[4] | Sabrina Kletz, Andreas Leibetseder, Klaus Schoeffmann, A comparative study of video annotation tools for scene understanding, In Proceedings of the 10th ACM Multimedia Systems Conference, ACM, pp. 133-144, 2019.
[bib][url] [doi] [abstract]
Abstract: Computers are powerful tools capable of solving a great variety of ever so complex problems, yet training them to interpret even the simplest video scenes can prove more challenging than one might imagine. Still being one of the major problems in computer vision, this issue recently is addressed by utilizing promising deep learning approaches in order to recognize objects and their semantics. For achieving this goal, huge artificial networks are fed with many human-created annotations using more or less sophisticated tools for speeding up the otherwise time-consuming task of manual annotation. Purposefully refraining from designing yet another of these annotation tools, in this work we strive for evaluating what makes existing ones great or not, i.e. we aim at determining effectiveness and efficiency of state-of-the-art object annotation tools when employed for annotating different kinds of video content. Our findings in a user study evaluating three comparable tools on three videos of distinct domains indicate a significant difference in annotation effort from a video perspective, yet no significance regarding utilized tools. Further, we determine a significant correlation between annotation time and accuracy.
|
[3] | Markus Waltl, Benjamin Rainer, Christian Timmerer, Hermann Hellwagner, An End-to-End tool chain for sensory experience based on MPEG-V, In Signal Processing: Image Communication, Elsevier, vol. 28, no. 2, Amsterdam, Netherlands, pp. 136-150, 2013.
[bib][url] [doi] [abstract]
Abstract: This paper provides an overview of our research conducted in the area of Sensory Experience including our implementations using MPEG-V Part 3 entitled ”Sensory Information”. MPEG-V Part 3 introduces Sensory Experience as a tool to increase the Quality of Experience by annotating traditional multimedia data with sensory effects. These sensory effects are rendered on special devices like fans, vibration chairs, ambient lights, scent disposers, water sprayers, or heating/cooling devices stimulating senses beyond the traditional ones. The paper's main focus is on the end-to-end aspects including the generation, transmission, and synchronized rendering of sensory effects with the traditional multimedia data taking movie clips as an example. Therefore, we present in this paper an open source tool chain that provides a complete end-to-end sensory effect generation and consumption framework. Furthermore, we summarize results from various subjective quality assessments conducted in this area. Finally, we point out research challenges that may encourage further research within this emerging domain.
|
[2] | Markus Waltl, Benjamin Rainer, Christian Timmerer, Hermann Hellwagner, A Toolset for the Authoring, Simulation, and Rendering of Sensory Experiences, In Proceedings of the 20th ACM Multimedia (MM'12) (Noboru Babaguchi, Kiyoharu Aizawa, John Smith, eds.), ACM, Nara, Japan, pp. 1469-1472, 2012.
[bib][url] [pdf] [abstract]
Abstract: This paper describes a toolset for the authoring, simulating, and rendering of multimedia content annotated with Sensory Effect Metadata (SEM) descriptions as specified in Part 3 of the MPEG V standard. This part of MPEG-V standardizes the description of sensory effects (e.g., light, wind) in order to be rendered on sensory devices (e.g., fans, vibration chairs) aiming at generating a sensory experience stimulating possibly all human senses. Our implementation comprises a toolset to author sensory effects associated with multimedia content and the simulation thereof. Furthermore, it includes a library, a standalone player, and a Web browser plug-in which enables the playback and rendering of sensory effects on off-the-shelf rendering devices and in various contexts. All software modules are available under the GNU General Public License (GPL) v3 and the GNU Lesser General Public License (LGPL) v3 respectively.
|
[1] | Mario Taschwer, Armin Müller, Laszlo Böszörmenyi, Integrating Semantic Search and Adaptive Streaming of Video Segments: the DAHL Project, Technical report, Institute of Information Technology (ITEC), Klagenfurt University, no. TR/ITEC/05/2.04, Klagenfurt, Austria, pp. 34, 2005.
[bib] [abstract]
Abstract: The DAHL project aimed at demonstrating some of the research achievements at ITEC by extending anexisting web application with content-based search mechanisms and an adaptive streaming environment for video data. The search is based on MPEG-7 descriptions of video data, and video retrieval uses an MPEG-4 conforming adaptive streaming server and player, which allows to adapt the video stream dynamically to client capabilities, user preferences, and available network bandwidth. This report describes the design, implementation, and integration work done in the DAHL project.
|