Semantic Technologies

In recent years the Semantic Web has emerged as one of the most essential achievements for the future of the World Wide Web (WWW). Semantic Web technology extends the WWW but also enables to improve applications which are related to other fields such as communication, information, knowledge, media, and interaction technologies. Semantic Web provides not just new technologies and tools but also new paradigms and ways of thinking, to make information processing more efficient and more structured.

Our research is focussed on the devolpment and improvement of 'semantically supported multimedia retrieval and search technologies'.

Current News
Prior Events and Activities
Research Topics
Research Team
Former Team Members
Teaching
Supervised Master Theses
Projects and Partners
In the Media
Recent Publications

Research Topics

(1) Semantic Multimedia

(2) Linked Data Engineering and Applications

(3) Semantically enhanced Information Retrieval (Semantic Search)

(4) Knowledge Mining and Ontological Engineering

(5) Semantically enriched e-Learning Applications

Job Offers

Student-Coworkers for Semantic Technologies
- Job Description English (PDF)
- Job Description German (PDF)

Research Team

Prof. Dr. Harald Sack (Senior Researcher, H-1.39, Tel.: -527)
Henning Agt-Rickauer (PhD student, H-1.40, Tel.: -515)
Christian Hentschel, M.Sc. (PhD student, H-1.38, Tel.: -540)
Dipl.-Inf. Magnus Knuth (PhD student, H-1.40, Tel.: -547)
Tabea Tietz, B.A. (Scientific coworker, H-1.40, Tel.: -548)
Dipl.-Inf. Jörg Waitelonis (PhD student, H-1.38, Tel.: -537)
Henrik Jürges (student coworker)
Fritz Meiners (student coworker)
Martin Zabel (student coworker)

Former Team Members

Dr. Olaf Hartig (PostDoc)
Dinesh Reddy, M.Sc.
Tamara Bobic, M.Sc.
Dipl.-Inf. Katarina Birghan
Bernhard Quehl, M.Sc.
Dr. Nadine Steinmetz
Dr. Haojin Yang
Dipl.-Inf. Lina Wolf
Dipl.-Dokumentar Johannes Hercher
Joscha Jäger, M.A. (internship)
Johannes Osterhoff, M.A.
Dipl.-Inf. Zalan Kramer

**Left to Right:** Nadine Steinmetz, Johannes Osterhoff, Dr. Harald Sack, Jörg Waitelonis, Christian Hentschel, Bernhard Quehl

Our group

Publications

Automated Recommendation of Related Model Elements for Domain Models.Agt-Rickauer, Henning; Kutsche, Ralf-Detlef; Sack, Harald (2019). 134--158.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1007/978-3-030-11030-7_7
Standardization and Automation of Audiovisual Annotations.Agt-Rickauer, Henning; Hentschel, Christian (2019).
[ Details ]

Weitere Informationen
VAMO – What Story Do You Want to Tell?Cabral, Felipe; Shah, Simran; Zhou, Zhiheng; Serth, Sebastian; Krogmann, Simon; Lötzsch, Winfried (2018).
[ Details ]

Weitere Informationen
AbstractAs technology improves it becomes more and more present in our everyday lives. Artificial Intel- ligence (AI) is a field of research that has existed for the past sixty years but only recently has it become ubiquitous. In the current context we live in, AI is present in smartphones and many ap- plications we use daily from search engines to image processing to recommendation engines. AI is finishing our sentences and learning our taste. Our team, comprised of three graduate students from Stanford University and three from Hasso Plattner Institute (HPI), Potsdam, has been approached by FutureWei Technologies to enhance human communication with Artificial Intelligence.
DoMoRe – A Recommender System for Domain Modeling.Agt-Rickauer, Henning; Kutsche, Ralf-Detlef; Sack, Harald (2018). 71-82.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.5220/0006555700710082
Authoring and Publishing Linked Open Film-Analytical Data.Agt-Rickauer, Henning; Aubert, Olivier; Hentschel, Christian; Sack, Harald (2018).
[ Details ]

Weitere Informationen
Semantic Annotation and Automated Extraction of Audio-Visual Staging Patterns in Large-Scale Empirical Film Studies.Agt-Rickauer, Henning; Hentschel, Christian; Sack, Harald (2018).
[ Details ]

Weitere Informationen
Serving Live Multimedia for the Linked Open Data Cloud.Serth, Sebastian; Haarmann, Stephan; Faber, Lukas in Lecture Notes in Informatics, M. Eibl, Gaedke, M. (reds.) (2017). (Vol. P-275) 2487-2498.
[ Details ]

Weitere Informationen
HerausgeberEibl, Maximilian and Gaedke, Martin
URNhttp://dx.doi.org/10.18420/in2017_252
AbstractDBpedia is a community-driven project to extract semantic data fromWikipedia articles. It publishes the results as RDF data in the Linked Open Data Cloud.With DBpedia Live, the community enabled live updates of linked data using the OAI-PMH protocol to receive and process changes on Wikipedia. The MediaWiki foundation discontinued their support for OAI-PMH in March 2016 causing DBpedia Live to no longer receive live updates. In this work, we use RCStream, the new MediaWiki protocol to notify other systems of changes, to re-enable live updates in DBpedia Live. Currently, users need to consume two DBpedia resources to access general information and multimedia files about one entity. On the one hand DBpedia holds the structured information. On the other DBpedia Commons holds most multimedia information. We improve the integration of multimedia data into DBpedia by introducing a new extractor to the DBpedia Extraction Framework that extracts most multimedia data from a Wikipedia page. Additionally, we present two further extractors that link pages in DBpedia with pages in DBpedia Commons and vice versa. All our changes are available in the DBpedia Extraction Framework and in use, e.g. for DBpedia Live.
Guilt-by-Association: Detecting Malicious Entities via Graph Mining.Najafi, Pejman; Sapegin, Andrey; Cheng, Feng; Meinel, Christoph (2017). 88--107.
[ Details ]

Weitere Informationen
AbstractIn this paper, we tackle the problem of detecting malicious domains and IP addresses using graph inference. In this regard, we mine proxy and DNS logs to construct an undirected graph in which vertices represent domain and IP address nodes, and the edges represent relationships describing an association between those nodes. More specifically, we investigate three main relationships: subdomainOf, referredTo, andresolvedTo. We show that by providing minimal ground truth information, it is possible to estimate the marginal probability of a domain or IP node being malicious based on its association with other malicious nodes. This is achieved by adopting belief propagation, i.e., an efficient and popular inference algorithm used in probabilistic graphical models. We have implemented our system in Apache Spark and evaluated using one day of proxy and DNS logs collected from a global enterprise spanning over 2 terabytes of disk space. In this regard, we show that our approach is not only efficient but also capable of achieving high detection rate (96% TPR) with reasonably low false positive rates (8% FPR). Furthermore, it is also capable of fixing errors in the ground truth as well as identifying previously unknown malicious domains and IP addresses. Our proposal can be adopted by enterprises to increase both the quality and the quantity of their threat intelligence and blacklists using only proxy and DNS logs.
Exploring Large Movie Collections: Comparing Visual Berrypicking and Traditional Browsing.Low, Thomas; Hentschel, Christian; Stober, Sebastian; Sack, Harald; Nürnberger, Andreas (2017). 198--208.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1007/978-3-319-51814-5_17
Data Integration for the Media Value Chain.Agt-Rickauer, Henning; Waitelonis, Jörg; Tietz, Tabea; Sack, Harald in 1690 (2016).
[ Details ]

Weitere Informationen
openSAP: Evaluating xMOOC Usage and Challenges for Scalable and Open Enterprise Education.Renz, Jan; Schwerer, Florian; Meinel, Christoph (2016).
[ Details ]

Weitere Informationen
Fine tuning CNNS with scarce training data - Adapting imagenet to art epoch classification.Hentschel, Christian; Wiradarma, Timur Pratama; Sack, Harald (2016). 3693-3697.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1109/ICIP.2016.7533049
AbstractDeep Convolutional Neural Networks (CNN) have recently been shown to outperform previous state of the art approaches for image classification. Their success must in parts be attributed to the availability of large labeled training sets such as provided by the ImageNet benchmarking initiative. When training data is scarce, however, CNNs have proven to fail to learn descriptive features. Recent research shows that supervised pre-training on external data followed by domain-specific fine-tuning yields a significant performance boost when external data and target domain show similar visual characteristics. Transfer-learning from a base task to a highly emphdissimilar target task, however, has not yet been fully investigated. In this paper, we analyze the performance of different feature representations for classification of paintings into art epochs. Specifically, we evaluate the impact of training set sizes on CNNs trained with and without external data and compare the obtained models to linear models based on Improved Fisher Encodings. Our results underline the superior performance of fine-tuned CNNs but likewise propose Fisher Encodings in scenarios were training data is limited.
Quantitative Analysis of Art Market Using Ontologies, Named Entity Recognition and Machine Learning: A Case Study.Filipiak, Dominik; Agt-Rickauer, Henning; Hentschel, Christian; Filipowska, Agata; Sack, Harald (2016). 79-90.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/http://dx.doi.org/10.1007/978-3-319-39426-8_7
Evaluating Query and Storage Strategies for RDF Archives.Fernández, Javier D.; Umbrich, Jürgen; Polleres, Axel; Knuth, Magnus (2016). 41--48.
[ Details ]

