% Categories: SOMA
% Encoding: utf-8
@Article{delfabro_mmsj2013,
  author = {Del Fabro, Manfred and Böszörmenyi, Laszlo},
  journal = {Multimedia Systems},
  title = {State-of-the-art and future challenges in video scene detection: a survey},
  year = {2013},
  issn = {0942-4962},
  month = {feb},
  number = {5},
  pages = {427-454},
  volume = {19},
  address = {Berlin, Heidelberg, New York},
  language = {EN},
  publisher = {Springer-Verlag}
}
@InProceedings{RT_ICME_1,
  author = {Tusch, Roland and Pletzer, Felix and Kraetschmer, Armin and Böszörmenyi, Laszlo and Rinner, Bernhard and Mariacher, Thomas and Harrer, Manfred},
  booktitle = {ICME '12 Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops},
  title = {Efficient Level of Service Classification for Traffic Monitoring in the Compressed Video Domain},
  year = {2012},
  address = {Piscataway (NJ)},
  editor = {Zhang, Jian and Schonfeld, Dan and Deagan, David Feng},
  month = {jul},
  pages = {967-972},
  publisher = {IEEE},
  abstract = {This paper presents a new method for estimating the level of service (LOS) on motorways in the compressed video domain. The method performs statistical computations on motion vectors of MPEG4 encoded video streams within a predefined region of interest to determine a set of four motion features describing the speed and density of the traffic stream. These features are fed into a Gaussian radial basis function network to classify the corresponding LOS. To improve the classification results, vectors of moving objects are clustered and outliers are eliminated. The proposed method is designed to be executed on a server system, where a large number of camera live streams can be analyzed in parallel in real-time. Evaluations with a comprehensive set of real-world training and test data from an Austrian motorway have shown an average accuracy of 86.7% on the test data set for classifying all four LOS levels. With a mean execution time of 48 microseconds per frame on a common server, hundreds of video streams can be analyzed in real-time.},
  doi = {10.1109/ICME.2012.101},
  isbn13 = {978-1-4673-1659-0},
  language = {EN},
  location = {Melbourne, Australia},
  talkdate = {2012.07.12},
  talktype = {registered}
}
@InProceedings{RT_ICME,
  author = {Tusch, Roland and Pletzer, Felix and Mudunuri, Vijay and Kraetschmer, Armin and Sabbavarapu, Karuna and Kogler, Marian and Böszörmenyi, Laszlo and Rinner, Bernhard and Harrer, Manfred and Mariacher, Thomas and Hrassnig, P},
  booktitle = {ICMEW '12 Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops},
  title = {LOOK2 - A Video-based System for Real-time Notification of Relevant Traffic Events.},
  year = {2012},
  address = {Piscataway (NJ)},
  editor = {Zhang, Jian and Schonfeld, Dan and Feng, Deagan David},
  month = {jul},
  pages = {670},
  publisher = {IEEE},
  abstract = {We demonstrate our novel video-based real-time traffic event notification and verification system LOOK2. It generates fast and reliable traffic information about relevant traffic state and road conditions changes on observed roads. It utilizes installed road-side sensors providing low-level traffic and environmental data, as well as video sensors which gain high-level traffic information from live video analysis. Spatio-temporal data fusion is applied on all available traffic and environmental data to gain reliable traffic information. This traffic information is published by a DATEXII compliant web service to a web-based traffic desk application. Road network and traffic channel operators receive real-time and relevant traffic event notifications by using this application. The system also enables a visual verification of the notified situations.},
  doi = {10.1109/ICMEW.2012.126},
  isbn10 = {978-1-4673-2027-6},
  language = {EN},
  location = {Melbourne, Australia},
  talkdate = {2012.07.10},
  talktype = {poster}
}
@InProceedings{DelFabro2012a,
  author = {Del Fabro, Manfred and Böszörmenyi, Laszlo},
  booktitle = {Advances in Multimedia Modeling},
  title = {{AAU} Video Browser: Non-Sequential Hierarchical Video Browsing without Content Analysis},
  year = {2012},
  address = {Berlin, Heidelberg, New York},
  editor = {Schoeffmann, Klaus and Merialdo, Bernard and Hauptmann, Alexander and Ngo, Chong-Wah and Andreopoulos, Yiannis and Breiteneder, Christian},
  month = {jan},
  pages = {639--641},
  publisher = {Springer},
