P
Pinar Duygulu
Researcher at Hacettepe University
Publications - 126
Citations - 6416
Pinar Duygulu is an academic researcher from Hacettepe University. The author has contributed to research in topics: Image retrieval & TRECVID. The author has an hindex of 26, co-authored 122 publications receiving 6189 citations. Previous affiliations of Pinar Duygulu include University of California, Berkeley & Bilkent University.
Papers
More filters
Book ChapterDOI
Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary
TL;DR: This work shows how to cluster words that individually are difficult to predict into clusters that can be predicted well, and cannot predict the distinction between train and locomotive using the current set of features, but can predict the underlying concept.
Journal ArticleDOI
Matching words and pictures
TL;DR: A new approach for modeling multi-modal data sets, focusing on the specific case of segmented images with associated text, is presented, and a number of models for the joint distribution of image regions and words are developed, including several which explicitly learn the correspondence between regions and Words.
Proceedings ArticleDOI
Automatic multimedia cross-modal correlation discovery
TL;DR: A novel, graph-based approach, "MMG", to discover cross-modal correlations across the media in a collection of multimedia objects, where it outperforms domain specific, fine-tuned methods by up to 10 percentage points in captioning accuracy.
Proceedings Article
Clustering art
TL;DR: This work extends a recently developed method for learning the semantics of image databases using text and pictures and uses WordNet to provide semantic grouping information and to help disambiguate word senses, as well as emphasize the hierarchical nature of semantic relationships.
Proceedings ArticleDOI
GCap: Graph-based Automatic Image Captioning
TL;DR: This paper proposes a novel, graph-based approach (GCap) which outperforms previously reported methods for automatic image captioning, and is fast and scales well, with its training and testing time linear to the data set size.