Weitere Informationen
AbstractThere is an emerging demand on efficiently archiving and (temporal) querying different versions of evolving semantic Web data. As novel archiving systems are starting to address this challenge, foundations/standards for benchmarking RDF archives are needed to evaluate its storage space efficiency and the performance of different retrieval operations. To this end, we provide theoretical foundations on the design of data and queries to evaluate emerging RDF archiving systems. Then, we instantiate these foundations along a concrete set of queries on the basis of a real-world evolving dataset. Finally, we perform an empirical evaluation of various current archiving techniques and querying strategies on this data. Our work comprises -- to the best of our knowledge -- the first benchmark for querying evolving RDF data archives.
I am a Machine, let me understand Web Media!.Knuth, Magnus; Waitelonis, Jörg; Sack, Harald in LNCS (2016). 467--475.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1007/978-3-319-38791-8_33
Pre-Course Key Segment Analysis of Online Lecture Videos.Che, Xiaoyin; Staubitz, Thomas; Yang, Haojin; Meinel, Christoph (2016).
[ Details ]

Weitere Informationen
AbstractIn this paper we propose a method to evaluate the importance of lecture video segments in online courses. The video will be first segmented based on the slide transition. Then we evaluate the importance of each segment based on our analysis of the teacher’s focus. This focus is mainly identified by exploring features in the slide and the speech. Since the whole analysis process is based on multimedia materials, it could be done before the official start of the course. By setting survey questions and collecting forum statistics in the MOOC “Web Technologies”, the proposed method is evaluated. Both the general trend and the high accuracy of selected key segments (over 70%) prove the effectiveness of the proposed method.
Joint proceedings of the 2nd Workshop on Managing the Evolution and Preservation of the Data Web (MEPDaW 2016) and the 3rd Workshop on Linked Data Quality (LDQ 2016)Debattista, Jeremy; Fernández, Javier D.; Knuth, Magnus; Kontokostas, Dimitris; Rula, Anisa; Umbrich, Jürgen; Zaveri, Amrapali in CEUR Workshop Proceedings (2016). CEUR.org.
[ Details ]

Weitere Informationen
AbstractThis joint volume of proceedings gathers together papers from the 2nd Workshop on Managing the Evolution and Preservation of the Data Web (MEPDaW) and the 3rd Workshop on Linked Data Quality (LDQ), held on the 30th of May of 2016 during the 13th ESWC conference in Anissaras, Crete, Greece.
DBpedia Links: The Hub of Links for the Web of Data.Dojchinovski, Milan; Kontokostas, Dimitris; Rößling, Robert; Knuth, Magnus; Hellmann, Sebastian (2016).
[ Details ]

Weitere Informationen
AbstractLinks are the key enabler for retrieval of related information on the Web of Data. Currently, DBpedia is one of the central interlinking hubs in the Linked Open Data (LOD) cloud. With over 28 million of described and localized things it is one of the largest and open datasets. With the increasing number of linked datasets, there is need for proper maintenance of these links. In this paper, we describe the DBpedia Links repository, which maintains linksets between DBpedia and other LOD datasets. We describe the system for maintenance, update and quality assurance of the linksets.
Scheduling Refresh Queries for Keeping Results from a SPARQL Endpoint Up-to-Date (Extended Version).Knuth, Magnus; Hartig, Olaf; Sack, Harald in CoRR (2016). abs/1608.08130
[ Details ]

Weitere Informationen
AbstractMany datasets change over time. As a consequence, long-running applications that cache and repeatedly use query results obtained from a SPARQL endpoint may resubmit the queries regularly to ensure up-to-dateness of the results. While this approach may be feasible if the number of such regular refresh queries is manageable, with an increasing number of applications adopting this approach, the SPARQL endpoint may become overloaded with such refresh queries. A more scalable approach would be to use a middle-ware component at which the applications register their queries and get notified with updated query results once the results have changed. Then, this middle-ware can schedule the repeated execution of the refresh queries without overloading the endpoint. In this paper, we study the problem of scheduling refresh queries for a large number of registered queries by assuming an overload-avoiding upper bound on the length of a regular time slot available for testing refresh queries. We investigate a variety of scheduling strategies and compare them experimentally in terms of time slots needed before they recognize changes and number of changes that they miss.
Scheduling Refresh Queries for Keeping Results from a SPARQL Endpoint Up-to-Date.Knuth, Magnus; Hartig, Olaf; Sack, Harald (2016).
[ Details ]

Weitere Informationen
AbstractMany datasets change over time. As a consequence, long-running applications that cache and repeatedly use query results obtained from a SPARQL endpoint may resubmit the queries regularly to ensure up-to-dateness of the results. While this approach may be feasible if the number of such regular refresh queries is manageable, with an increasing number of applications adopting this approach, the SPARQL endpoint may become overloaded with such refresh queries. A more scalable approach would be to use a middle-ware component at which the applications register their queries and get notified with updated query results once the results have changed. Then, this middle-ware can schedule the repeated execution of the refresh queries without overloading the endpoint. In this paper, we study the problem of scheduling refresh queries for a large number of registered queries by assuming an overload-avoiding upper bound on the length of a regular time slot available for testing refresh queries. We investigate a variety of scheduling strategies and compare them experimentally in terms of time slots needed before they recognize changes and number of changes that they miss.
Don't compare Apples to Oranges - Extending GERBIL for a fine grained NEL evaluation.Waitelonis, Jörg; Jürges, Henrik; Sack, Harald (2016).
[ Details ]

Weitere Informationen
AbstractIn recent years, named entity linking (NEL) tools were primarily developed as general approaches, whereas today numerous tools are focusing on specific domains such as e.g. the mapping of persons and organizations only, or the annotation of locations or events in microposts. However, the available benchmark datasets used for the evaluation of NEL tools do not respect this focalizing trend. We have analyzed the evaluation process applied in the NEL benchmarking framework GERBIL and its benchmark datasets. Based on these insights we extend the GERBIL framework to enable a more fine grained evaluation and in deep analysis of the used benchmark datasets according to different emphases. In this paper, we present the implementation of an adaptive filter for arbitrary entities as well as a system to automatically measure benchmark dataset properties, such as the extent of content-related ambiguity and diversity. The implementation as well as a result visualization are integrated in the publicly available GERBIL framework.
Semantic Annotation and Information Visualization for Blogposts with refer.Tietz, Tabea; Jäger, Joscha; Waitelonis, Jörg; Sack, Harald (2016). (Vol. 1704) 28 - 40.
[ Details ]

Weitere Informationen
refer: a Linked Data based Text Annotation and Recommender System for Wordpress.Tietz, Tabea; Waitelonis, Jörg; Jäger, Joscha; Sack, Harald in CEUR-WS (2016). (Vol. 1690)
[ Details ]

Weitere Informationen
Improving text recognition by distinguishing scene and overlay textQuehl, Bernhard; Yang, Haojin; Sack, Harald (2015). (Vol. 9445) 944509. SPIE.
[ Details ]

