The loss of information due to occlusion and other complications has been one of the main bottlenecks in the field of motion estimation. In this paper, we propose a novel motion e...
In this work we present a new string similarity feature, the sparse spatial sample (SSS). An SSS is a set of short substrings at specific spatial displacements contained in the or...
In this paper, we present a new approach for viewinvariant action recognition using constraints derived from the eigenvalues of planar homographies associated with triplets of bod...
We present the Higher Order Proxy Neighborhoods (HOPS) approach to modeling higher order neighborhoods in Markov Random Fields (MRFs). HOPS incorporates more context information i...
Many existing spectral clustering algorithms share a conventional graph partitioning criterion: normalized cuts (NC). However, one problem with NC is that it poorly captures the g...
A new feature descriptor is presented for object and scene recognition. The new approach, called CDIKP, uniquely combines the scale-invariant feature detection with a robust proje...
The covariance region descriptor recently proposed in [1] has been proved robust and versatile for a modest computational cost. The covariance matrix enables efficient fusion of d...
We present a compact representation for human action recognition in videos using line and optical flow histograms. We introduce a new shape descriptor based on the distribution of...
Nazli Ikizler, Pinar Duygulu, Ramazan Gokberk Cinb...
Recently, there is a growing interest in automatic recognition of human motion for applications, such as humanoid robots, human activity monitoring, and surveillance. In this pape...
This paper presents a new adaptive approach for document image binarization. The proposed method is mainly based on the combination of several stateof-the-art binarization methodo...
Basilios Gatos, Ioannis Pratikakis, Stavros J. Per...