Complex Event Detection via Event Oriented Dictionary Learning


  • Yan Yan University of Trento
  • Yi Yang University of Technology Sydney
  • Haoquan Shen University of Technology Sydney
  • Deyu Meng Xi’an Jiao Tong University
  • Gaowen Liu University of Trento
  • Alex Hauptmann Carnegie Mellon University
  • Nicu Sebe University of Trento



Complex event detection is a retrieval task with the goal of finding videos of a particular event in a large-scale unconstrained internet video archive, given example videos and text descriptions. Nowadays, different multimodal fusion schemes of low-level and high-level features are extensively investigated and evaluated for the complex event detection task. However, how to effectively select the high-level semantic meaningful concepts from a large pool to assist complex event detection is rarely studied in the literature. In this paper, we propose two novel strategies to automatically select semantic meaningful concepts for the event detection task based on both the events-kit text descriptions and the concepts high-level feature descriptions. Moreover, we introduce a novel event oriented dictionary representation based on the selected semantic concepts. Towards this goal, we leverage training samples of selected concepts from the Semantic Indexing (SIN) dataset with a pool of 346 concepts, into a novel supervised multi-task dictionary learning framework. Extensive experimental results on TRECVID Multimedia Event Detection (MED) dataset demonstrate the efficacy of our proposed method.




How to Cite

Yan, Y., Yang, Y., Shen, H., Meng, D., Liu, G., Hauptmann, A., & Sebe, N. (2015). Complex Event Detection via Event Oriented Dictionary Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1).