Weitere Informationen
An Improved System For Real-Time Scene Text Recognition.Yang, Haojin; Wang, Cheng; Che, Xiaoyin; Luo, Sheng; Meinel, Christoph (2015). 657-660.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1145/2671188.2749352
AbstractIn this paper we showcase a system for real-time text detection and recognition. We apply deep features created by Convolutional Neural Networks (CNNs) for both text detection and word recognition task. For text detection we follow the common localization-verification scheme which already shown its excellent ability in numerous previous work. In text localization stage, textual regions are roughly detected by using a MSERs (Maximally Stable Extremal Regions) detector with high recall rate. False alarms are then eliminated by using a CNNs classifier, and remaining text regions are further grouped into words. In the word recognition stage, we developed an skeleton-based text binarization method for segmenting text from its background. A CNNs based recognizer is then applied for recognizing character. The initial experiments show the powerful ability of deep features for text classification comparing with commonly used visual features. Our current implementation demonstrates real-time performance for recognizing scene text by using a standard PC with webcam.
Enhance Lecture Archive Search with OCR Slide Detection and In-Memory Database Technology.Malchow, Martin; Bauer, Matthias; Meinel, Christoph (2015). 176-183.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1109/CSE.2015.19
AbstractOn the Web there are a lot of frequently used video lecture archives which have grown up fast during the last couple of years. This fact led to a lot of lecture recordings which include knowledge for a variety of subjects. The typical way of searching these videos is by title and description. Unfortunately, not all important keywords and facts are mentioned in the title or description if they are available. Furthermore, there is no possibility to analyze how important those detected keywords are for the whole video. Another lecture archive specific virtue is that every regular university lecture is repeated yearly. Normally this will lead to duplicate lecture recordings. In search results doubling is disturbing for students when they want to watch the most recent lectures from the search result. This paper deals with the idea to resolve these problems by analyzing the recorded lecture slides with Optical Character Recognition (OCR). In addition to the name and description the OCR data will be used for a full text analysis to create an index for the lecture archive search. Furthermore, a fuzzy search is introduced. This will solve the issue of misspelled search requests and OCR detection defects. Additionally, this paper deals with the performance issues of a full text search with an in-memory database, issues in OCR detection, handling duplicate recordings of lectures repeated every year. Finally, an evaluation of the search performance in comparison with other database ideas besides the in-memory database is performed. Additionally, a user acceptability survey for the search results to increase the learning experience on lecture archives was performed. As a result, this paper shows how to handle the big amount of OCR data for a full text live search performed on an in-memory database in reasonable time. During this search a fuzzy search is performed additionally to resolve spelling mistakes and OCR detection problems. In conclusion this paper shows a solution for an enhanced video lecture archive search that supports students in online research processes and enhances their learning experience.
Proceedings of the 2nd Workshop on Linked Data Quality co-located with 12th Extended Semantic Web Conference (ESWC 2015)Rula, Anisa; Zaveri, Amrapali; Knuth, Magnus; Kontokostas, Dimitris (2015). (Vol. 1376) CEUR-WS.org, Portorož, Slovenia.
[ Details ]

Weitere Informationen
HerausgeberRula, Anisa and Zaveri, Amrapali and Knuth, Magnus and Kontokostas, Dimitris
Towards Linked Data Update Notifications - Reviewing and Generalizing the sparqlPuSH approach.Knuth, Magnus; Reddy, Dinesh; Dimou, Anastasia; Vahdati, Sahar; Kastrinakis, George A. Dimou, van Ossenbruggen, J., Vidal, M. -E., Sande, M. V. (reds.) (2015).
[ Details ]

Weitere Informationen
HerausgeberDimou, Anastasia and van Ossenbruggen, Jacco and Vidal, Maria-Esther and Sande, Miel Vander
The DBpedia Events Dataset.Knuth, Magnus; Lehmann, Jens; Kontokostas, Dimitris; Steiner, Thomas; Sack, Harald S. Villata, Pan, J. Z., Dragoni, M. (reds.) (2015).
[ Details ]

Weitere Informationen
HerausgeberVillata, Serena and Pan, Jeff Z. and Dragoni, Mauro
DBpedia Commons: Structured Multimedia Metadata from the Wikimedia Commons.Vaidya, Gaurav; Kontokostas, Dimitris; Knuth, Magnus; Lehmann, Jens; Hellmann, Sebastian in Lecture Notes in Computer Science, M. Arenas, Corcho, O., Simperl, E., Strohmaier, M., d'Aquin, M., Srinivas, K., Groth, P. T., Dum, M. (reds.) (2015). (Vol. 9367) 281--289.
[ Details ]

Weitere Informationen
HerausgeberArenas, Marcelo and Corcho, Oscar and Simperl, Elena and Strohmaier, Markus and d'Aquin, Mathieu and Srinivas, Kavitha and Groth, Paul T. and Dum, Michel
Adaptive E-Lecture Video Outline Extraction Based on Slides Analysis.Che, Xiaoyin; Yang, Haojin; Meinel, Christoph (2015). 59-68.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1007/978-3-319-25515-6_6
AbstractIn this paper, we propose an automated adaptive solution to generate logical, accurate and detailed tree-structure outline for video-based online lectures, by extracting the attached slides and reconstructing their content. The proposed solution begins with slide-transition detection and optical character recognition, and then proceeds by a static method of analyzing the layout of single slide and the logical relations within the slides series. Some features about the under-processing slides series, such as a �xed title position, will be �gured out and applied in the adaptive rounds to improve the outline quality. The result of our experiments shows that the general accuracy of the �nal lecture outline reaches 85%, which is about 13% higher than the static method.
FRanCo - A Ground Truth Corpus for Fact Ranking Evaluation.Bobic, Tamara; Waitelonis, Joerg; Sack, Harald G. Cheng, Gunaratna, K., Thalhammer, A. (reds.) (2015).
[ Details ]

Weitere Informationen
HerausgeberCheng, Gong and Gunaratna, Kalpa and Thalhammer, Andreas
AbstractThe vast amount of information on the Web poses a challenge when trying to identify the most important facts. Many fact ranking algorithms have emerged, however, thus far there is a lack of a general domain, objective gold standard that would serve as an evaluation benchmark for comparing such systems. We present FRanCo, a ground truth for fact ranking acquired using crowdsourcing. The corpus is built on a representative DBpedia sample of 541 entities and made freely available. We have published both the aggregated and the raw data collected, including identified nonsense statements that contribute to improving data quality in DBpedia.
Optimizing the Video Experience in MOOCs.Renz, Jan; Bauer, Matthias; Malchow, Martin; Staubitz, Thomas; Meinel, Christoph (2015).
[ Details ]

Weitere Informationen
PatchR: A Framework for Linked Data Change Requests.Knuth, Magnus; Sack, Harald in International Journal on Semantic Web and Information Systems (IJSWIS) (2015). 11(1) 30-45.
[ Details ]

Weitere Informationen
TailR: A Platform for Preserving History on the Web of Data.Meinhardt, Paul; Knuth, Magnus; Sack, Harald A. Polleres, Pellegrini, T., Hellmann, S., Parreira, J. X. (reds.) (2015). 57-64.
[ Details ]

Weitere Informationen
HerausgeberPolleres, Axel and Pellegrini, Tassilo and Hellmann, Sebastian and Parreira, Josiane Xavier
WaSABi 2014: Breakout Brainstorming Session Summary.Coppens, Sam; Hammar, Karl; Knuth, Magnus; Neumann, Marco; Ritze, Dominique; Sande, Miel Vander in CEUR Workshop Proceedings, Á. García-Crespo, Berbís, J. M. G., Radzimski, M., Sánchez-Cervantes, J. L., Coppens, S., Hammar, K., Knuth, M., Neumann, M., Ritze, D., Sande, M. V. (reds.) (2014).
[ Details ]

Weitere Informationen
HerausgeberGarcía-Crespo, Ángel and Berbís, Juan Miguel Gómez and Radzimski, Mateusz and Sánchez-Cervantes, José Luis and Coppens, Sam and Hammar, Karl and Knuth, Magnus and Neumann, Marco and Ritze, Dominique and Sande, Miel Vander
Linked Data Cleansing and Change Management.Knuth, Magnus in Lecture Notes in Computer Science, P. Lambrix, Hyvönen, E., Blomqvist, E., Presutti, V., Qi, G., Sattler, U., Ding, Y., Ghidini, C. (reds.) (2014). (Vol. 8982) 201-208.
[ Details ]

Weitere Informationen
HerausgeberLambrix, Patrick and Hyvönen, Eero and Blomqvist, Eva and Presutti, Valentina and Qi, Guilin and Sattler, Uli and Ding, Ying and Ghidini, Chiara
URNhttp://dx.doi.org/10.1007/978-3-319-17966-7_29
Smart Media Navigator: Visualizing Recommendations based on Linked Data.Tietz, Tabea; Waitelonis, Jörg; Jäger, Joscha; Sack, Harald (2014). 48 - 51.
[ Details ]

Weitere Informationen
Data Cleansing Consolidation with PatchR.Knuth, Magnus; Sack, Harald in Lecture Notes in Computer Science, Presutti, V.,, Blomqvist,, E.,, Troncy,, R.,, Sack,, H.,, Papadakis,, I.,, Tordai,, A., (reds.) (2014). (8798 ed)
[ Details ]

Weitere Informationen
HerausgeberPresutti and V. and Blomqvist and E. and Troncy and R. and Sack and H. and Papadakis and I. and Tordai and A.
Linked Data Quality: Identifying and Tackling the Key Challenges.Knuth, Magnus; Kontokostas, Dimitris; Sack, Harald in CEUR Workshop Proceedings (2014).
[ Details ]

Weitere Informationen
Proceedings of the 1st Workshop on Linked Data Quality (LDQ)Knuth, Magnus; Kontokostas, Dimitris; Sack, Harald in CEUR Workshop Proceedings (2014). CEUR-WS.org, Leipzig, Germany.
[ Details ]

