TitleMultimodal classification of events in social media
Publication TypeJournal Article
Year of Publication2016
AuthorsZeppelzauer, M., and D. Schopfhauser
JournalImage and Vision Computing
Pages-
ISSN0262-8856
KeywordsFeature Extraction, GIST, Image Retrieval, LDA, Machine learning, Multimodal Retrieval, pattern recognition, SIFT, Social Event Classification, Social Event Mining, Social Event Recognition, Text Retrieval, TFIDF
AbstractAbstract A large amount of social media hosted on platforms like Flickr and Instagram is related to social events. The task of social event classification refers to the distinction of event and non-event-related contents as well as the classification of event types (e.g. sports events and concerts). In this paper, we provide an extensive study of textual, visual, as well as multimodal representations for social event classification. We investigate the strengths and weaknesses of the modalities and study the synergy effects between the modalities. Experimental results obtained with our multimodal representation outperform state-of-the-art methods and provide a new baseline for future research.
URLhttp://arxiv.org/pdf/1601.00599
DOI10.1016/j.imavis.2015.12.004