A multi-scale self-supervised hypergraph contrastive learning framework for video question answering
Zheng Wang, Bin Wu, Kaoru Ota, Mianxiong Dong, He Li
Topics & Concepts
Question answeringHypergraphComputer scienceScale (ratio)Artificial intelligenceNatural language processingMachine learningMathematicsQuantum mechanicsPhysicsDiscrete mathematicsMultimodal Machine Learning ApplicationsDomain Adaptation and Few-Shot LearningHuman Pose and Action Recognition