The Use of Multiple Cues and Contextual Knowledge in Computer Vision
Finished Project
Abstract This project will explore the influences of visual context and multiple cues on a number of computer vision problems. First, a novel visual saliency or attention model will be developed towards a direction that combines information coming from multiple cues with the contextual knowledge. The goal is to come up with a model that can effectively predict where people look in an image. In the second part of the project, we will investigate the problem of image filtering with a focus on devising appropriate ways of extracting high-level contextual knowledge for filtering and using them to guide the ongoing image smoothing process. The third part of the project will be about developing adaptive approaches to image segmentation that integrates information obtained from multi cues. A novel and effective segmentation algorithm will be developed that adaptively combines high-level prior knowledge with the information obtained from different visual cues at different scales.

Sponsors: The Scientific and Technological Research Council of Turkey (TUBITAK) Career Development Program (Award# 112E146)

Related Publications Alpha Matting with KL-Divergence Based Sparse Sampling
IEEE Transactions on Image Processing
Levent Karacan, Aykut Erdem, and Erkut Erdem
A Region Covariances-based Visual Attention Model for RGB-D Images
International Journal of Intelligent Systems and Applications in Engineering, Vol. 4, No. 4., pp. 128-134, October 2016
Erkut Erdem
Structure-Texture Decomposition of RGB-D Images
International Journal of Intelligent Systems and Applications in Engineering, Vol. 4, No. 4., pp. 111-118, October 2016
Aykut Erdem
Predicting Memorability of Images Using Attention-driven Spatial Pooling and Image Semantics
Image and Vision Computing, 42, pp. 35-46, October 2015 (Editor's choice article)
Bora Celikkale, Aykut Erdem and Erkut Erdem
Image Matting with KL-Divergence Based Sparse Sampling
IEEE International Conference on Computer Vision (ICCV 2015), Santiago, Chile, December 2015
Levent Karacan, Aykut Erdem, Erkut Erdem
Görsel Belirginlik Güdümlü Pozlandırma Birleştirimi (Visual Saliency Guided Exposure Fusion)
22. IEEE Sinyal İşleme ve İletişim Uygulamaları Kurultayı (SIU 2014), Trabzon, Nisan 2014
K. Mammadova, E. Erdem and A. Erdem
Top down saliency estimation via superpixel-based discriminative dictionaries
British Machine Vision Conference (BMVC 2014), Nottingham, UK, September 2014
Aysun Kocak, Kemal Cizmeciler, Aykut Erdem and Erkut Erdem
Visual saliency estimation by integrating features using multiple kernel learning
6th International Symposium on Attention in Cognitive Systems (ISACS 2013), Beijing, China, August 2013
Yasin Kavak, Erkut Erdem, Aykut Erdem
Structure Preserving Image Smoothing via Region Covariances
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2013), 32(6), November 2013.
Levent Karacan, Erkut Erdem, Aykut Erdem