Trans Media Relevance Feedback for Image Autoannotation

Thomas Mensink 1, 2 Jakob Verbeek 2 Gabriela Csurka 1
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Automatic image annotation is an important tool for keyword-based image retrieval, providing a textual index for non-annotated images. Many image auto annotation methods are based on visual similarity between images to be annotated and images in a training corpus. The annotations of the most similar training images are transferred to the image to be annotated. In this paper we consider using also similarities among the training images, both visual and textual, to derive pseudo relevance models, as well as crossmedia relevance models. We extend a recent state-of-the-art image annotation model to incorporate this information. On two widely used datasets (COREL and IAPR) we show experimentally that the pseudo-relevance models improve the annotation accuracy.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [30 references]  Display  Hide  Download


https://hal.inria.fr/inria-00548632
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 10:22:16 AM
Last modification on : Tuesday, February 12, 2019 - 10:30:05 AM
Document(s) archivé(s) le : Monday, November 5, 2012 - 2:36:37 PM

Files

MVC10.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Thomas Mensink, Jakob Verbeek, Gabriela Csurka. Trans Media Relevance Feedback for Image Autoannotation. BMVC 2010 - British Machine Vision Conference, Aug 2010, Aberystwyth, United Kingdom. pp.20.1-20.12, ⟨10.5244/C.24.20⟩. ⟨inria-00548632⟩

Share

Metrics

Record views

592

Files downloads

446