Conference paper Open Access

Concept Language Models and Event-based Concept Number Selection for Zero-example Event Detection

Galanopoulos, Damianos; Markatopoulou, Foteini; Mezaris, Vasileios; Patras, Ioannis

Zero-example event detection is a problem where, given an event query as input but no example videos for training a detector, the system retrieves the most closely related videos. In this paper we present a fully-automatic zero-example event detection method that is based on translating the event description to a predefined set of concepts for which previously trained visual concept detectors are available. We adopt the use of Concept Language Models (CLMs), which is a method of augmenting semantic concept definition, and we propose a new concept-selection method for deciding on the appropriate number of the concepts needed to describe an event query. The proposed system achieves state-of-the-art performance in automatic zero-example event detection.

Files (1.2 MB)
Name Size
icmr17_2_preprint.pdf md5:bc2e4517e1d2fb10f8266c1d8709cbeb 1.2 MB Download


Cite as