Robust video question answering via contrastive cross-modality representation learning
Xun Yang, Jianming Zeng, Dan Guo, Shanshan Wang, Jianfeng Dong, Meng Wang
Topics & Concepts
Modality (human–computer interaction)Question answeringRepresentation (politics)Computer scienceArtificial intelligenceNatural language processingEpistemic modalityLinguisticsPhilosophyPolitical sciencePoliticsLawMultimodal Machine Learning ApplicationsHuman Pose and Action RecognitionVideo Analysis and Summarization