Video Question Answering via Hierarchical Dual-Level Attention Network Learning
Authors:
Open Access
- 19 October 2017
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1050-1058
Abstract
No abstract availableKeywords
This publication has 35 references indexed in Scilit:
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- VQA: Visual Question Answering2015
- Graph Regularized Feature Selection with Data ReconstructionIEEE Transactions on Knowledge and Data Engineering, 2015
- A discriminative CNN video representation for event detection2015
- Exploring Inter-feature and Inter-class Relationships with Deep Neural Networks for Video Classification2014
- Expert Finding for Question Answering via Graph Regularized Matrix CompletionIEEE Transactions on Knowledge and Data Engineering, 2014
- Learning representations for affective video understanding2013
- Attribute-augmented semantic hierarchy2013
- Long Short-Term MemoryNeural Computation, 1997
- Visual information retrievalCommunications of the ACM, 1997