This paper starts with the concept of a virtual gallery where art works, mainly pictures, are presented on the world wide web. One of the first such galleries, the Slovenian Virtual Gallery existing from 1995 is being considered. Today, such galleries are conceptually not much different, however, they typically contain much more material of higher resolution in 2D and 3D. Several open source to...

Art museums can be complex, confounding, boring, exciting, absurd, and breathtaking. They can be sad, enlightening, hurtful, alive, dead, mainstream and avant-garde. They can, at once, be all of these things. Or they can be any one of these things separately. Museums can be more. Art museums might provide a place for contemplation, a place for social commentary, a place for political discourse,...

Video playback in mobile devices is becoming increasingly popular. Since mobile devices are typically resource constrained, various video personalization strategies are used to provide personalized video content that is most relevant to the client’s request. In this paper, we propose a novel video personalization server and cache architecture, which uses automatic video segmentation and video i...

In order to enhance the accuracy of the motion vector (MV) estimation and also reduce the error propagation issue during the estimation, in this paper, a new adaptive error concealment (EC) approach is proposed based on the information extracted from the video scene. In this regard, the motion information of the video scene around the degraded MB is first analyzed to estimate the motion type of...

Video is one of the fastest-growing sources of data and is rich with interesting semantic information. Furthermore, recent advances in computer vision, in the form of deep convolutional neural networks (CNNs), have made it possible to query this semantic information with near-human accuracy (in the form of image tagging). However, performing inference with state-of-the-art CNNs is computational...

Although techniques for separate image and audio steganography are widely known, relatively little has been described concerning the hiding of information within video streams (“video steganography”). In this paper we review the current state of the art in this field, and describe the key issues we have encountered in developing a practical video steganography system. A supporting video is also...

Today video communication technology offers real time learning experiences although teachers and students work and collaborate together without being physically at the same geographical location. This paper outlines and discusses infrastructure dependent factors that affect just-in-time transfer of new skills, competence and know-how to the workplace in Small and Medium Sized Enterprises (SME),...

Our objective is video retrieval based on natural language queries. In addition, we consider the analogous problem of retrieving sentences or generating descriptions given an input video. Recent work has addressed the problem by embedding visual and textual inputs into a common space where semantic similarities correlate to distances. We also adopt the embedding approach, and make the following...