January 4, 2015, held in conjunction with the 21st International MultiMedia Modeling Conference (MMM) in Sydney, Australia
The Video Search Showcase (VSS) is an annual live video search competition, where international researchers evaluate and demonstrate the efficiency of their interactive video search tools. The Video Search Showcase is a special session at the International Conference on MultiMedia Modeling (MMM), where it started in 2012 under the name â€śVideo Browser Showdownâ€ť (VBS). Participating teams first present the details of their systems and then perform several interactive video search tasks in different parts. The last part of the VSS is a moderated session that is open for the public, where participants of the MMM conference can see the interactive tools in action!
VSS2015 will be a half-day workshop that will take place one day before MMM2015 at the conference venue of MMM2015 in Sydney, Australia. Most of the session will consist of a sequence of interactive search tasks without audience. At the end of the workshop, a public session will start with a round of presentations of the participantsâ€™ interactive video search tools, followed by a 45 minutes moderated session allowing members of the audience to use the tools. The evaluation of the results will be published in an own paper after the workshop.
Demo paper submission deadline: September 22, 2014
Notification of acceptance: October 6, 2014
Camera-ready paper due: October 17, 2014
Author registration deadline: October 17, 2014
Many thanks again to Prof. Wolfgang Hürst for giving a great keynote talk about “Mobile Interaction â€“ Examples for Visualization of and Interaction with Different Media Types on Mobiles” at the 1st International Workshop on Visualization of Heterogeneous Multimedia Content (VisHMC’14), held together with the IEEE International Conference on Multimedia & Expo 2014 (ICME 2014) in Chengdu, China. The talk was very interesting and inspiring! Below you can find a few pictures of it. The slides of the talk are available as PDF here.
A preprint of our paper “3D Interfaces to Improve the Performance of Visual Known-Item Search”, to appear in IEEE Transactions on Multimedia, is available here.
Here are the slides from my talk about Video Browsing, which I gave in Klagenfurt on June 18, 2014 at the International Workshop on Content-Based Multimedia Indexing (CBMI) 2014.
The video players on smartphones and tablets typically use seeker-bars for temporal navigation in videos. In order to jump to different positions in the video you simply have to drag the seeker-bar. However, we argue that this interaction concept is inconsistent to usual interaction with other media on touch devices. For example, in a photo collection you perform horizontal wipe (i.e., drag) gestures in order to browse through all photos of the collection. Similarly, when scrolling through documents or presentation slides, you perform horizontal (or vertical) wipe gestures. Hence, we propose to use such wipe gestures also for navigation in video. Our work combines the ideas proposed earlier by Huber et al. and HĂĽrst et al. in order to allow flexible navigation within a single video but also in a video collection. More details can be found in the preprint of our paper â€śVideo Navigation on Tablets with Multi-Touch Gesturesâ€ť, to be presented at the 3rd International Workshop on Emerging Multimedia Systems and Applications (EMSA) at the IEEE International Conference on Multimedia & Expo (ICME) in July 2014 in Chengdu, China. Our prototype is also available on the App Store on iTunes for the Apple iPad (many thanks to Kevin Chromik for the implementation and evaluation)!
The paper submission deadline for ICME 2014 workshops has been extended to April 1, 2014. Please consider submitting a paper (6 pages in IEEE double-column style) to one of these interesting workshops:
The Pacific-Rim Conference on Multimedia (PCM) is the major annual international conference in Asia organized as a forum for the dissemination of state-of-the-art technological advances and research results in the fields
of theoretical, experimental, and applied multimedia analysis and processing. The conference calls for research papers reporting original investigation results and industrial-track papers reporting real-world multimedia applications and system development experiences. The conference also solicits proposals for tutorials on enabling multimedia technologies, and calls for dedicated special session proposals focusing on emerging challenges in the multimedia arena. PCM 2014 will be held in Kuching, Sarawak, Malaysia. Sarawak, also know as the “Land of the Hornbills”, offers an unforgettable mix of culture- and nature-based travel experiences.
PCM 2014 accepts both full, short and demo papers. Papers should be formatted according to the Lecture Notes in Computer Science template available at the PCM2014 website. A full paper should be 9-10 pages in length; short papers should be exactly 6 pages, and demo paper should be exactly 4 pages.
31 May 2014:Â Regular paper submission
15 June 2014: Demo paper submission
10 Aug 2014:Â Notification of acceptance
31 Aug 2014:Â Camera ready submission
For more information please visit the PCM 2014 website!
Our paper on “OpenCV Performance Measurements on Mobile Devices” has been accepted for the ACM International Conference on Multimedia Retrieval (ICMR 2014)! It investigates the run-time performance of typical image content analysis tasks performed with OpenCV on iOS-based mobile devices in direct comparison to a desktop computer. So in case you wonder whether it is a good idea to run content-based analysis methodsÂ directly on the iPad, you should read our paper, which is available here as a preprint:
The intimate presence of mobile devices in our daily life, such as smartphones and tablets, has dramatically changed the way we connect with the world around us. Users rely on mobile devices to maintain an always-on relation to information, personal, and social networks. With a growing number of powerful embedded mobile sensors like camera, microphone, GPS, gyroscope, accelerometer, digital compass, and proximity sensor, there is a variety of data recorded and hence enables new sensing applications across diverse research domains comprising mobile media analysis, mobile information retrieval, mobile computer vision, mobile social networks, mobile human-computer interaction, mobile entertainment, mobile gaming, mobile healthcare, mobile learning, and mobile advertising.
Regardless of the application fields, many issues and challenges brought by the emerging technologies for mobile multimedia still lie ahead and many research questions remain to be answered. For example, seamless user experience has been identified as one key factor in designing mobile multimedia applications for multiple form factors, but its provision can be challenging and require effective integration of rich mobile sensors and multidisciplinary research, such as multimedia content adaptation and user behavior analysis. In addition, for power saving purpose, application-driven energy management is an important technical consideration in mobile multimedia computing, e.g. what part of the computing should be performed on mobile devices, and what part is better shifted to the cloud servers?
This workshop, WMMC 2014, aims to bring together researchers and professionals from worldwide academia and industry for showcasing, discussing, and reviewing the whole spectrum of technological opportunities, challenges, solutions, and emerging applications in mobile multimedia.
More information here.
Call for Papers
We are pleased to announce the 1st International Workshop on the Visualization of Heterogeneous Multimedia Content, held in conjunction with ICME 2014.
Most of the time when we speak of multimedia corpora, we think of homogeneous datasets consisting of either audio files, videos or sensor data. In recent years, however, we could observe the creation of more and more heterogeneous corpora that consist of data from different sources and of different modality. A typical example are visual lifelogs, i.e., private data collections consisting of large numbers of automatically recorded images, video snippets and accompanying sensor streams. Visualizing such heterogeneous and often large multimedia corpora raise novel challenges that cannot easily be addressed by existing visualization methodologies that have been developed for homogeneous datasets. However, not only visualizing but also browsing such multimedia corpora is a challenging task that needs new interaction and filtering methods in addition to textual queries. This workshop aims to provide a platform for multimedia practitioners and researchers to discuss emerging research trends in this field.
More information here.