Compositional Prompting Video-language Models to Understand Procedure in Instructional Videos
Guyue Hu, Bin He, Hanwang Zhang
Topics & Concepts
Computer scienceTask (project management)Term (time)Object (grammar)Artificial intelligenceMatching (statistics)Natural language processingLanguage modelShot (pellet)NarrativeHuman–computer interactionLinguisticsPhilosophyEconomicsPhysicsQuantum mechanicsMathematicsManagementStatisticsChemistryOrganic chemistryHuman Pose and Action RecognitionMultimodal Machine Learning ApplicationsVideo Analysis and Summarization