From multi-scale grids to dynamic regions: Dual-relation enhanced transformer for image captioning
Wei Zhou, Chuanle Song, Dihu Chen, Tao Su, Haifeng Hu, Chun Shan
Topics & Concepts
Closed captioningComputer scienceTransformerRelation (database)Dual (grammatical number)Scale (ratio)Image (mathematics)GridComputer visionArtificial intelligenceElectrical engineeringMathematicsData miningGeographyCartographyEngineeringLinguisticsGeometryVoltagePhilosophyMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesHuman Pose and Action Recognition