  abstract = {We participate in the Video Browser Showdown with our easy-to-use video browsing tool. It can be used for getting a quick overview of videos as well as for simple Known Item Search (KIS) tasks. It offers a parallel and a tree-like browsing interface for navigating through the content of single videos or even small video collections in a hierarchical, non-sequential manner. We want to validate whether simple KIS tasks can be completed without a time consuming content analysis in advance.},
  doi = {10.1007/978-3-642-27355-1_63},
  language = {EN},
  location = {Klagenfurt, Austria},
  pdf = {https://www.itec.aau.at/bib/files/delfabro_mmm2012_VBS.pdf},
  talkdate = {2012.01.06},
  talktype = {poster}
}
@InProceedings{DelFabro2012,
  author = {Del Fabro, Manfred and Böszörmenyi, Laszlo},
  booktitle = {Advances in Multimedia Modeling},
  title = {Summarization and Presentation of Real-Life Events Using Community-Contributed Content},
  year = {2012},
  address = {Berlin, Heidelberg, New York},
  editor = {Schoeffmann, Klaus and Merialdo, Bernard and Hauptmann, Alexander and Ngo, Chong-Wah and Andreopoulos, Yiannis and Breiteneder, Christian},
  month = {jan},
  pages = {630--632},
  publisher = {Springer},
  abstract = {We present an algorithm for the summarization of social events with community-contributed content from Flickr and YouTube. A clustering algorithm groups content related to the searched event. Date information, GPS coordinates, user ratings and visual features are used to select relevant photos and videos. The composed event summaries are presented with our video browser.},
  doi = {10.1007/978-3-642-27355-1_60},
  language = {EN},
  location = {Klagenfurt, Austria},
  pdf = {https://www.itec.aau.at/bib/files/submission_145.pdf},
  talkdate = {2012.01.05},
  talktype = {poster}
}
@InProceedings{Sobe2011,
  author = {Sobe, Anita and Elmenreich, Wilfried and Böszörmenyi, Laszlo},
  booktitle = {Proceedings of the Ninth Workshop on intelligent solutions for embedded systems},
  title = {Replication for Bio-inspired Delivery in Unstructured Peer-to-Peer Networks},
  year = {2011},
  address = {Los Alamitos, CA, USA},
  editor = {Kucera, Markus and Waas, Thomas},
  month = {jul},
  pages = {6},
  publisher = {IEEE},
  language = {EN},
  location = {Regensburg, Germany},
  talkdate = {2011.07.08},
  talktype = {registered}
}
@InProceedings{SchoeffmannACMMM11,
  author = {Schoeffmann, Klaus and Del Fabro, Manfred},
  booktitle = {Proceedings of the {ACM} International Conference on Multimedia},
  title = {Hierarchical Video Browsing with a 3D Carousel},
  year = {2011},
  address = {Scottsdale, AZ, USA},
  editor = {Candan, Selcuk and Panchanthan, Sethuraman and Prabhakaran, Balakrishnan Prabhakaran},
  month = {dec},
  pages = {1609-1612},
  publisher = {ACM Pre},
  language = {EN},
  location = {Scottsdale, AZ, USA},
  talkdate = {2011.11.30},
  talktype = {poster}
}
@PhdThesis{DelFabro2011a,
  author = {Del Fabro, Manfred},
  school = {Klagenfurt University},
  title = {Non-Sequential Decomposition, Composition and Presentation of Multimedia Content},
  year = {2011},
  month = {dec},
  abstract = {This thesis discusses three major issues that arise in the context of non-sequential usage of multimedia content, i.e. a usage, where users only access content that is interesting for them. These issues are (1) semantically meaningful segmentation of videos, (2) composition of new video streams with content from different sources and (3) non-sequential presentation of multimedia content.
A semantically meaningful segmentation of videos can be achieved by partitioning a video into scenes. This thesis gives a comprehensive survey of scene segmentation approaches, which were published in the last decade. The presented approaches are categorized based on the underlying mechanisms used for the segmentation. The characteristics that are common for each category as well as the strengths and weaknesses of the presented algorithms are stated. Additionally, an own scene segmentation approach for sports videos with special properties is introduced. Scenes are extracted based on recurring patterns in the motion information of a video stream.
Furthermore, different approaches in the context of real-life events are presented for the composition of new video streams based on content from multiple sources. Community-contributed photos and videos are used to generate video summaries of social events. The evaluation shows that by using content provided by a crowd of people a new and richer view of an event can be created. This thesis introduces a new concept for this emerging view, which is called ``The Vision of Crowds''.
