Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Dogancan Temel"'
Autor:
Dogancan Temel, Ghassan AlRegib
Publikováno v:
Signal Processing: Image Communication. 70:37-46
In this paper, we analyze the statistics of error signals to assess the perceived quality of images. Specifically, we focus on the magnitude spectrum of error images obtained from the difference of reference and distorted images. Analyzing spectral s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c054e1811a0a96d330a7c49b755394d
https://doi.org/10.1016/j.image.2018.09.005
https://doi.org/10.1016/j.image.2018.09.005
Publikováno v:
ICIP
Semantic segmentation is a scene understanding task at the heart of safety-critical applications where robustness to corrupted inputs is essential. Implicit Background Estimation (IBE) has demonstrated to be a promising technique to improve the robus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8483294b010b4e6816f6f5c2184fc19a
http://arxiv.org/abs/2009.00817
http://arxiv.org/abs/2009.00817
Publikováno v:
ICIP
In this paper, we propose a model-based characterization of neural networks to detect novel input types and conditions. Novelty detection is crucial to identify abnormal inputs that can significantly degrade the performance of machine learning algori
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c97cfce7e62e255c1d898e47d94858ad
http://arxiv.org/abs/2008.06094
http://arxiv.org/abs/2008.06094
Publikováno v:
ICIP
Visual explanations are logical arguments based on visual features that justify the predictions made by neural networks. Current modes of visual explanations answer questions of the form $`Why \text{ } P?'$. These $Why$ questions operate under broad
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::103f2868d1d7952eb73814e681925a96
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585884
ECCV (21)
ECCV (21)
Learning representations that clearly distinguish between normal and abnormal data is key to the success of anomaly detection. Most of existing anomaly detection algorithms use activation representations from forward propagation while not exploiting
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::096b0bd74a63d624002f704279baf52c
https://doi.org/10.1007/978-3-030-58589-1_13
https://doi.org/10.1007/978-3-030-58589-1_13
Autor:
Ghassan AlRegib, Dogancan Temel
Publikováno v:
IEEE Signal Processing Magazine. 35:154-161
Robust and reliable traffic sign detection is necessary to bring autonomous vehicles onto our roads. State-of-the-art algorithms successfully perform traffic sign detection over existing databases that mostly lack severe challenging conditions. VIP C
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53528529d6e0652a4bfd94fe516d8b38
https://doi.org/10.1109/msp.2017.2783449
https://doi.org/10.1109/msp.2017.2783449
Publikováno v:
ICIP
In this paper, we utilize weight gradients from backpropagation to characterize the representation space learned by deep learning algorithms. We demonstrate the utility of such gradients in applications including perceptual image quality assessment a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::220ce841213f7473c2bdb87135cc9933
https://doi.org/10.1109/icip.2019.8803228
https://doi.org/10.1109/icip.2019.8803228
Abnormalities in pupillary light reflex can indicate optic nerve disorders that may lead to permanent visual loss if not diagnosed in an early stage. In this study, we focus on relative afferent pupillary defect (RAPD), which is based on the differen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::852b26d84b538286b78a30ac70af584f
http://arxiv.org/abs/1908.02300
http://arxiv.org/abs/1908.02300
Publikováno v:
ICIP
In this paper, we investigate the reliability of online recognition platforms, Amazon Rekognition and Microsoft Azure, with respect to changes in background, acquisition device, and object orientation. We focus on platforms that are commonly used by
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e1d61348137f679cda6afbf7fa0d4125
http://arxiv.org/abs/1902.06585
http://arxiv.org/abs/1902.06585
Traffic signs are critical for maintaining the safety and efficiency of our roads. Therefore, we need to carefully assess the capabilities and limitations of automated traffic sign detection systems. Existing traffic sign datasets are limited in term
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e6fe1097dd2cd64292930e9f06abe8e