Video Summarization

      Video Summarization - Featured image

      Video summarization has been one of research topics that require deep understanding of video content. We explore various methods for automatic video summarization and also the limitation of current datasets.

      Publications

      • Mayu Otani, Yuta Nakashima, Esa Rahtu, and Janne Heikkilä (2019). Rethinking the evaluation of video summaries. Proc.~Computer Vision and Pattern Recognition (CVPR), pp. 7596-7604.
      • Antonio Tejero-de-Pablos, Yuta Nakashima, Tomokazu Sato, Naokazu Yokoya, Marko Linna, and Esa Rahtu (2018). Summarization of user-generated sports video by using deep action recognition features,’’ IEEE Transactions on Multimedia, vol. 20, no. 8, pp. 2000-2011.
      • Mayu Otani, Yuta Nakashima, Esa Rahtu, Janne Heikkilä, and Naokazu Yokoya (2018). Linking videos and languages: Representations and their applications. 情報処理学会研究報告, CVIM-212-38, 16 pages.
      • Mayu Otani, Yuta Nakashima, Esa Rahtu, and Janne Heikkilä (2018). Finding video parts with natural language. 情報処理学会研究報告, CVIM-211-7, 7 pages.
      • Mayu Otani, Yuta Nakashima, Esa Rahtu, and Janne Heikkilä (2017). Fine-grained video retrieval for multi-clip video. Closing the Loop Between Vision and Language (CLVL) at ICCV.
      • Mayu Otani, Yuta Nakashima, Esa Rahtu, and Janne Heikkilä (2017). Video question answering to find a desired video segment. Open Knowledge Base and Question Answering Workshop (OKBQA) at SIGIR.
      • Mayu Otani, Yuta Nakashima, Tomokazu Sato, and Naokazu Yokoya (2017). Video summarization using textual descriptions for authoring video blogs. Multimedia Tools and Applications, vol. 76, no. 9, pp. 12097-12115.
      • Mayu Otani, Yuta Nakashima, Esa Rahtu, Janne Heikkilä, and Naokazu Yokoya (2016). Video summarization using deep semantic features. Proc.~Asian Conference on Computer Vision, 16 pages.
      • Mayu Otani, Yuta Nakashima, Esa Rahtu, Janne Heikkilä, and Naokazu Yokoya (2016). Learning joint representations of videos and sentences with web image search. Proc. Workshop on Web-scale Vision and Social Media with ECCV6, 16 pages.
      • Antonio Tejero-de-Pablos, Yuta Nakashima, Tomokazu Sato, and Naokazu Yokoya (2016). Human action recognition-based video summarization for RGB-D personal sports video. Proc. IEEE International Conference on Multimedia and Expo (ICME), 6 pages.
      • Mayu Otani, Yuta Nakashima, Tomokazu Sato, and Naokazu Yokoya (2015). Textual description-based video summarization for video blogs. Proc. IEEE International Conference on Multimedia and Expo (ICME), 6 pages.