Placing images with refined language models and similarity search with PCA-reduced VGG features

G. Kordopatis-Zilos (1) , A. Popescu (2) , S. Papadopoulos (1) , Y. Kompatsiaris (1)

1 CERTH ITI - CERTH Information Technologies Institute
2 DIASI - Département Intelligence Ambiante et Systèmes Interactifs

We describe the participation of the CERTH/CEA-LIST team in the MediaEval 2016 Placing Task. We submitted five runs to the estimation-based sub-task: one based only on text by employing a Language Model-based approach with several refinements, one based on visual content, using geospatial clustering over the most visually similar images, and three based on a hybrid scheme exploiting both visual and textual cues from the multimedia items, trained on datasets of different size and origin. The best results were obtained by a hybrid approach trained with external training data and using two publicly available gazetteers.

Keywords: Computational linguistics; Different sizes; Geospatial clustering; Hybrid approach; Hybrid scheme; Language model; Multimedia items; Similarity search; Visual content; Visual languages

Domains: Computer Science [cs]

G. Kordopatis-Zilos, A. Popescu, S. Papadopoulos, Y. Kompatsiaris. Placing images with refined language models and similarity search with PCA-reduced VGG features. 2016 Multimedia Benchmark Workshop, MediaEval 2016, Oct 2016, Hilversum, Netherlands. ⟨cea-01843183⟩