Multimodal graph neural network for video procedural captioning
Lei Ji, Rong-Cheng Tu, Kevin Lin, Lijuan Wang, Nan Duan
Topics & Concepts
Closed captioningComputer scienceGraphArtificial intelligenceDependency graphContext (archaeology)Event (particle physics)Artificial neural networkDependency (UML)Recurrent neural networkNatural language processingTheoretical computer scienceImage (mathematics)Quantum mechanicsBiologyPhysicsPaleontologyVideo Analysis and SummarizationMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval Techniques