Results for "Cătălina Cangea"

total 5took 0.02s
XFlow: 1D-2D Cross-modal Deep Neural Networks for Audiovisual ClassificationSep 02 2017We propose two multimodal deep learning architectures that allow for cross-modal dataflow (XFlow) between the feature extractors, thereby extracting more interpretable features and obtaining a better representation than through unimodal learning, for ... More
XFlow: Cross-modal Deep Neural Networks for Audiovisual ClassificationSep 02 2017Apr 12 2019In recent years, there have been numerous developments towards solving multimodal tasks, aiming to learn a stronger representation than through a single modality. Certain aspects of the data can be particularly useful in this case - for example, correlations ... More
Towards Sparse Hierarchical Graph ClassifiersNov 03 2018Recent advances in representation learning on graphs, mainly leveraging graph convolutional networks, have brought a substantial improvement on many graph-based benchmark tasks. While novel approaches to learning node embeddings are highly suitable for ... More
Structure-Based Networks for Drug ValidationNov 21 2018Classifying chemicals according to putative modes of action (MOAs) is of paramount importance in the context of risk assessment. However, current methods are only able to handle a very small proportion of the existing chemicals. We address this issue ... More
Spatio-Temporal Deep Graph InfomaxApr 12 2019Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time. To address these issues, we introduce Spatio-Temporal Deep Graph ... More