The presentation of such newly, composed video streams is described with a simple but powerful formalism. It provides a great flexibility in defining the temporal and spatial arrangement of content. Additionally, a video browsing application for the hierarchical, non-sequential exploration of video content is introduced. It is able to interpret the formal description of compositions and can be adapted for different purposes with plug-ins.},
  language = {EN},
  pages = {168}
}
@InProceedings{DelFabro2011,
  author = {Del Fabro, Manfred and Böszörmenyi, Laszlo},
  booktitle = {ACM CHI 2011 Workshop – Data Collection By The People For The People},
  title = {The Vision of Crowds: Social Event Summarization Based on User- Generated Multimedia Content},
  year = {2011},
  address = {http://databythepeople.com/ (May 2011)},
  editor = {Robson, Christine and Kandel, Sean and Heer, Jeff and Pierce, Jeff},
  month = {may},
  pages = {1--5},
  publisher = {published on workshop homepage},
  abstract = {In this position paper we introduce the idea of generating a superior view of a large social event, based on user-generated -- crowdsourced -- content. Instead of just collecting and making them available in a raw form (as social platforms like YouTube), we automatically generate semantically coherent summarizations of the entire event. The individual consuming user gets thus a compact view generated by a large number of producing users. We call this idea the "Vision of Crowds".
A case study has been conducted at a social event where we used user-generated content to automatically generate live reports about that event. Furthermore, we have implemented a GUI that allows users to interactively compose personalized video summaries, based on the user-generated data collected at the case study.},
  language = {EN},
  location = {Vancouver, BC, Canada},
  pdf = {https://www.itec.aau.at/bib/files/The Vision of Crowds - Social Event Summarization Based on User-Generated Multimedia Content.pdf},
  talkdate = {2011.05.08},
  talktype = {registered}
}
@InProceedings{Sobe2010a,
  author = {Sobe, Anita and Elmenreich, Wilfried and Böszörmenyi, Laszlo},
  booktitle = {Proceedings of the 18th International Conference on Multimedea 2010},
  title = {{Towards a self-organizing replication model for non-sequential media access}},
  year = {2010},
  address = {New York},
  editor = {Del Bimbo, Alberto and Chang, Shih-Fu and Smeulders, Arnold},
  month = {jan},
  pages = {3--8},
  publisher = {ACM},
  isbn10 = {978-1-60558-933-6},
  keywords = {non-sequential, replication, self-organization, video delivery},
  language = {EN},
  location = {Florence, Italy},
  talkdate = {2010.10.29},
  talktype = {registered}
}
@InProceedings{DelFabro2010a,
  author = {Del Fabro, Manfred and Schoeffmann, Klaus and Böszörmenyi, Laszlo},
  booktitle = {Proceedings of HCI in Work and Learning, Life and Leisure 6th Symposium of the Workgroup Human-Computer Interaction and Usability Engineering},
  title = {Instant Video Browsing: A Tool for Fast Non-sequential Hierarchical Video Browsing},
  year = {2010},
  address = {Berlin, Heidelberg, New York},
  editor = {Leitner, Gerhard and Hitz, Martin and Holzinger, Andreas},
  month = {nov},
  pages = {443-446},
  publisher = {Springer Verlag GmbH},
  abstract = {We introduce an easy-to-use video browsing tool which assists users in getting a quick overview of videos as well as in finding segments of interest. It provides a parallel and a tree-based view for browsing the content of videos -- or even video collections -- in a hierarchical, non-sequential manner. The tool has a plug-in architecture and can be extended both by further presentation methods and by video analysis algorithms.},
  doi = {10.1007/978-3-642-16607-5_30},
  language = {EN},
  location = {Klagenfurt, Austria},
  pdf = {https://www.itec.aau.at/bib/files/Instant Video Browsing - A Tool for Fast Non-Sequential Hierarchical Video Browsing.pdf},
  talkdate = {2010.11.05},
  talktype = {registered}
}
@InProceedings{DelFabro2010,
  author = {Del Fabro, Manfred and Böszörmenyi, Laszlo},
  booktitle = {Proceedings of the Second International Conference on Advances in Multimedia (MMEDIA 2010)},
  title = {Video Scene Detection Based on Recurring Motion Patterns},
  year = {2010},
  address = {Washington (DC)},
  editor = {Böszörmenyi, Laszlo and Burdescu, Dumitru and Davies, Philip and Newell, David},
  month = {jun},
  pages = {113--118},
  publisher = {IEEE},
  abstract = {We present an algorithm for video scene detection based on the identification of recurring motion sequences within a video stream. The motion information is extracted in the compressed domain of H.264/AVC videos, no full decoding of the video stream is needed. Based on the motion information our algorithm identifies sequences of adjacent frames with similar motion. Throughout all identified motion sequences we are searching for recurring patterns of similar ones. The most recurring pattern is used for the segmentation of the video stream into scenes. The evaluation shows promising results.},
