Multi-Task Transfer Methods to Improve One-Shot Learning for Multimedia Event Detection
Yan Wang, Jordan Yap, Greg Mori · 2015
Learning a model for complex video event detection from only one positive sam-ple is a challenging and important problem in practice, yet seldom has been addressed. This paper proposes a new one-shot learning method based on multi-task learning to ad-dress this problem. Information from external relevant events is utilized to overcome the paucity of positive samples for the given event. Relevant events are identified implicitly and are emphasized more in the training. Moreover, a new dataset focusing on personal video search is collected. Experiments on both TRECVid Multimedia Event Detection video set and the new dataset verify the efficacy of the proposed methods. 1