In this paper we propose a Gaussian-kernel-based online kernel density estimation which can be used for applications of online probability density estimation and online learning. Our approach generates a Gaussian mixture model of the observed data and allows online adaptation from positive examples as well as from the negative examples. The strength of the proposed approach is demonstrated with examples of online estimation of complex distributions, an example of unlearning, and with an interactive learning of basic visual concepts.
COBISS.SI-ID: 7326804
In this work we present a new approach to interest point detection. New entities are introduced: circumferences and radii. The total sum of squares computed on the intensity values of a local region is divided into three components: between-circumferences sum of squares, between-radii sum of squares, and the remainder. These three components normalized by the total sum of squares represent three new saliency measures, namely radial, tangential, and residual. The proposed approach gives a rich set of highly distinctive local regions that can be used for object recognition and image matching.
COBISS.SI-ID: 41304418
Image categorisation involves the well known difficulties with different visual appearances of a single object, but also introduces the problem of within-category variation. This within-category variation makes highly distinctive local descriptors less appropriate for categorisation. Difficulties of the within category variation and clutter are tackled by modelling image fragments in a new manner. The authors propose a family of local image descriptors, called probabilistic patch descriptors (PPDs). PPDs encode the appearance of image fragments as well as their variability within a category.
COBISS.SI-ID: 38466658
The high discrepancy between the accuracy of object classification and detection/segmentation suggests that the problem still poses a significant and open challenge. The recent preoccupation with tuning the approaches to specific datasets might have precluded the attention from the most crucial issue: the representation. This paper will focus on what we believe are two central representational design principles, namely a hierarchical organization of categorical representations, more specifically, the principle of hierarchical compositionality, and statistical, bottom-up learning.
COBISS.SI-ID: 7461204
Contemporary art nowadays tries to exploit modern technology to better address and enlighten specific problems and ideas of our time. Our interest in contemporary art, brought our attention also to the use of computer vision methods in art. This chapter walks us through projects: 15 Seconds of Fame, Dynamic Anamorphosis, Virtual Skiing, Smart Wall, Virtual Dance and Virtual Painter, which require face detection, motion following, depth recovery, touchless human-computer interaction, immersion into virtual worlds without the need for any special equipment.
COBISS.SI-ID: 7398996