Weitere Informationen
HerausgeberKnuth, Magnus and Kontokostas, Dimitris and Sack, Harald
Joint Proceedings of the Second International Workshop on Semantic Web Enterprise Adoption and Best Practice and Second International Workshop on Finance and Economics on the Semantic Web Co-located with 11th European Semantic Web ConferenceGarcía-Crespo, Ángel; Berbís, Juan Miguel Gómez; Radzimski, Mateusz; Sánchez-Cervantes, José Luis; Coppens, Sam; Hammar, Karl; Knuth, Magnus; Neumann, Marco; Ritze, Dominique; Sande, Miel Vander in CEUR Workshop Proceedings (2014). CEUR-WS.org, Anissaras, Crete, Greece.
[ Details ]

Weitere Informationen
HerausgeberGarcía-Crespo, Ángel and Berbís, Juan Miguel Gómez and Radzimski, Mateusz and Sánchez-Cervantes, José Luis and Coppens, Sam and Hammar, Karl and Knuth, Magnus and Neumann, Marco and Ritze, Dominique and Sande, Miel Vander
openHPI - a Case-Study on the Emergence of two Learning Communities.Grünewald, Franka; Mazandarani, Elnaz; Meinel, Christoph; Teusner, Ralf; Totschnig, Michael; Willems, Christian (2013).
[ Details ]

Weitere Informationen
AbstractRecently a new format of online education has emerged that combines video lectures, interactive quizzes and social learning into an event that aspires to attract a massive number of participants. This format, referred to as Massive Open Online Course (MOOC), has garnered considerable public attention, and has been invested with great hopes (and fears) of transforming higher education by opening up the walls of closed institutions to a world-wide audience. In this paper, we present two MOOCs that were hosted at the same platform, and have implemented the same learning design. Due to their difference in language, topic domain and difficulty, the communities that they brought into existence were very different. We start by describing the MOOC format in more detail, and the distinguishing features of openHPI. We then discuss the literature on communities of practice and cultures of participation. After some statistical data about the first openHPI course, we present our qualitative observations about both courses, and conclude by giving an outlook on an ongoing comparative analysis of the two courses.
Tree-structure Outline Generation for Lecture Videos with Synchronized Slides.Che, Xiaoyin; Yang, Haojin; Meinel, Christoph (2013). 87-92.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1109/ICeLeTE.2013.6644353
AbstractIn this paper we propose a solution to generate tree-structure outline for lecture videos by analyzing their synchronized slides, by which detailed lecture overview can be automatically provided to E-learning portal users. Starting with OCR (Optical Character Recognition) result, we reconstruct the content of each slide. After that, we explore logical relations between slides, in order to make them hierarchical. And all potential redundant content will also be removed. Our evaluation shows that, based on our test dataset, the final outline achieved retains about 1/4 of the original texts from all slides and is organized well in an up-to-6-level tree structure. Furthermore, the average accuracy of all slide titles, which are undoubtedly the most important information, reaches 86%.
Semantic Multimedia Information Retrieval Based on Contextual Descriptions.Steinmetz, Nadine; Sack, Harald (2013).
[ Details ]

Weitere Informationen
CONTENTUS - technologies for next generation multimedia libraries.Nandzik, Jan; Litz, Berenike; Flores-Herr, Nicolas; Löhden, Aenne; Konya, Iuliu; Baum, Doris; Bergholz, André; Schönfuß, Dirk; Fey, Christian; Osterhoff, Johannes; Waitelonis, Jörg; Sack, Harald; Köhler, Ralf; Ndjiki-Nya, Patrick in Multimedia Tools and Applications (2013). 63(2) 287-329.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/doi:10.1007/s11042-011-0971-2
AbstractAn ever-growing amount of digitized content urges libraries and archives to integrate new media types from a large number of origins such as publishers, record labels and film archives, into their existing collections. This is a challenging task, since the multimedia content itself as well as the associated metadata is inherently heterogeneous—the different sources lead to different data structures, data quality and trustworthiness. This paper presents the contentus approach towards an automated media processing chain for cultural heritage organizations and content holders. Our workflow allows for unattended processing from media ingest to availability thorough our search and retrieval interface. We aim to provide a set of tools for the processing of digitized print media, audio/visual, speech and musical recordings. Media specific functionalities include quality control for digitization of still image and audio/visual media and restoration of the most common quality issues encountered with these media. Furthermore, the contentus tools include modules for content analysis like segmentation of printed, audio and audio/visual media, optical character recognition (OCR), speech-to-text transcription, speaker recognition and the extraction of musical features from audio recordings, all aimed at a textual representation of information inherent within the media assets. Once the information is extracted and transcribed in textual form, media independent processing modules offer extraction and disambiguation of named entities and text classification. All contentus modules are designed to be flexibly recombined within a scalable workflow environment using cloud computing techniques. In the next step analyzed media assets can be retrieved and consumed through a search interface using all available metadata. The search engine combines Semantic Web technologies for representing relations between the media and entities such as persons, locations and organizations with a full-text approach for searching within transcribed information gathered through the preceding processing steps. The contentus unified search interface integrates text, images, audio and audio/visual content. Queries can be narrowed and expanded in an exploratory manner, search results can be refined by disambiguating entities and topics. Further, semantic relationships become not only apparent, but can also be navigated.
Statistical Analyses of Named Entity Disambiguation Benchmarks.Steinmetz, Nadine; Knuth, Magnus; Sack, Harald (2013).
[ Details ]

Weitere Informationen
Linked Soccer Data.Bergmann, Tanja; Bunk, Stefan; Eschrig, Johannes; Hentschel, Christian; Knuth, Magnus; Sack, Harald; Schüler, Ricarda (2013).
[ Details ]

Weitere Informationen
openHPI: Evolution of a MOOC Platform from LMS to SOA.Totschnig, Michael; Willems, Christian; Meinel, Christoph (2013). 49-54.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.5220/0004416905930598
Lecture Video Segmentation by Automatically Analyzing the Synchronized Slides.Che, Xiaoyin; Yang, Haojin; Meinel, Christoph (2013). 345-348.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1145/2502081.2508115
AbstractIn this paper we propose a solution which segments lecture video by analyzing its supplementary synchronized slides. The slides content derives automatically from OCR (Optical Character Recognition) process with an approximate accuracy of 90%. Then we partition the slides into different subtopics by examining their logical relevance. Since the slides are synchronized with the video stream, the subtopics of the slides indicate exactly the segments of the video. Our evaluation reveals that the average length of segments for each lecture is ranged from 5 to 15 minutes, and 45% segments achieved from test datasets are logically reasonable.
Open Up Cultural Heritage in Video Archives with Mediaglobe.Hentschel, Christian; Hercher, Johannes; Knuth, Magnus; Osterhoff, Johannes; Quehl, Bernhard; Sack, Harald; Steinmetz, Nadine; Waitelonis, Jörg; Yang, Haojin in Lecture Notes in Informatics (2012).
[ Details ]

Weitere Informationen
Text Detection in Video Images Using Adaptive Edge Detection and Stroke Width Verification.Haojin Yang, Bernhard Quehl; Sack, Harald (2012).
[ Details ]

Weitere Informationen
Towards exploratory video search using linked data.Waitelonis, Jörg; Sack, Harald in Multimedia Tools and Applications (2012). 59(2) 645 - 672.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/doi:10.1007/s11042-011-0733-1
AbstractKeyword-based search in general is particularly applicable if the searcher really knows what she is looking for and how to find it, i.e. to know the appropriate keywords to obtain the desired results. But in many cases either the objectives of the searcher are intrinsically fuzzy or she is not aware of the appropriate keywords. One way to solve this problem is to navigate and explore the search space along guided routes. In this paper we show, how Linked Open Data can be adopted to facilitate an exploratory semantic search for video data. We present a prototype implementation of exploratory video search and show how traditional keyword-based search can be augmented by the use of Linked Open Data.
Automated Extraction of Lecture Outlines from Lecture Videos: a Hybrid Solution for Lecture Video Indexing.Yang, Haojin; Gruenewald, Franka; Meinel, Christoph (2012).
[ Details ]

Weitere Informationen
Cross-Dataset Learning of Visual Concepts In: Adaptive Multimedia Retrieval: User, Context, and Feedback.Hentschel, Chirstian; Sack, Harald; Steinmetz, Nadine (2012).
[ Details ]

Weitere Informationen
A framework for improved video text detection and recognition.YANG, Haojin; Quehl, Bernhard; Sack, Harald in Multimedia Tools and Applications (2012). 69(1) 217-245.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/doi:10.1007/s11042-012-1250-6
AbstractText displayed in a video is an essential part for the high-level semantic information of the video content. Therefore, video text can be used as a valuable source for automated video indexing in digital video libraries. In this paper, we propose a workflow for video text detection and recognition. In the text detection stage, we have developed a fast localization-verification scheme, in which an edge-based multi-scale text detector first identifies potential text candidates with high recall rate. Then, detected candidate text lines are refined by using an image entropy-based filter. Finally, Stroke Width Transform (SWT)- and Support Vector Machine (SVM)-based verification procedures are applied to eliminate the false alarms. For text recognition, we have developed a novel skeleton-based binarization method in order to separate text from complex backgrounds to make it processible for standard OCR (Optical Character Recognition) software. Operability and accuracy of proposed text detection and binarization methods have been evaluated by using publicly available test data sets.
DBpedia Ontology Enrichment for Inconsistency Detection.Töpper, Gerald; Knuth, Magnus; Sack, Harald (2012).
[ Details ]

