Abstract

Finding a matching image for a news article is a core problem in the creation of traditional and online newspapers. The task of image- text matching has thus become a vibrant research area in computer science. The performance of state-of-the-art image retrieval systems on various benchmarks is excellent. However, they all rely on datasets with a detailed textual description of the images or on very large training collections. In this work, we optimize image- text matching algorithms for a small dataset based on the data of a single newspaper. Our optimized processing pipeline and the computed configurations reach precise results. The evaluation results obtained in the MediaEval NewsImages benchmark significantly outperforming the algorithms from previous years.

@inproceedings{SuehrEtAl:RematchingUsingEmbeddingsAndCnns2021,
	author    = {Tom S{\"u}hr and Ajay Madhavanr and Nasim Jamshidi Avanaki and Ren{\´e} Berk and Andreas Lommatzsch},
	title     = {Image-Text Rematching for News Items using Optimized Embeddings and CNNs in MediaEval NewsImages 2021},
	booktitle = {Proceedings of the MediaEval Benchmarking Initiative for Multimedia Evaluation 2021},
	year      = {2021},
	issn      = {1613-0073},
	url       = {https://ceur-ws.org/Vol-3181/paper11.pdf},
	location  = {Online},
	publisher = {CEUR Workshop Proceedings},
	keywords  = {workshop, paper, multi-media, nlp}
}