Temporal Web Image Retrieval

Gaël Dias (1) , José G. Moreno (1) , Adam Jatowt (2) , Ricardo Campos (3)

1 Equipe Hultech - Laboratoire GREYC - UMR6072
2 Kyoto University
3 LIAAD - INESC Porto, LA

Temporal Web Image Retrieval can be defined as the process that retrieves sets ofWeb images with their temporal dimension from explicit or implicit temporal text queries. Supposing that (a) the temporal dimension is included in image indexing and (b) the query is explicitly expressed with a time tag (e.g. "Fukushima 2011"), the retrieval task can be straightforward as image retrieval has been studied for several years with success. However, text queries are usually implicit in time (e.g. "Second World War") and automatically capturing the time dimension included in Web images is a challenge that has not been studied so far to the best of our knowledge. In this paper, we will discuss different research issues about Temporal Web Image Retrieval and the current progresses of our research in temporal ephemeral clustering and temporal image filtering.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Traitement du texte et du document

Gaël Dias, José G. Moreno, Adam Jatowt, Ricardo Campos. Temporal Web Image Retrieval. 19th edition of the International Symposium on String Processing and Information Retrieval (SPIRE 2012)., Oct 2012, Cartagena de Indias, Colombia. 6 p. ⟨hal-01070166⟩