Weitere Informationen
Evaluating Entity Summarization Using a Game-Based Ground Truth.Thalhammer, Andreas; Knuth, Magnus; Sack, Harald (2012).
[ Details ]

Weitere Informationen
A Skeleton based Binarization Approach for Video Text Recognition.Yang, Haojin; Quehl, Bernhard; Sack, Harald (2012).
[ Details ]

Weitere Informationen
Open Up Cultural Heritage in Video Archives with Mediaglobe.Hentschel, Christian; Hercher, Johannes; Knuth, Magnus; Osterhoff, Johannes; Quehl, Bernhard; Sack, Harald; Steinmetz, Nadine; Waitelonis, Jörg; Yang, Haojin in Lecture Notes in Informatics (2012).
[ Details ]

Weitere Informationen
Collaboratively Patching Linked Data.Knuth, Magnus; Hercher, Johannes; Sack, Harald (2012). 33-40.
[ Details ]

Weitere Informationen
An Automated Analysis and Indexing Framework for Lecture Video Portal.Yang, Haojin; Oehlke, Christoph; Meinel, Christoph in lecture notes in computer science (2012). 285--294.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1007/978-3-642-33642-3
WhoKnows? - Evaluating Linked Data Heuristics with a Quiz that Cleans Up DBpedia.Ludwig, Nadine; Waitelonis, Jörg; Knuth, Magnus; Sack, Harald in LNCS (2011).
[ Details ]

Weitere Informationen
Automatic Lecture Video Indexing Using Video OCR Technology.Yang, Haojin; Siebert, Maria; Lühne, Patrick; Sack, Harald; Meinel, Christoph (2011).
[ Details ]

Weitere Informationen
More than the Sum of its Parts: CONTENTUS -- A Semantic Multimodal Search User Interface.Waitelonis, Jörg; Osterhoff, Johannes P.; Sack, Harald in CEUR Workshop Proceedings (2011). (Vol. 694)
[ Details ]

Weitere Informationen
AbstractThis paper presents the semantic search engine CONTENTUS and its user interface, a multimedia retrieval sys- tem developed in the context of the German research project THESEUS.This interface uses content-based suggestions and a multi-modal presentation of search results to support semantic search. In addition, the system deploys a combi- nation of a facetted browsing and breadcrumb-based navi- gation, a time-line enables time based filtering of the search results and the system suggests related search results according to the user’s preferences. Finally, CONTENTUS has become more than the sum of its parts. Its unique feature combination facilitates search to become a more efficient and overall more pleasant user experience.
Lecture Video Indexing and Analysis Using Video OCR Technology.Yang, Haojin; Siebert, Maria; Lühne, Patrick; Sack, Harald; Meinel, Christoph (2011).
[ Details ]

Weitere Informationen
Lecture Video Indexing and Analysis Using Video OCR Technology.Yang, Haojin; Sack, Harald; Meinel, Christoph in International Journal of Multimedia Processing and Technologies (JMPT) (2011). 2(4) 176-196.
[ Details ]

Weitere Informationen
AbstractTexts displayed in lecture videos are closely related to the lecture content. Therefore, they provide a valuable source for indexing and retrieving lecture videos. Textual content can be detected, extracted and analyzed automatically by video OCR (Optical Character Recognition) techniques. In this paper, we present an approach for automated lecture video indexing based on video OCR technology: first, we developed a novel video segmenter for the structure analysis of slide videos. Having adopted a localization and verification scheme, we perform text detection secondly. We apply SWT (Stroke Width Transform) not only to remove false alarms from the text detection stage, but also to analyze the slide structure further. To recognize texts, a multi-hypotheses framework is applied, that consists ofmultiple text binarization, OCR, spell checking and result merging processes. Finally, we have implemented a novel algorithm for extracting lecture structure from the OCR-transcript by using geometrical information and text strokewidth of detected text lines. We use both segmented key frames and extracted lecture outlines for the further videoindexing. The accuracy of the proposed approach is proven by evaluation.
Towards exploratory video search using linked data.Waitelonis, Jörg; Sack, Harald (2011). (Vol. 53) 1-28.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1007/s11042-011-0733-1
A Solution for German Speech Recognition for Analysis and Processing of Lecture Videos.Yang, Haojin; Oehlke, Christoph; Meinel, Christoph (2011).
[ Details ]

Weitere Informationen
Sneak Preview? Instantly Know What To Expect In Faceted Browsing.Osterhoff, Johannes; Waitelonis, Jörg; Jäger, Joscha; Sack, Harald (2011).
[ Details ]

Weitere Informationen
Improving Search in Tele-Lecturing: Using Folksonomies as Trigger to Query Semantic Datasets to Extract Additional Metadata.Franka Moritz, Maria Siebert; Meinel, Christoph (2011).
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/1988688.1988731
WhoKnows? - Evaluating Linked Data Heuristics with a Quiz that Cleans Up DBpedia.Waitelonis, Jörg; Ludwig, Nadine; Knuth, Magnus; Sack, Harald (2011). (Vol. 8) 236-248.
[ Details ]

Weitere Informationen
Whoknows? - Evaluating Linked Data Heuristics with a Quiz that cleans up DBpedia.Waitelonis, Jörg; Ludwig, Nadine; Knuth, Magnus; Sack, Harald in International Journal of Interactive Technology and Smart Education (ITSE) (2011). 8(4) 236-248.
[ Details ]

Weitere Informationen
AbstractPurpose – Linking Open Data (LOD) provides a vast amount of well structured semantic information, but many inconsistencies may occur, especially if the data are generated with the help of automated methods. Data cleansing approaches enable detection of inconsistencies and overhauling of affected data sets, but they are difficult to apply automatically. The purpose of this paper is to present WhoKnows?, an online quiz that generates different kinds of questionnaires from DBpedia data sets. Design/methodology/approach – Besides its playfulness, WhoKnows? has been developed for the evaluation of property relevance ranking heuristics on DBpedia data, with the convenient side effect of detecting inconsistencies and doubtful facts. Findings – The original purpose for developing WhoKnows? was to evaluate heuristics to rank LOD properties and thus, obtain a semantic relatedness between entities according to the properties by which they are linked. The presented approach is an efficient method to detect popular properties within a limited amount of triples. Ongoing work continues in the development of sound property ranking heuristics for the purpose of detecting the most relevant characteristics of entities. Originality/value – WhoKnows? uses the approach of “Games with a Purpose” to detect inconsistencies in Linked Data and score properties to rank them for sophisticated semantic search scenarios.
The Generation of User Interest Profiles from Semantic Quiz Games.Knuth, Magnus; Ludwig, Nadine; Wolf, Lina; Sack, Harald (2011).
[ Details ]

Weitere Informationen
RISQ! Renowned Individuals Semantic Quiz – A Jeopardy like Quiz Game for Ranking Facts.Wolf, Lina; Knuth, Magnus; Osterhoff, Johannes; Sack, und Harald in ICPS (2011).
[ Details ]

Weitere Informationen
Community Tagging in Tele-Teaching Environments.Grünewald, Franka; Siebert, Maria; Meinel, Christoph (2011).
[ Details ]

Weitere Informationen
Named Entity Recognition for User-Generated Tags.Ludwig, Nadine; Sack, Harald in CS (2011).
[ Details ]

Weitere Informationen
Community Rating in the Tele-Lecturing Context.Moritz, Franka; Siebert, Maria; Meinel, Christoph (2010).
[ Details ]

Weitere Informationen
Unsupervised Matching of Object Models and Ontologies.Quasthoff, Matthias; Völkel, Max; Meinel, Christoph (2010). 7.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1145/1839707.1839716
Tracing the Provenance of Object-Oriented Computations on RDF Data.Quasthoff, Matthias; Meinel, Christoph in 576 (2010). paper 4.
[ Details ]

Weitere Informationen
A Linked Data Web Programm Framework.Quasthoff, Matthias; Meinel, Christoph in LNCS (2010).
[ Details ]

Weitere Informationen
The Path is the Destination -- Enabling a New Search Paradigm with Linked Data.Waitelonis, Jörg; Knuth, Magnus; Wolf, Lina; Hercher, Johannes; Sack, Harald in CEUR Workshop Proceedings (2010). (Vol. 700)
[ Details ]