  doi = {10.1109/MMEDIA.2010.26},
  language = {EN},
  location = {Athens, Greece},
  pdf = {https://www.itec.aau.at/bib/files/4068a113.pdf},
  talkdate = {2010.06.15},
  talktype = {registered}
}
@InProceedings{Lux2009b,
  author = {Lux, Mathias},
  booktitle = {Multimedia, 2009. ISM '09. 11th IEEE International Symposium on},
  title = {An Evaluation of Metrics for Retrieval of MPEG-7 Semantic Descriptions},
  year = {2009},
  address = {Los Alamitos, CA, USA},
  editor = {Tsai, Jeffrey and Jain, Ramesh},
  month = dec,
  pages = {546-551},
  publisher = {IEEE},
  abstract = {MPEG-7 is an extensive multimedia metadata standard covering a huge number of aspects of metadata. However, as with most metadata standards details of usage and application of the standards are – at least partially – open to interpretation. In case of MPEG-7storage and transmission of high level metadata on concept level are defined but retrieval methods are not proposed. So if for instance a user annotates photos using the MPEG-7 semantic description scheme, there are no standardized ways to retrieve the photos based on the annotation. In this paper we propose metrics for retrieval based on the MPEG-7 semantic description scheme and evaluate them in a digital photo retrieval scenario.},
  doi = {10.1109/ISM.2009.104},
  isbn10 = {978-1-4244-5231-6},
  language = {EN},
  talktype = {none}
}
@InProceedings{Kogler2009,
  author = {Kogler, Marian and Del Fabro, Manfred and Lux, Mathias and Schoeffmann, Klaus and Böszörmenyi, Laszlo},
  booktitle = {Proceedings of the 10th International Workshop of the Multimedia Metadata Community on Semantic Multimedia Database Technologies (SeMuDaTe'09) in conjunction with the 4th International Conference on Semantic and Digital Media Technologies (SAMT 2009)},
  title = {Global vs. Local Feature in Video Summarization: Experimental Results},
  year = {2009},
  address = {Aachen, Germany},
  editor = {Ralf, Klamma and Harald, Kosch and Lux, Mathias and Florian, Stegmaier},
  month = dec,
  pages = {6},
  publisher = {http://ceur-ws.org},
  language = {EN},
  talktype = {none},
  url = {http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-539/}
}
@InProceedings{Kofler2009c,
  author = {Kofler, Christoph and Lux, Mathias},
  booktitle = {MM '09 Proceedings of the 17th ACM international conference on Multimedia},
  title = {Dynamic presentation adaptation based on user intent classification.},
  year = {2009},
  address = {NA},
  editor = {Gao, Wen and Tui, Yong and Hanjalic, Alan},
  month = oct,
  pages = {1117-1118},
  publisher = {NA},
  abstract = {Results of internet searches are typically presented as lists. When searching for digital photos different search result presentations however offer different benefits. If users are primarily interested in the visual content of images a thumbnail grid may be more appropriate than a list. For people searching photos taken at a specific place image metadata in the result presentation is of interest too. In this paper we present an application which monitors a user's behavior while searching for digital photos and classifies the user's intention. Based on the intention, the result is adapted to support the user in an optimal way.},
  doi = {10.1145/1631272.1631526},
  language = {EN},
  talktype = {none},
  url = {http://dl.acm.org/citation.cfm?id=1631526}
}
@InProceedings{Kofler2009b,
  author = {Kofler, Christoph and Lux, Mathias},
  booktitle = {Proceedings of I-KNOW ’09 and I-SEMANTICS ’09},
  title = {An Exploratory Study on the Explicitness of User Intentions in Digital Photo Retrieval.},
  year = {2009},
  address = {Graz, Austria},
  editor = {Tochtermann, Klaus and Maurer, Hermann},
  month = sep,
  pages = {208-214},
  publisher = {TU Graz \& Know Center},
  abstract = {Search queries are typically interpreted as specification of information need of a user. Typically the search query is either interpreted as is or based on the context of a user, being for instance a user profile, his/her previously undertaken searches or any other background information. The actual intent of the user – the goal s/he wants to achieve with information retrieval – is an important part of a user’s context. In this paper we present the results of an exploratory study on the interplay between the goals of users and their search behavior in multimedia retrieval.},
  language = {EN},
  talktype = {none},
  url = {http://www.i-know.tugraz.at/2009/papers/an_exploratory_study_explicitness_user_intentions.pdf}
}