Skip to content (access key 's')
Logo of Technion
Logo of CS Department


High-Order Attention Models for Visual Question Answering
event speaker icon
Idan Schwartz, M.Sc. Thesis Seminar
event date icon
Wednesday, 5.7.2017, 17:30
event location icon
Taub 601
The quest for algorithms which enable cognitive abilities is an important part of machine learning. A common trait in these recent cognitive-like tasks is that they take into account different data modalities, e.g., visual and lingual. We propose a novel and generally applicable form of attention mechanism that learns high-order correlations between various data modalities. We show that high-order correlations effectively direct the appropriate attention to the relevant elements in the different data modalities that are required to solve the joint task. We demonstrate the effectiveness of our high-order attention mechanism on the task of visual question answering (VQA), where we achieve state-of-the-art performance on the standard VQA dataset.
[Back to the index of events]