Christian Otto (M.Sc.)

Research Assistant

Email: christian.ottotibeu

Phone: +49 511 762-14479

Postal address: Welfengarten 1 B, 30167 Hannover

Address for visitors: Lange Laube 28, 30159 Hannover, Room: 2.08

My research topic is the examination of cross-modal interrelations between visual and textual information. This includes the consideration of insights from communication sciences, the research design of deep learning applications to analyse multimodal information and the incorporation of this knowledge into search engines, such as for scientific publications or scientific videos. I am also responsible for the research group’s usability lab, which explores new possibilities of user interaction for TIB’s AV-Portal.

  • H. Zhou, C. Otto, R. Ewerth:
    Visual Summarization of Scholarly Videos using Word Embeddings and Keyphrase Extraction
    In: International Conference on Theory and Practice of Digital Libraries (TPDL), Oslo, Norway, 2019. accepted for publication (short paper)

  • C. Otto, M. Springstein, A. Anand, R. Ewerth:
    Understanding, Categorizing and Predicting Semantic Image-Text Relations 
    In: Proceedings of ACM International Conference on Multimedia Retrieval (ICMR), Ottawa, Canada, 2019, 168-176. Best Paper Award

    https://dl.acm.org/citation.cfm?id=3325049

  • C. Otto, S. Holzki, R. Ewerth:
    ''Is this an example image?'' – Predicting the Relative Abstractness Level of Image and Text
    In: Proceedings of the 41st European Conference on Information Retrieval (ECIR), Cologne, Germany, 2019, 711-725.

    https://arxiv.org/abs/1901.07878

  • J. Medrek, C. Otto, R. Ewerth:
    Recommending Scientific Videos based on Metadata Enrichment using Linked Open Data
    In Proceedings of International Conference on Theory and Practice of Digital Libraries (TPDL), Porto, Portugal, 2018, 286-292.

    https://arxiv.org/abs/1806.07309

  • M. Mühling, N. Korfhage, E. Müller, C. Otto, M. Springstein, T. Langelage, U. Veith, R. Ewerth, B. Freisleben: 
    Deep learning for content-based video retrieval in film and television production. 
    In Multimedia Tools and Applications, 1-26, 2017. 
    https://link.springer.com/article/10.1007/s11042-017-4962-9
     
  • E. Müller, C. Otto, R. Ewerth: 
    Semi-supervised Identification of Rarely Appearing Persons in Video by Correcting Weak Labels
    In: Proceedings of ACM International Conference on Multimedia Retrieval (ICMR), New York, ACM, 2016, 381-384