Výsledky vyhledávání - "Horst Eidenberger"

Gestalt descriptions for deep image understanding

Publikováno v: Pattern Analysis and Applications. 24:89-107

In this work, we present a novel visual perception-inspired local description approach as a preprocessing step for deep learning. With the ongoing growth of visual data, efficient image descriptor methods are becoming more and more important. Several

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::1b66f791f4498f201ed6ddc1b8fbeb7f
https://doi.org/10.1007/s10044-020-00904-6

Zobrazit plný text záznamu

Smell and touch in the Virtual Jumpcube

Autor: Horst Eidenberger

Publikováno v: Multimedia Systems. 24:695-709

The Virtual Jumpcube is a virtual reality setup from 2015 that allows for jumping and flying in audiovisual virtual environments. Recently, we have included several haptic and olfactory stimuli that should further increase the degree of immersion in

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::eee501d3b31a9e27a76f91deca614ddd
https://doi.org/10.1007/s00530-018-0592-y

Zobrazit plný text záznamu

Gestalt Interest Points with a Neural Network for Makeup-Robust Face Recognition

Autor: Horst Eidenberger, Markus Horhan

Publikováno v: ICIP

In this paper, we propose a novel approach for the domain of makeup-robust face recognition. Most face recognition schemes usually fail to generalize well on these data where there is a large difference between the training and testing sets, e.g., ma

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::39cebe0a8832ec6232f50ba036b73763
https://doi.org/10.1109/icip.2018.8451075

Zobrazit plný text záznamu

Handwritten Music Object Detection: Open Issues and Baseline Results

Autor: Yann Ricquebourg, Kwon-Young Choi, Horst Eidenberger, Alexander Pacha, Richard Zanibbi, Bertrand Coüasnon

Publikováno v: DAS
13th IAPR International Workshop on Document Analysis Systems
13th IAPR International Workshop on Document Analysis Systems, Apr 2018, Vienne, Austria

International audience; Optical Music Recognition (OMR) is the challenge of understanding the content of musical scores. Accurate detection of individual music objects is a critical step in processing musical documents, because a failure at this stag

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::58d9c9f5ec71006185dffe2cd90c6e06
https://doi.org/10.1109/das.2018.51

Zobrazit plný text záznamu

Towards Self-Learning Optical Music Recognition

Autor: Alexander Pacha, Horst Eidenberger

Publikováno v: ICMLA

Optical Music Recognition (OMR) is a branch of artificial intelligence that aims at automatically recognizing and understanding the content of music scores in images. Several approaches and systems have been proposed that try to solve this problem by

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::36c9f2b86e77dfb1a4d6eca7599e8a8c
https://doi.org/10.1109/icmla.2017.00-60

Zobrazit plný text záznamu

The Gestalt Interest Points distance feature for compact and accurate image description

Autor: Markus Horhan, Horst Eidenberger

Publikováno v: ISSPIT

In this work, we present the novel Inter-GIP Distances (IGD) feature and its integration into the Gestalt Interest Points (GIP) image descriptor. With the ongoing growth of visual data, efficient image descriptor methods are becoming more and more im

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::111a720a526294594b6978e55cf6bd78
https://doi.org/10.1109/isspit.2017.8388315

Zobrazit plný text záznamu

Towards a Universal Music Symbol Classifier

Autor: Alexander Pacha, Horst Eidenberger

Publikováno v: GREC@ICDAR

Optical Music Recognition (OMR) aims to recognize and understand written music scores. With the help of Deep Learning, researchers were able to significantly improve the stateof- the-art in this research area. However, Deep Learning requires a substa

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::427504b8112c018dfcb8e2cfca6cd79a
https://doi.org/10.1109/icdar.2017.265

Zobrazit plný text záznamu

An efficient DCT template-based object detection method using phase correlation

Autor: Horst Eidenberger, Markus Horhan

Publikováno v: ACSSC

In this work, we propose an efficient algorithm, which utilizes the combination of discrete cosine transform (DCT) and phase correlation (PC) for fast object detection. To test the algorithm's classification performance and computational complexity w

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5b0385d130a41380b9d610133d2d8dba
https://doi.org/10.1109/acssc.2016.7869078

Zobrazit plný text záznamu

Autor: Horst Eidenberger, Bert Klauninger

Publikováno v: ICPRAM

Based on recent findings from the field of human similarity perception, we propose a dual process model (DPM) of taxonomic and thematic similarity assessment which can be utilised in machine learning applications. Taxonomic reasoning is related to pr

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0252f20e939f5669d31cf30fcbb03961
https://doi.org/10.5220/0005655801410147

Zobrazit plný text záznamu

Machine Learning with Dual Process Models

Autor: Martin Unger, Horst Eidenberger, Bert Klauninger

Publikováno v: ICPRAM

Similarity measurement processes are a core part of most machine learning algorithms. Traditional approaches focus on either taxonomic or thematic thinking. Psychological research suggests that a combination of both is needed to model human-like simi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4fe91d29cede2c544dd9fd613fae0bdb
https://doi.org/10.5220/0005655901480153

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání