden, Refik Can Mallı, Sebastjan Fabijan +3
Face deidentification is an active topic amongst privacy and security researchers. Early deidentification methods relying on image blurring or pixelization were replaced in recent…