Weitere Informationen
AbstractToday, searching the World Wide Web in most cases turns out in looking for a specific item, which means that the user should know the item in advance. In the future internet, searching for infor- mation comes closer to the notion of ’window shopping’ by means of exploratory and semantic search technologies. In the course of the ex- ploratory search process the user constantly receives new information and establishes a personalized knowledge base. To make this possible, se- mantic search technologies utilize domain knowledge and semantic data, as e.g., Linked Open Data (LOD), to expand and refine search results, to derive cross-references, and to reveal implicitly hidden semantic rela- tions. Implementing semantic exploratory search requires various issues have to be solved including mapping text to semantic entities, detecting and cleaning inconsistencies in available LOD, ranking algorithms for se- mantic data and heuristics for recommendations, as well as appropriate visualizations of complex semantic relationships. This paper describes how LOD can be utilized to enable exploratory search systems for the future internet.
Enabling Reputation Interoperability through Semantic Technologies.Alnemr, Rehab; Paschke, Adrian; Meinel, Christoph (2010). No.13.
[ Details ]

Weitere Informationen
Distributed Recognition of Content Similarity in a Tele-Teaching Portal.Siebert, Maria; Moritz, Franka; Meinel, Christoph (2010).
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/1988688.1988731
Establishing an Expandable Architecture for a tele-Teaching Platform.Siebert, Maria; Moritz, Franka; Meinel, Christoph in ACIS (2010). 323-328.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1109/ICIS.2010.141
Use What You Have -- Yovisto Video Search Engine Takes a Semantic Turn.Waitelonis, Jörg; Ludwig, Nadine; Sack, Harald (2010).
[ Details ]

Weitere Informationen
Semantische Suche - Theorie und Praxis am Beispiel der Videosuchmaschine yovisto.com.Sack, Harald in Web 3.0 & Semantic Web, HMD - Praxis der Wirtschaftsinformatik, (U. Hentgartner; Meier, A., reds.) (2010). 271
[ Details ]

Weitere Informationen
HerausgeberHentgartner, Urs and Meier, Andreas
AbstractTraditionelle Suchmaschinen stoßen im World Wide Web heute schnell an ihre Grenzen. Einerseits liefern Suchanfragen oft Listen mit Millionen von Ergebnisdokumenten zurück, sodass die Vollständigkeit des Suchergebnisses nicht mehr beurteilt werden kann. Andererseits finden sich darin zahlreiche nicht relevante Informationen, verursacht durch die Mehrdeutigkeiten, unterschiedlichen Kontext oder Pragmatik. Wünschenswert wären sowohl eine höhere Treffgenauigkeit und damit Qualität der erzielten Suchergebnisse sowie ein besserer Überblick über die Ergebnisse bzw. über den gesamten Suchraum. Abhilfe verspricht eine Suche, die sich am tatsächlichen Inhalt der durchsuchten Dokumente und dessen Bedeutung orientiert anstatt wie heute üblich am Vergleich von Zeichenketten, wobei Kontext und Pragmatik berücksichtigt werden müssen. Im Semantic Web wird die Bedeutung multimedialer Dokumente mithilfe geeigneter Wissensrepräsentationen explizit gemacht. Werden diese semantischen Annotationen in den Suchprozess integriert, eröffnen sich neue Möglichkeiten, die Qualität der erzielten Suchergebnisse zu verbessern und speziell an Benutzerbedürfnisse anzupassen. Inhaltliche Zusammenhänge zwischen einzelnen Dokumenten können explizit gemacht werden und erlauben über Klassifikationen und Kategorisierungen neue Wege der Visualisierung des Such- und Ergebnisraumes hin zu einer explorativen Suche, die es dem Benutzer gestattet, die Suchergebnisse und damit im Zusammenhang stehende Informationen zu erkunden. Diese neuen Möglichkeiten der semantischen Suche sollen am Beispiel der Videosuchmaschine yovisto.com dargestellt werden.
Semantically Enabled Exploratory Video Search.Waitelonis, Jörg; Sack, Harald; Kramer, Zalan; Hercher, Johannes (2010). 8:1-8:8.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1145/1863879.1863887
Indexing German Audiovisual Heritage - SKOSification Made Easy.Hercher, Johannes; Sack, Harald (2010).
[ Details ]

Weitere Informationen
Realization of an Expandable Search Function for an E-Learning Web Portal.Siebert, Maria; Meinel, Christoph in ACIS (2010). 361-366.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1109/ICIS.2010.117
Exploratory Semantic Video Search with yovisto.Waitelonis, Jörg; Sack, Harald (2010). 446-447.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1109/ICSC.2010.98
SEMANTISCHE SUCHE-Theorie und Praxis am Beispiel der Videosuchmaschine yovisto.com.Sack,; Harald, (2010). 13-25.
[ Details ]

Weitere Informationen
Linking the tele-TASK Video Portal to the Semantic Web.Baumann, Bert; Sack, Harald; Groß, Andreas; Meinel, Christoph (2009). (Vol. 148) 205-216.
[ Details ]

Weitere Informationen
Towards Exploratory Video Search Using Linked Data.Waitelonis, Jörg; Sack, Harald (2009). 540 - 545.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1109/ISM.2009.111
How to Simplify Building Semantic Web Applications.Quasthoff, Matthias; Sack, Harald; Meinel, Christoph in CEUR Workshop Proceedings (2009). (Vol. 524)
[ Details ]

Weitere Informationen
AbstractThis paper formalizes several independent approaches on how to develop Semantic Web applications using object-oriented programming languages and Object-Triple Mapping. Using such mapping, Semantic Web applications have been developed up to three times faster compared to traditional Semantic Web software engineering. Results show that at the same time, developer satisfaction has been significantly higher if they used object triple mapping. We present a formal notation of object triple mapping and results of an experimental evaluation clearly showing the benefits of such mapping. The work presented here may one day help to make Semantic Web technologies part of the majority of future applications.
Can Software Developers Use Linked Data Vocabulary?Quasthoff, Matthias; Sack, Harald; Meinel, Christoph in J.UCS Conference Proceedings Series (2009). 542-549.
[ Details ]

Weitere Informationen
Augmenting Video Search with Linked Open Data.Waitelonis, Jörg; Sack, Harald in J.UCS Conference Proceedings Series (2009). 550-558.
[ Details ]

Weitere Informationen
AbstractLinked Open Data has become one of the driving forces for the emerging Semantic Web, which enables interlinking and integrating former proprietary data to the global linked data by using RDF as a standard data format. In this paper we show how to integrate the database of the open academic video search plattform yovisto.com with the linked open data cloud and how to augment yovisto video search by including semantically interrelated linked open data
Semantic Web Admission Free – Obtaining RDF and OWL Data from Application Source Code.Quasthoff, Matthias; Meinel, Christoph (2008).
[ Details ]

Weitere Informationen
Automatische Erzeugung Semantischer Annotationen für Vorlesungsvideos.Repp, Stephan; Linckels, Serge; Meinel, Christoph (2008). (Vol. 132GI) 149-160.
[ Details ]

Weitere Informationen
Who Reads and Writes the Social Web? A Security Architecture for Web 2.0 Applications.Quasthoff, Matthias; Sack, Harald; Meinel, Christoph (2008). 576-582.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1109/ICIW.2008.59
Optimizing the Retrieval of Pertinent Answers for NL Questions with the E-Librarian Service.Linckels, Serge; Sack, Harald; Meinel, Christoph in LNCS (2007).
[ Details ]

Weitere Informationen
Encouraging Participation in Virtual Communities - The IT-Summit Blog Case.Bross, Justus; Sack, Harald; Meinel, Christoph in Int. Journal on WWW/Internet (2007). 5(2) 113-129.
[ Details ]

Weitere Informationen
Why HTTPS Is Not Enough - A Signature-Based Architecture for Trusted Content on the Social Web.Quasthoff, Matthias; Sack, Harald; Meinel, Christoph (2007). 820 - 824.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1109/WI.2007.154
Segmentation and Annotation of Audiovisual Recordings based on Automated Speech Recognition.Repp, Stephan; Waitelonis, Jörg; Sack, Harald; Meinel, Christoph in LNCS (2007). (Vol. 4881) 620 - 629.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1007/978-3-540-77226-2_63
Encouraging Participation in Virtual Communities: The "IT-summit-blog" Case.Bross, Justus; Sack, Harald; Meinel, Christoph (2007). 245 - 254.
[ Details ]

Weitere Informationen
Retrieval Optimization of Pertinent Answers for NL Questions with the E-Librarian Service.Linckels, Serge; Sack, Harald; Meinel, Christoph (2007).
[ Details ]

Weitere Informationen
Probabilistic Equivalence Checking of Multiple-Valued Functions.Dubrova, Elena; Sack, Harald in Multiple-Valued Logic and Soft Computing (2004). 10(4) 395-414.
[ Details ]

