Automatic Image Annotation Using Auxiliary Text Information

By Yansong Feng, Mirella Lapata. 2008

85 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Multimodal Learning

Citations in the corpus

Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (2013, background): “Some work, notably in the natural language processing community, has focused on images in news articles (Feng & Lapata, 2008, 2010).”
Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures (2016, background): “The BBC News dataset (Feng & Lapata, 2008) was one of the earliest collections of images and co-occurring texts.”
Captioning Images Taken by People Who Are Blind (2020, background): “The trend has been to include a larger number of examples, relying on scraping images from the web (typically Flickr) to support the growth from a few thousand [19,20,43] to hundreds of thousands [15,27,33] of captioned images in such datasets.”
How Many Words Is a Picture Worth? Automatic Caption Generation for News Images (2010, methodology): “Our experiments used the dataset created by Feng and Lapata (2008).2 It contains 3,361 articles downloaded from the BBC News website3 each of which is associated with a captioned news image.”
Cross-Caption Coreference Resolution for Automatic Image Understanding (2010, background): “Some research has used the text that surrounds an image in a news article as a proxy (Feng and Lapata, 2008; Deschacht and Moens, 2007).”
Topic Models for Image Annotation and Text Illustration (2010, background): “Our second baseline is the extended relevance model (Feng and Lapata, 2008) that also takes the document into account but crucially assumes that the process of generating the images is independent from the process of generating its keywords.”
Visual Information in Semantic Representation (2010, methodology): “We trained the multimodal topic model on the corpus created in Feng and Lapata (2008).”
Estimating the information gap between textual and visual representations (2017, methodology): “The BBC news article set from [5] is used as an example corpus of particularly complicated image-text relations, since their content is typically loosely correlated and the meaning of their co-occurrence usually hard to infer.”
Automatic Caption Generation for News Images (2013, methodology): “M. Lapata is with the Institute for Language, Cognition and Computation, School of Informatics, University of Edinburgh, Room 4.16, Informatics Forum, 10 Crichton Street, Edinburgh EH8 9AB, United Kingdom.”