Title | ||
---|---|---|
Concept Language Models and Event-based Concept Number Selection for Zero-example Event Detection. |
Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1145/3078971.3079043 | ICMR |
Keywords | Field | DocType |
Zero-example multimedia event detection, Video search, Query representation | Pattern recognition,Computer science,Complex event processing,Artificial intelligence,Detector,Language model,Machine learning | Conference |
Citations | PageRank | References |
2 | 0.39 | 16 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Damianos Galanopoulos | 1 | 23 | 3.89 |
Fotini Markatopoulou | 2 | 35 | 5.93 |
Vasileios Mezaris | 3 | 803 | 81.40 |
Ioannis Patras | 4 | 1960 | 123.15 |