- document
-
Lu, Y.J. (author), Zhang, H. (author), Ngo, C.W. (author), de Boer, M. (author), Schavemaker, J. (author), Schutte, K. (author), Kraaij, W. (author)0-Shot System - The simple exact matching performs the best - The quality of concepts selected to represent an event is more important than quantity - It's an open problem of how to harness the ontology-based mapping MER System - In key evidence localization, we emphasize the event relevancy first, then the hot concepts - We recommend three...conference paper 2020
- document
- Kronemeijer, A.J. (author), Akkerman, H. (author), van der Steen, J.L. (author), Steudel, S. (author), Pendyala, R. (author), Panditha, P. (author), Bel, T. (author), van Diesen, K. (author), de Haas, G. (author), Maas, J. (author), de Riet, J. (author), Rovers, M. (author), Verbeek, R. (author), Nag, M. (author), Verschueren, L. (author), Genoe, J. (author), Dehaene, W. (author), Lu, Y.J. (author), Chiang, S.C. (author), Huang, Y.Y. (author), Yeh, M.H. (author), Gelinck, G. (author) conference paper 2018
- document
-
de Boer, M.H.T. (author), Lu, Y.J. (author), Zhang, H. (author), Schutte, K. (author), Ngo, C.W. (author), Kraaij, W. (author)Searching in digital video data for high-level events, such as a parade or a car accident, is challenging when the query is textual and lacks visual example images or videos. Current research in deep neural networks is highly beneficial for the retrieval of high-level events using visual examples, but without examples it is still hard to (1)...article 2017
- document
-
de Boer, M.H.T. (author), Schutte, K. (author), Zhang, H. (author), Lu, Y.J. (author), Ngo, C.W. (author), Kraaij, W. (author)One of the challenges in Multimedia Event Retrieval is the integration of data from multiple modalities. A modality is defined as a single channel of sensory input,such as visual or audio. We also refer to this as data source. Previous research has shown that the integration of different data sources can improve performance compared to only...article 2016
- document
-
Lu, Y.J. (author), Zhang, H. (author), de Boer, M.H.T. (author), Ngo, C.W. (author)Complex video event detection without visual examples is a very challenging issue in multimedia retrieval. We present a state-of-the-art framework for event search without any need of exemplar videos and textual metadata in search corpus. To perform event search given only query words, the core of our framework is a large, pre-built bank of...conference paper 2016
- document
-
Zhang, H. (author), Lu, Y.J. (author), de Boer, M.H.T. (author), ter Haar, F.B. (author), Schutte, K. (author), Kraaij, W. (author), Ngo, C.W. (author)This paper presents an overview and comparative analysis of our systems designed for the TRECVID 2015 [1] multimedia event detection (MED) task. We submitted 17 runs, of which 5 each for the zero-example, 10-example and 100-example subtasks for the Pre-Specified (PS) event detection and 2 runs for the 10-example subtask for the Ad-Hoc (AH) event...conference paper 2015
- document
-
Ngo, C.W. (author), Lu, Y.J. (author), Zhang, H. (author), Yao, T. (author), Tan, C.C. (author), Pang, L. (author), de Boer, M.H.T. (author), Schavemaker, J.G.M. (author), Schutte, K. (author), Kraaij, W. (author)This paper presents an overview and comparative analysis of our systems designed for TRECVID 2014 [1] multimedia event detection (MED) and recounting (MER) tasks, including all sub-tasks for Pre-Specified (PS) event detection, all sub-tasks except 100Ex for Ad-Hoc (AH) event detection, and 010Ex sub-task for both PS and AH event recounting....conference paper 2014