Publication | Closed Access

Hierarchical Temporal Fusion of Multi-grained Attention Features for Video Question Answering

Natural Language ProcessingVideo Question AnsweringEngineeringMachine LearningPattern RecognitionMulti-grained Attention FeaturesVideo SummarizationVisual Question AnsweringHierarchical Temporal FusionVideo UnderstandingDeep LearningVideo RetrievalVideo InterpretationComputer Vision