GRIT: Faster and Better Image Captioning Transformer Using Dual Visual Features
Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani
Topics & Concepts
Closed captioningComputer scienceTransformerArtificial intelligenceGridDetectorComputer visionInferenceVisualizationObject detectionFuse (electrical)Pattern recognition (psychology)Image (mathematics)VoltageEngineeringMathematicsQuantum mechanicsElectrical engineeringTelecommunicationsPhysicsGeometryMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot Learning