Zobrazeno 1 - 10
of 81
pro vyhledávání: '"Duygulu, Pınar"'
In this paper, we explore a new domain for video-to-video translation. Motivated by the availability of animation movies that are adopted from illustrated books for children, we aim to stylize these videos with the style of the original illustrations
Externí odkaz:
http://arxiv.org/abs/2310.04901
Convolutional Neural Networks (CNN) are known to exhibit poor generalization performance under distribution shifts. Their generalization have been studied extensively, and one line of work approaches the problem from a frequency-centric perspective.
Externí odkaz:
http://arxiv.org/abs/2307.11823
We propose a new method for producing color images from sketches. Current solutions in sketch colorization either necessitate additional user instruction or are restricted to the "paired" translation strategy. We leverage semantic image segmentation
Externí odkaz:
http://arxiv.org/abs/2301.08590
Data shift robustness has been primarily investigated from a fully supervised perspective, and robustness of zero-shot learning (ZSL) models have been largely neglected. In this paper, we present novel analyses on the robustness of discriminative ZSL
Externí odkaz:
http://arxiv.org/abs/2201.10972
We introduce a new method for generating color images from sketches or edge maps. Current methods either require some form of additional user-guidance or are limited to the "paired" translation approach. We argue that segmentation information could p
Externí odkaz:
http://arxiv.org/abs/2102.06192
Autor:
Bilge, Yunus Can, Yucel, Mehmet Kerim, Cinbis, Ramazan Gokberk, Ikizler-Cinbis, Nazli, Duygulu, Pinar
In many real-world problems, there is typically a large discrepancy between the characteristics of data used in training versus deployment. A prime example is the analysis of aggression videos: in a criminal incidence, typically suspects need to be i
Externí odkaz:
http://arxiv.org/abs/2009.07576
Machine learning (ML) systems have introduced significant advances in various fields, due to the introduction of highly complex models. Despite their success, it has been shown multiple times that machine learning models are prone to imperceptible pe
Externí odkaz:
http://arxiv.org/abs/2008.07651
In this paper, we explore illustrations in children's books as a new domain in unpaired image-to-image translation. We show that although the current state-of-the-art image-to-image translation models successfully transfer either the style or the con
Externí odkaz:
http://arxiv.org/abs/2002.05638
Autor:
Yucel, Mehmet Kerim, Bilge, Yunus Can, Oguz, Oguzhan, Ikizler-Cinbis, Nazli, Duygulu, Pinar, Cinbis, Ramazan Gokberk
With the introduction of large-scale datasets and deep learning models capable of learning complex representations, impressive advances have emerged in face detection and recognition tasks. Despite such advances, existing datasets do not capture the
Externí odkaz:
http://arxiv.org/abs/1805.07566
This paper is motivated from a young boy's capability to recognize an illustrator's style in a totally different context. In the book "We are All Born Free" [1], composed of selected rights from the Universal Declaration of Human Rights interpreted b
Externí odkaz:
http://arxiv.org/abs/1704.03057