LinkedTV at MediaEval 2014 Search and Hyperlinking Task
Hoang-An Le, Q.M. Bui, Benoît Huet, B. Cˇ Ervenková, J. Bouchner, Evlampios Apostolidis, Fotini Markatopoulou, Alexandros Pournaras, Vasileios Mezaris, D. Stein, Stefan Eickeler, Michael Stadtschnitzer · 2014
The paper presents the LinkedTV approaches for the Search and Hyperlinking (S&H) task at MediaEval 2014. Our sub-missions aim at evaluating 2 key dimensions: temporal gran-ularity and visual properties of the video segments. The temporal granularity of target video segments is defined by grouping text sentences, or consecutive automatically de-tected shots, considering the temporal coherence, the vi-sual similarity and the lexical cohesion among them. Visual properties are combined with text search results using mul-timodal fusion for re-ranking. Two alternative methods are proposed to identify which visual concepts are relevant to each query: using WordNet similarity or Google Image anal-ysis. For Hyperlinking, relevant visual concepts are identi-fied by analysing the video anchor. 1.