Weitere Informationen
AbstractThis paper describes a probabilistic method for verifying the equivalence of two multiple-valued functions. Each function is hashed to an integer code by transforming it to a integer-valued polynomial and evaluating it for values of variables taken independently and uniformly at random from a finite field. Since the polynomial is unique for a given function, if two hash codes are different, then the functions are not equivalent. However, if two hash codes are the same, the functions may or may not be equivalent, because different polynomials may happen to hash to the same code. Thus, the method presented in this paper determines the equivalence of two functions with a known (small) probability of error, arising from collisions between inequivalent functions. Such a method seems to be an attractive alternative for verifying functions that are too large to be handled by deterministic equivalence checking methods.
Adapted Variable Reordering for XOR-OBDDs.Meinel, Christoph; Sack, H. (2003). 135-144.
[ Details ]

Weitere Informationen
VisBDD - A Webbased Visualization Framework for OBDD Algorithms.Meinel, Christoph; Sack, Harald; Schillings, Volker (2002). 385-390.
[ Details ]

Weitere Informationen
Course Management in the Twinkle of an Eye.Meinel, Christoph; Sack, Harald; Schillings, Volker (2002). 281-283.
[ Details ]

Weitere Informationen
A Simple Heuristic for Mod2-OBDD Minimization.Meinel, Christoph; Sack, Harald (2001). 304-309.
[ Details ]

Weitere Informationen
Improving XOR-node Placement for Mod2-OBDD Minimzation.Meinel, Christoph; Sack, Harald (2001). 51-56.
[ Details ]

Weitere Informationen
IDDS: An Interactive Decentralized Documentation System.Meinel, Christoph; Sack, Harald; Schillings, Volker (2001).
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1145/501516.501549
Representation of Multiple-Valued Functions with Mod-p Decision Diagrams.Sack, Harald; Dubrova, Elena; Meinel, Christoph (2000). 341-348.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1109/ISMVL.2000.848625
Functional Extension of Decision Diagrams in Practice.Sack, Harald; Meinel, Christoph (2000). 195-196.
[ Details ]

Weitere Informationen
Mod-p-DDs: A Data-Structure for Multiple-Valued Functions.Sack, Harald; Dubrova, Elena; Meinel, Christoph (2000). 233-238.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/10.1109/ISMVL.2000.848625
A Search-Engine-Topology to Improve Document Retrieval on the Web.Roth, Uwe; Heuer, Andreas; Haffner, Ernst-Georg; Meinel, Christoph (2000). 470-475.
[ Details ]

Weitere Informationen
Integration der Schleusentechnologie "Lock-Keeper" in moderne Sicherheitsarchitekturen.Haffner, Ernst-Georg; Engel, Thomas; Meinel, Christoph (2000).
[ Details ]

Weitere Informationen
Probabilistic Symbolic Simulation and Verification with Mod2-OBDDs.Sack, Harald; Meinel, Christoph in Electronic Notes in Theoretical Computer Science (1999). 22 156-170.
[ Details ]

Weitere Informationen
URNhttp://dx.doi.org/doi:10.1016/S1571-0661(05)80601-2
AbstractOrdered Binary Decision Diagrams (OBDDs) have already proved useful in the verification of combinational and sequential circuits. Due to limitations of the descriptive power of OBDDs several more general models of Binary Decision Diagrams have been studied. In this paper, ⊕-OBDDs - also known as Mod2OBDDs - in respect to their ability to serve as a tool for combinational verification are considered. Besides the application of ⊕-OBDDs, the more general problem of how to exploit the inherent potential of ⊕-OBDDs more efficiently is addressed.

Projects and Partners

AV-Portal Gottfried-Leibnitz-Universität Hannover, project with Technische Informationsbibliothek Hannover (TIB)
Semantic Media Explorer (SEMEX)
The Semantic Media Explorer is a demonstrator that combines the latest media analysis processes to provides optimal access to video content.
MEDIAGLOBE Project
The aim of MEDIAGLOBE is to open and interlink heterogenouse and currently isolated information sources in media archives and broadcasting corporation. Project partners: DEFA-spektrum, Medienbildungsgesellschaft Babelsberg mbH, Blue Order GmbH
THESEUS/CONTENTUS Project
The purpose of CONTENTUS is to develop basic technologies with which to access, archive and search for multi-media cultural assets and works of art.
YOVISTO
Yovisto is a video search engine specialized in academic content. Yovisto's search index is based on the combination of automated content based video analysis with user generated collaborative annotation (collaborative tagging, discussions, and comments). In difference to traditional video search engines, Yovisto enables pinpoint access within video data by providing fine-granular, time-dependent metadata.
Semantic Games
Games with a purpose that are dedicated to create and curate semantic content.

Current News

Invited Keynote: 21.06.2013: Harald Sack "Semantic Multimedia Analysis and Search", Symposium on Future Trends in Service-Oriented Computing, HPI, Potsdam.
Invited Talk: 18.03.2013: Harald Sack "Context-driven Semantic Multimedia Search", GoPortis Conference 2013 on non-textual Information - Strategy and Innovation Beyond Text, Hannover.
Invited Talk: 21.01.2013: Harald Sack "Strukturelle und semantische Analyse audiovisueller Medien - von der automatischen Schnitterkennung zur semantischen Suche", Gastvorlesung in den Medienwissenschaften, Universität Potsdam.
Invited Talk: 09.10.2012: Harald Sack "Semantics and Media Analysis"(6th_tele_task_symposium_2012) HPI-Potsdam.
Invited Talk: 25.09.2012: Harald Sack "Summarization and Relevance of Linked Data Facts"(LSWT2012) , Leipzig.
Invited Talk: 25.09.2012: Magnus Knuth "Linked Data Cleansing" (LSWT2012) , Leipzig.
Invited Talk: 25.09.2012: Nadine Steinmetz"How to Use Suggestion Services in Semantic Applications" (LSWT2012) , Leipzig.
Invited Talk: 20.09.2012: Harald Sack "Der Weg ist das Ziel – Explorative semantische Suche" (IVDW2012) Braunschweig.
20.09.2012: Jörg Waitelonis "Widen the Peepholes! Entity-based Auto-Suggestion as a rich and yet immediate Starting Point for Exploratory Search" (IVDW2012) Braunschweig.
Invited Talk: 29.05.2012: Magnus Knuth "Semantic Web Technologies" at TMF Forum Metadata and Linked Data, Berlin.
23.05.-25.05.2012: Bernhard Quehl "A Skeleton Based Binarization Approach for Video Text Recognition" at 13th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS2012), Dublin.
10.05.2012: Harald Sack "Medienanalyse", at the Mediaglobe concluding event, Berlin
10.05.2012: Jörg Waitelonis "Semantische Suche" at the Mediaglobe concluding event, Berlin
07.05.2012: "Neues Sucherlebnis beim Stöbern in Videoarchiven", HPI press release, Potsdam
10.05.2012: Meet us at the Mediaglobe concluding event in Berlin.
08.05.2012: Meet us at the Infomare satelite event "Lange Nacht der Suchmaschinen" in Berlin.
27.04.2012: Meet us at the CONTENTUS concluding event in Berlin.
18.04.2012: Christian Hentschel "High Performance Visual Video Analysis" at Future SOC Lab Day, Potsdam.
17.04.2012: Magnus Knuth "Colaboratively Patching Linked Data" at 2nd International Workshop on Usage Analysis and the Web of Data (USEWOD2012), Workshop at WWW 2012, Lyon.
12.04.2012: Bernhard Quehl "Text Detection in Video Images Using Adaptive Edge Detection and Stroke Width Verification" at 19th International Conference on Systems, Signals and Image Processing (IWSSIP2012).
23.03.2012: Johannes Hercher "Quo vadis nutzergenerierte Metadaten" at 2. DGI-Konferenz, Düsseldorf.
06.03.-10.03.2012: Meet us at the CeBIT Hannover, Hall 26 (H12).
13.02-15.02.2012: Meet us at the THESEUS congress in Berlin.
10.01.2012: Harald Sack Bildersuche im Netz, Interview on DRadio Wissen.
Invited Talk - 18. Jan 2012: Harald Sack, "Semantic Multimedia Analysis and Exploration", 63. Theorietag - Workshop über Algorithmen und Komplexität, Fachhochschule Brandenburg.

