G
Gabriel Doyle
Researcher at Stanford University
Publications - 21
Citations - 2129
Gabriel Doyle is an academic researcher from Stanford University. The author has contributed to research in topics: Enculturation & Image retrieval. The author has an hindex of 12, co-authored 20 publications receiving 1835 citations. Previous affiliations of Gabriel Doyle include San Diego State University & University of California, San Diego.
Papers
More filters
Proceedings ArticleDOI
A new approach to cross-modal multimedia retrieval
Nikhil Rasiwasia,Jose Costa Pereira,Emanuele Coviello,Gabriel Doyle,Gert R. G. Lanckriet,Roger Levy,Nuno Vasconcelos +6 more
TL;DR: It is shown that accounting for cross-modal correlations and semantic abstraction both improve retrieval accuracy and are shown to outperform state-of-the-art image retrieval systems on a unimodal retrieval task.
Journal ArticleDOI
On the Role of Correlation and Abstraction in Cross-Modal Multimedia Retrieval
Jose Costa Pereira,Emanuele Coviello,Gabriel Doyle,Nikhil Rasiwasia,Gert R. G. Lanckriet,Roger Levy,Nuno Vasconcelos +6 more
TL;DR: A mathematical formulation equating the design of cross-modal retrieval systems to that of isomorphic feature spaces for different content modalities is proposed, finding that both hypotheses hold, in a complementary form, although evidence in favor of the abstraction hypothesis is stronger than that for correlation.
Proceedings ArticleDOI
Accounting for burstiness in topic models
Gabriel Doyle,Charles Elkan +1 more
TL;DR: A topic model is introduced that uses Dirichlet compound multinomial (DCM) distributions to model this burstiness phenomenon and achieves better held-out likelihood than standard latentDirichlet allocation (LDA).
Proceedings ArticleDOI
Mapping Dialectal Variation by Querying Social Media
TL;DR: Tests show that this Bayesian method of estimating a conditional distribution of data given metadata based on queries from a big data/social media source, such as Twitter, can provide distributions that are tightly correlated with existing gold-standard studies at a fraction of the time, cost, and effort.
Proceedings ArticleDOI
Unsupervised word discovery from speech using automatic segmentation into syllable-like units
TL;DR: A syllable-based approach to unsupervised pattern discovery from speech is presented, able to limit potential word onsets and offsets to a finite number of candidate locations by first segmenting speech into syllables-like units.