CMU Informedia at TRECVID 2020: Activity Detection with Dense Spatio-Temporal Proposals

Lijun Yu, Yijun Qian, Wenhe Liu, Alexander G. Hauptmann

Published in TRECVID, 2020


We propose an action recognition system for surveillance scenarios, which wins TRECVID 2020 Activities in Extended Video (ActEV) Challenge with a large advantage of 23.8% ahead the runner up system. Our system develops a dense spatial-temporal proposal generation model which collaborates with the state-of-the-art action classifiers. The proposed system utilizes multiple state-of-the-art modules and is trained on VIRAT Dataset with only released annotations. In this paper, we demonstrate the architecture and algorithms with technique details of the winner system.

  title={ {CMU} Informedia at {TRECVID} 2020: Activity Detection with Dense Spatio-Temporal Proposals},
  author={Yu, Lijun and Qian, Yijun and Liu, Wenhe and Hauptmann, Alexander G.},