Paper Info
Title
Event Detection with Zero Example: Select the Right and Suppress the Wrong Concepts.
Abstract
Complex video event detection without visual examples is a very challenging issue in multimedia retrieval. We present a state-of-the-art framework for event search without any need of exemplar videos and textual metadata in search corpus. To perform event search given only query words, the core of our framework is a large, pre-built bank of concept detectors which can understand the content of a video in the perspective of object, scene, action and activity concepts. Leveraging such knowledge can effectively narrow the semantic gap between textual query and the visual content of videos. Besides the large concept bank, this paper focuses on two challenges that largely affect the retrieval performance when the size of the concept bank increases: (1) How to choose the right concepts in the concept bank to accurately represent the query; (2) if noisy concepts are inevitably chosen, how to minimize their influence. We share our novel insights on these particular problems, which paves the way for a practical system that achieves the best performance in NIST TRECVID 2015.
Year
DOI
Venue
2016
10.1145/2911996.2912015
ICMR
Keywords
Field
DocType
Multimedia Event Detection, Video Search, 0Ex, Concept Selection, Semantic Pooling, Concept Bank
Metadata,Pattern recognition,Information retrieval,Computer science,TRECVID,Semantic gap,NIST,Artificial intelligence,Information and Communications Technology,Concept selection,Machine learning
Conference
Citations 
PageRank 
References 
11
0.68
31
Authors
4
Name
Order
Citations
PageRank
Yi-Jie Lu1515.14
Hao Zhang2536.42
Maaike de Boer3264.25
C. W. Ngo44271211.46