no code implementations • 3 May 2022 • Darian Tomašević, Peter Peer, Vitomir Štruc
Current state-of-the-art segmentation techniques for ocular images are critically dependent on large-scale annotated datasets, which are labor-intensive to gather and often raise privacy concerns.
no code implementations • 1 Apr 2022 • Miha Grabner, Yi Wang, Qingsong Wen, Boštjan Blažič, Vitomir Štruc
Efficient load forecasting is needed to ensure better observability in the distribution networks, whereas such forecasting is made possible by an increasing number of smart meter installations.
no code implementations • 24 Nov 2021 • Dailé Osorio-Roig, Christian Rathgeb, Pawel Drozdowski, Philipp Terhörst, Vitomir Štruc, Christoph Busch
The attack is based on two observations: (1) to achieve high recognition accuracy, certain similarities between facial representations have to be retained in their privacy-enhanced versions; (2) highly similar facial representations usually originate from face images with similar soft-biometric attributes.
no code implementations • 28 Sep 2021 • Marija Ivanovska, Vitomir Štruc
Due to the separation of semantically-relevant and residual information, Y-GAN is able to derive informative data representations that allow for efficient anomaly detection across a diverse set of anomaly detection tasks.
no code implementations • 29 Jun 2021 • Fadi Boutros, Naser Damer, Jan Niklas Kolf, Kiran Raja, Florian Kirchbuchner, Raghavendra Ramachandra, Arjan Kuijper, Pengcheng Fang, Chao Zhang, Fei Wang, David Montero, Naiara Aginako, Basilio Sierra, Marcos Nieto, Mustafa Ekrem Erakin, Ugur Demir, Hazim Kemal, Ekenel, Asaki Kataoka, Kohei Ichikawa, Shizuma Kubo, Jie Zhang, Mingjie He, Dan Han, Shiguang Shan, Klemen Grm, Vitomir Štruc, Sachith Seneviratne, Nuran Kasthuriarachchi, Sanka Rasnayaka, Pedro C. Neto, Ana F. Sequeira, Joao Ribeiro Pinto, Mohsen Saffari, Jaime S. Cardoso
These teams successfully submitted 18 valid solutions.
1 code implementation • 20 Mar 2021 • Martin Pernuš, Vitomir Štruc, Simon Dobrišek
The proposed approach is based on an optimization procedure that directly optimizes the latent code of a pre-trained (state-of-the-art) Generative Adversarial Network (i. e., StyleGAN2) with respect to several constraints that ensure: (i) preservation of relevant image content, (ii) generation of the targeted facial attributes, and (iii) spatially--selective treatment of local image areas.
no code implementations • 28 Jan 2020 • Jaka Šircelj, Tim Oblak, Klemen Grm, Uroš Petković, Aleš Jaklič, Peter Peer, Vitomir Štruc, Franc Solina
In this paper we address the problem of representing 3D visual data with parameterized volumetric shape primitives.
no code implementations • 24 Apr 2019 • Janez Križaj, Peter Peer, Vitomir Štruc, Simon Dobrišek
We develop two distinct approaches around the proposed gating mechanism: i) the first uses a gated multiple ridge descent (GRID) mechanism in conjunction with established (hand-crafted) HOG features for face alignment and achieves state-of-the-art landmarking performance across a wide range of facial poses, ii) the second simultaneously learns multiple-descent directions as well as binary features (SMUF) that are optimal for the alignment tasks and in addition to competitive landmarking results also ensures extremely rapid processing.
no code implementations • 13 Apr 2019 • Tim Oblak, Klemen Grm, Aleš Jaklič, Peter Peer, Vitomir Štruc, Franc Solina
It has been a longstanding goal in computer vision to describe the 3D physical space in terms of parameterized volumetric models that would allow autonomous machines to understand and interact with their surroundings.
no code implementations • 11 Mar 2019 • Žiga Emeršič, Aruna Kumar S. V., B. S. Harish, Weronika Gutfeter, Jalil Nourmohammadi Khiarak, Andrzej Pacut, Earnest Hansley, Mauricio Pamplona Segundo, Sudeep Sarkar, Hyeonjung Park, Gi Pyo Nam, Ig-Jae Kim, Sagar G. Sangodkar, Ümit Kaçar, Murvet Kirci, Li Yuan, Jishou Yuan, Haonan Zhao, Fei Lu, Junying Mao, Xiaoshuang Zhang, Dogucan Yaman, Fevziye Irem Eyiokur, Kadir Bulut Özler, Hazim Kemal Ekenel, Debbrota Paul Chowdhury, Sambit Bakshi, Pankaj K. Sa, Banshidhar Majhi, Peter Peer, Vitomir Štruc
The goal of the challenge is to assess the performance of existing ear recognition techniques on a challenging large-scale ear dataset and to analyze performance of the technology from various viewpoints, such as generalization abilities to unseen data characteristics, sensitivity to rotations, occlusions and image resolution and performance bias on sub-groups of subjects, selected based on demographic criteria, i. e. gender and ethnicity.
no code implementations • 29 Jan 2019 • Juš Lozej, Dejan Štepec, Vitomir Štruc, Peter Peer
How important is the use of traditional segmentation methods in a deep learning setting?
no code implementations • 21 Dec 2018 • Klemen Grm, Martin Pernuš, Leo Cluzel, Walter Scheirer, Simon Dobrišek, Vitomir Štruc
This down-sampling (or degradation) procedure not only defines the characteristics of the LR training data, but also determines the type of image degradations the learned FH models are eventually able to handle.
no code implementations • 28 May 2018 • Klemen Grm, Simon Dobrišek, Walter J. Scheirer, Vitomir Štruc
In this paper we address the problem of hallucinating high-resolution facial images from unaligned low-resolution inputs at high magnification factors.
no code implementations • 27 Nov 2017 • Žiga Emeršič, Dejan Štepec, Vitomir Štruc, Peter Peer
The result of our work is the first CNN-based approach to ear recognition that is also made publicly available to the research community.
1 code implementation • 4 Oct 2017 • Klemen Grm, Vitomir Štruc, Anais Artiges, Matthieu Caron, Hazim Kemal Ekenel
However, studies systematically exploring the strengths and weaknesses of existing deep models for face recognition are still relatively scarce in the literature.
no code implementations • 23 Aug 2017 • Žiga Emeršič, Dejan Štepec, Vitomir Štruc, Peter Peer, Anjith George, Adil Ahmad, Elshibani Omar, Terrance E. Boult, Reza Safdari, Yuxiang Zhou, Stefanos Zafeiriou, Dogucan Yaman, Fevziye I. Eyiokur, Hazim K. Ekenel
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 images captured in uncontrolled conditions.
no code implementations • 28 Jul 2017 • Blaž Meden, Refik Can Malli, Sebastjan Fabijan, Hazim Kemal Ekenel, Vitomir Štruc, Peter Peer
Our results show that the recognition performance on deidentified images is close to chance, suggesting that the deidentification process based on GNNs is highly effective.
no code implementations • 1 Feb 2017 • Žiga Emeršič, Luka Lan Gabriel, Vitomir Štruc, Peter Peer
For our technique, we formulate the problem of ear detection as a two-class segmentation problem and train a convolutional encoder-decoder network based on the SegNet architecture to distinguish between image-pixels belonging to either the ear or the non-ear class.
no code implementations • 18 Nov 2016 • Žiga Emeršič, Vitomir Štruc, Peter Peer
This paper presents an overview of the field of automatic ear recognition (from 2D images) and focuses specifically on the most recent, descriptor-based methods proposed in this area.