Prior Events and Activities

2011

Invited talk: 19.11.2011: Harald Sack, "Vom Suchen und Finden im Internet", for "Flüchtige Worte - Leben im digitalen Zeitalter" Tagung des Forum OST-WEST e.V. Potsdam, Seddiner See, Potsdam.
15.11.2011: Harald Sack, "Milliarden neuer Internetadressen - Verloren im Adressdschungel oder Raum für neue Geschäftsideen?", Keynote im Rahmen der Zukunftsdialoge, ständige Vertretung des Landes Brandenburgs beim Bund, Berlin.
Invited talk: 30.09.2011: Harald Sack, "Enabling Exploratory Video Search by Semantic Video Analysis" atLearning, Knowledge, Adaptation (LWA) 2011, Magdeburg.
19.09.2011: Harald Sack, "Suchen ist nicht immer gleich Suchen" at Corporate Semantic Web (CSW) Workshop, Xinnovations, Berlin.
Invited talk: 01.09.2011: Jörg Waitelonis, "Inhaltsbasierte Erschließung und Suche in multimedialen Objekten" at 35. Jahrestagung der Gesellschaft für Klassifikation, Frankfurt.
31.08.2011: Nadine Ludwig, "Named Entity Recognition for User-Generated Tags" at Text-based Information Retrieval (TIR) Workshop at DEXA 2011, Toulouse.
Invited talk: 20.06.2011: Harald Sack, "Semantic Search for audiovisual media" at THESEUS Thementag, Effiziente Erschließung digitaler Medien, Berlin.
16.06.2011: Harald Sack, Panel Discussion at 10th Innovative Internet Community Systems (I2CS 2011), Berlin: "Blessing or Curse for Online Communities? The Influence of Social Media, Mobile Internet and Clouds on Communities"
09.06.2011: Harald Sack / Jörg Waitelonis, "Projekt Mediaglobe im Theseus Forschungsprogram / Yovisto Akademische Videosuche", Workshop Inhaltsbasierte Erschließung und Suche in multimedialen Objekten, 100. Bibliothekartag 2011, Berlin.
Invited talk: 25.05.2011:Harald Sack, "Wie Sie schon immer finden wollten, was Sie noch nie gesucht haben", Leibniz Kolleg Potsdam, Potsdamer Naturwissenschaftliche Vorträge, Universitätscampus Golm, Potsdam.
Invited talk: 05.05.2011: Harald Sack, "Semantic Media Explorer - Neue Wege der Suche in Medienarchiven", Leipziger Semantic Web Tag 2011, Leipziger Mediencampus, 5. Mai 2011, Leipzig.
Invited talk: 22.03.2011: Johannes Hercher, "Semantische Suche im audiovisuellen Kulturerbe – Das Projekt mediaglobe", 2. I-Science Tage, March 22th, 2011, University of Applied Sciences, Potsdam.
01.-05. Mar. 2011: We present our research at CEBIT Hannover, Hall 9 (C15).
VISSW 2011, Visual Interfaces to the Social and Semantic Web, in conjunction with the International Conference on Intelligent User Interfaces (IUI 2011), Palo Alto, CA, USA, 13 Feb 2011.
Invited talk: 7. Feb. 2011: Harald Sack, "Semantik - Die nächste Herausforderungen für Anwendungen in der IT", HPI Academy, Feburary 7th, 2011, Hasso Plattner-Institute for IT Systems Engineering, Potsdam.
Invited talk: 7. Feb. 2011: Harald Sack, "Semantische Multimediasuche - CONTENTUS, MEDIAGLOBE und yovisto", Berlin Semantic Meetup, Feburary 6th, 2011, Konrad Zuse Zentrum für Informationstechnik, Freie Universität Berlin, Berlin.

2010

Invited talk: 2. Dec. 2010: Harald Sack, "Explorative und semantische Suche mit Mediaglobe", IRT-Symposium "Vom Suchen zum Finden - in multimedialen Archiven der nächsten Generation", December 1-2, 2010, Institut für Rundfunktechnik, München.
5th Int. Conference on Semantic and Digital Media Technologies (SAMT 2010), December 1-3, 2010, Saarbrücken, Germany.
Invited talk: 13. Oct. 2010: Harald Sack, "Archivierung, Analyse, Interaktion und Remix von wissenschaftlichen Online-Vorträgen", Wissenschaft auf neuer Bühne, 2. Meilensteintagung des Forschungsverbundes "Interactive Science - Interaktive Wissenschaftskommunikation über digitale Medien, Schloss Rauischgolzhausen, Justus-Liebig-Universität Gießen.
4th IEEE International Conference on Semantic Computing (ICSC 2010), September 22-24, 2010, Carnegie Mellon University, Pittsburgh, PA, USA.
Invited Talk:Harald Sack, "Semantic Search Technologies for Video Archives", Sino-German Forum on 'Digital University and Higher Education', in conjunction with 5th tele-TASK Symposium, Sept. 15-17, 2010, Bejing, China.
3rd KRDB school on 'Trends in the Web of Data' (KRDBs-2010), Brixen-Bressanone, Italy, 17-18 September 2010
9th European Workshop on Networked Knowledge Organization Systems and Services (NKOS 2010), Sep 9-10, 2010, at 14th European Conference on Digital Libraries 2010 (ECDL 2010), Glasgow, Scottland
Invited talk: 08. Sept. 2010: Harald Sack, "Semantic Web - Vom WWW zum Web of Data", Workshop 'Future Internet: Web 3.0 - Social, Service, Semantic Web' im Rahmen des 7. Fernausbildungskongresses 2010 der Bundeswehr, 7.-9. Sept. 2010, Helmut-Schmidt-Universität / Universität der Bundeswehr, Hamburg
Semantic Search Workshop (SemSearch10) at the 19th Int. World Wide Web Conference (WWW2010), 26-30 April 2010, Raleigh, NC, USA, 2010
Invited Talk: 15. Juni 2010: Harald Sack:"Linked Open Data Universe", Eröffnung FutureSOC-Lab, 5th Annual Symposium on Future Trends in Service-Oriented Computing, Hasso-Plattner-Institut für Softwaresystemtechnik, Potsdam.
Invited Talk: 26. Feb. 2010:Harald Sack:"Der Weg ist das Ziel - Explorative Videosuche jenseits des gängigen Suchparadigmas", 4. tele-TASK Symposium, Hasso-Plattner-Institut für Softwaresystemtechnik, Potsdam.

2009

International Symposium on Multimedia (ISM2009), December 14-16, 2009, San Diego
Invited Talk: 07. Dez. 2009: Harald Sack, "Das Semantic Web als kulturelles Phänomen", Impuls-Referat im Seminar "Web-Tendenzen als kulturelles Phänomen" an der FH-Potsdam, 07. Oktober 2009.
International Conference on Semantic Systems, I-SEMANTICS '09, 02.-04. September, Graz, Austia
Invited Talk: 07. Okt. 2009: Harald Sack, "Semantische Co-Annotation und Videosuche mit YOVISTO", Multimedia-Forum der DFN-Betriebstagung, 06./07. Oktober 2009, Johannesstift Berlin-Spandau.
Invited Talk: 09. Sep. 2009: Harald Sack, "Wie Sie schon immer finden wollten, was Sie noch nie gesucht haben - Paradigmenwechsel in der (Web)Suche", Keynote, 13. Verbundkonferenz des GBV, 9.-10.09.2009, Hamburg.
Summer School on Multimedia Semantics 2009, 23.-28. August, Koblenz, Germany
Open Video Conference, Metadata-Round-Table, 19.-21. June 2009, New York City

Teaching

&nb

2014 (SS)

Seminar (Master): Semantic Multimedia (Blog)
Seminar (Master): Principles of Linked Data Publishing (Blog)

2013/14 (WS)

Lecture (Master): Semantic Web Technologien (Blog)

2013 (SS)

Seminar (Master): Semantic Multimedia (Blog)
Seminar (Bachelor): Multimedia Analyse Technologien (Blog)
Schülerkolleg (für Schüler der 8. bis 10. Klasse): Internetsuche und Google PageRank - Wie wird was durch wen gefunden?
- Woche 1 - 09.04.2013: Die Geschichte der Web-Suchmaschinen (pdf)
- Woche 2 - 23.04.2013: Term- und Dokumentenranking (pdf)
- Woche 3 - 07.05.2013: Google Page Rank (pdf)
- Woche 4 - 21.05.2013: Personalisierung und Web Crawling (pdf)
- Woche 5 - 04.06.2013: Semantische Suche

&nb

Supervised Master Theses

Gerald Töpper: Erweiterung der DBpedia Ontologie und des Extraction Frameworks zur Sicherung der Datenqualität. (finished April 2012)
Peter Retzlaff: Visualisierung von Bag-of-Visual-Words-Vektoren für die Visual Concept Detection (finished March 2014)
Sebastian Stange: Evaluierung einer semantischen Videosuche und Ermittlung geeigneter Videoanalysetechniken (finished March 2014)
Michael Wolowyk: Semantic Recommender Systems (preliminary title) (in progress)

Open Master Theses

Please find a list of possible topics for Master Theses. Contact us, if you are interested in one of these topics or have own suggestions.

Video Analysis:
- OCR Spellcorrection
- Tag Relevance Estimation in Photo Communities
- Learning Local Image Descriptors
Linked Data and Semantic Web:
- Named Entity Evolution
- Authority File Mapping
- A Mereology for Media Fragments