Search Results - "Gevers, Theo"

On the benefit of adversarial training for monocular depth estimation by Groenendijk, Rick, Karaoglu, Sezer, Gevers, Theo, Mensink, Thomas

“…In this paper we address the benefit of adding adversarial training to the task of monocular depth estimation. A model can be trained in a self-supervised…”
Get full text

Generalized Gamut Mapping using Image Derivative Structures for Color Constancy by Gijsenij, Arjan, Gevers, Theo, van de Weijer, Joost

“…The gamut mapping algorithm is one of the most promising methods to achieve computational color constancy. However, so far, gamut mapping algorithms are…”
Get full text

ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition by Baslamisli, Anil S., Das, Partha, Le, Hoang-An, Karaoglu, Sezer, Gevers, Theo

“…In general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are…”
Get full text

Combining Priors, Appearance, and Context for Road Detection by Alvarez, Jose M., Lopez, Antonio M., Gevers, Theo, Lumbreras, Felipe

“…Detecting the free road surface ahead of a moving vehicle is an important research topic in different areas of computer vision, such as autonomous driving or…”
Get full text

CNN Based Learning Using Reflection and Retinex Models for Intrinsic Image Decomposition by Baslamisli, Anil S., Le, Hoang-An, Gevers, Theo

“…Most of the traditional work on intrinsic image decomposition rely on deriving priors about scene characteristics. On the other hand, recent research use deep…”
Get full text

Spatial-temporal dual-actor CNN for human interaction prediction in video by Afrasiabi, Mahlagha, Khotanlou, Hassan, Gevers, Theo

“…Predicting the interaction between two humans, when viewed as a part of video is one of the most challenging issues in the field of computer vision, due to its…”
Get full text

Three-D Wide Faces (3DWF): Facial Landmark Detection and 3D Reconstruction over a New RGB⁻D Multi-Camera Dataset by Quintana, Marcos, Karaoglu, Sezer, Alvarez, Federico, Menendez, Jose Manuel, Gevers, Theo

“…Latest advances of deep learning paradigm and 3D imaging systems have raised the necessity for more complete datasets that allow exploitation of facial…”
Get full text

Initial development of perpetrator confrontation using deepfake technology in victims with sexual violence-related PTSD and moral injury by van Minnen, Agnes, Ter Heide, F Jackie June, Koolstra, Tilly, de Jongh, Ad, Karaoglu, Sezer, Gevers, Theo

“…Interventions aimed at easing negative moral (social) emotions and restoring social bonds - such as amend-making and forgiving-have a prominent role in the…”
Get full text

Corrigendum: Initial development of perpetrator confrontation using deepfake technology in victims with sexual violence-related PTSD and moral injury by van Minnen, Agnes, Ter Heide, F Jackie June, Koolstra, Tilly, de Jongh, Ad, Karaoglu, Sezer, Gevers, Theo

“…[This corrects the article DOI: 10.3389/fpsyt.2022.882957.]…”
Get full text

Evaluation of Color STIPs for Human Action Recognition by Everts, Ivo, van Gemert, Jan C., Gevers, Theo

“…This paper is concerned with recognizing realistic human actions in videos based on spatio-temporal interest points (STIPs). Existing STIP-based action…”
Get full text

Accurate eye center location and tracking using isophote curvature by Valenti, R., Gevers, T.

“…The ubiquitous application of eye tracking is precluded by the requirement of dedicated and expensive hardware, such as infrared high definition cameras…”
Get full text

Image saliency by isocentric curvedness and color by Valenti, Roberto, Sebe, Nicu, Gevers, Theo

“…In this paper we propose a novel computational method to infer visual saliency in images. The method is based on the idea that salient objects should have…”
Get full text

Evaluation of color descriptors for object and scene recognition by van de Sande, K., Gevers, T., Snoek, C.

“…Image category recognition is important to access visual information on the level of objects and scene types. So far, intensity-based descriptors have been…”
Get full text

Effects of chromatic image statistics on illumination induced color differences by Lucassen, Marcel P, Gevers, Theo, Gijsenij, Arjan, Dekker, Niels

“…We measure the color fidelity of visual scenes that are rendered under different (simulated) illuminants and shown on a calibrated LCD display. Observers make…”
Get more information

Color in Computer Vision: Fundamentals and Applications by Gevers, Theo, Gijsenij, Arjan, van de Weijer, Joost, Geusebroek, Jan-Mark

“…While the field of computer vision drives many of today's digital technologies and communication networks, the topic of color has emerged only recently in most…”
Get full text

T-Patterns revisited: mining for temporal patterns in sensor data by Salah, Albert Ali, Pauwels, Eric, Tavenard, Romain, Gevers, Theo

“…The trend to use large amounts of simple sensors as opposed to a few complex sensors to monitor places and systems creates a need for temporal pattern mining…”
Get full text

Color Constancy using Natural Image Statistics by Gijsenij, A., Gevers, T.

“…Although many color constancy methods exist, they are all based on specific assumptions such as the set of possible light sources, or the spatial and spectral…”
Get full text

Per-patch metric learning for robust image matching by Karaoglu, Sezer, Everts, Ivo, van Gemert, Jan C., Gevers, Theo

“…We propose a patch-specific metric learning method to improve matching performance of local descriptors. Existing methodologies typically focus on invariance,…”
Get full text

Geometric Back-propagation in Morphological Neural Networks by Groenendijk, Rick, Dorst, Leo, Gevers, Theo

“…This paper provides a definition of back-propagation through geometric correspondences for morphological neural networks. In addition, dilation layers are…”
Get full text

Interactive Learning of Intrinsic and Extrinsic Properties for All-Day Semantic Segmentation by Bi, Qi, You, Shaodi, Gevers, Theo

“…Scene appearance changes drastically throughout the day. Existing semantic segmentation methods mainly focus on well-lit daytime scenarios and are not well…”
Get full text