Zero-shot event detection via event-adaptive concept relevance mining

作者:

Highlights:

摘要

Zero-shot complex event detection has been an emerging task in coping with the scarcity of labeled training videos in practice. Aiming to progress beyond the state-of-the-art zero-shot event detection, we propose a new zero-shot event detection approach, which exploits the semantic correlation between an event and concepts. Based on the concept detectors pre-trained from external sources, our method learns the semantic correlation from the concept vocabulary and emphasizes on the most related concepts for the zero-shot event detection. Particularly, a novel Event-Adaptive Concept Integration algorithm is introduced to estimate the effectiveness of semantically related concepts by assigning different weights to them. As opposed to assigning weights by an invariable strategy, we compute the weights of concepts using the area under score curve. The assigned weights are incorporated into the confidence score vector statistically to better characterize the event-concept correlation. Our algorithm is proved to be able to harness the related concepts discriminatively tailored for a target event. Extensive experiments are conducted on the challenging TRECVID event video datasets, which demonstrate the advantage of our approach over the state-of-the-art methods.

论文关键词:Zero-shot event detection,Concept relevance mining,Semantic concept

论文评审过程:Received 19 October 2017, Revised 29 September 2018, Accepted 15 December 2018, Available online 18 December 2018, Version of Record 21 December 2018.

论文官网地址:https://doi.org/10.1016/j.patcog.2018.12.010