Citations
More filters
Proceedings Article
Unfolding temporal dynamics: predicting social media popularity using multi-scale temporal decomposition
TL;DR: To predict photo popularity, a novel framework named Multi-scale Temporal Decomposition (MTD) is proposed, which decomposes the popularity matrix in latent spaces based on contextual associations and models time-sensitive context on different time scales, which is beneficial to automatically learn temporal patterns.
Proceedings ArticleDOI
Image retagging
TL;DR: This paper proposes a social image "retagging" scheme that aims at assigning images with better content descriptors and shows the remarkable performance improvements brought by retagging via two applications, i.e., tag-based search and automatic annotation.
Journal ArticleDOI
Gaussian Processes for Underdetermined Source Separation
TL;DR: A general formulation of underdetermined source separation as a problem involving GP regression is proposed and framing as a GP approximation is introduced to make the GP models tractable for very large signals and it is shown that computations for regularly sampled and locally stationary GPs can be done very efficiently in the frequency domain.
Journal ArticleDOI
Analysing interactions among Sustainable Development Goals with Integrated Assessment Models
Heleen van Soest,Heleen van Soest,Detlef P. van Vuuren,Detlef P. van Vuuren,Jérôme Hilaire,Jan C. Minx,Mathijs Harmsen,Mathijs Harmsen,Volker Krey,Alexander Popp,Keywan Riahi,Gunnar Luderer +11 more
TL;DR: In this article, the authors compare the key interactions identified among the SDGs in an expert survey, with their current and planned representation in models as identified in a survey among modellers.
Journal ArticleDOI
LS-NMF: A modified non-negative matrix factorization algorithm utilizing uncertainty estimates
TL;DR: A new algorithm, least squares non-negative matrix factorization, LS-NMF, is created, which integrates uncertainty measurements of gene expression data into NMF updating rules and significantly improves the power of the NMF technique.
Related Papers (5)
Learning the parts of objects by non-negative matrix factorization
Positive matrix factorization: A non-negative factor model with optimal utilization of error estimates of data values†
Pentti Paatero,Unto Tapper +1 more