Accepted: 10 January 2020 Violent event detection is an interesting research problem and it
is a branch of action recognition and computer vision. The detection of violent events is …

In this paper, we concentrate on the problem of cross-domain aerial scene classification.
The primary assumption of the proposed cross-domain distance metric learning (CDDML) …

The main idea of this paper is to exploit our earlier work of image segmentation [11] and to
propose a novel transform technique known as Coslets which is derived by applying 1D …

Annotating, retrieving and classifying images in an ever increasing large image datasets
with semantic information is still an exigent task. Image pre-processing plays a vital role in …

With the growing popularity of digital services and internet technology billions of people are
prone to information sharing and uploading photos. For accurate retrieval of images from …

Image classification is one of the major research areas, to meet the needs of reliable and
automatic image annotation system. Deep learning techniques have proved to be the …

Advancements in sensors and image acquisition devices lead to tremendous increase in
creation of unlabeled database of images, and traditional image retrieval approaches are …

Since Gaussian Mixture Models (GMM) captures complex densities of the data and has
become one of the most significant methods for clustering in unsupervised context; we study …

Assigning a label pertaining to an image belonging to its category is defined as object
taxonomy. In this paper, we propose a transform based descriptor which effectively extracts …

Image Classification is major aide in improving Human Computer Interaction (HCI) by
providing semantic level user experience. Classification of images has ever since been on a …