Towards local visual modeling for image captioning
Yiwei Ma, Jiayi Ji, Xiaoshuai Sun, Yiyi Zhou, Rongrong Ji
Topics & Concepts
Closed captioningComputer scienceLocalityEncoderTransformerGridArtificial intelligenceSnapshot (computer storage)Source codePattern recognition (psychology)Image (mathematics)Speech recognitionDatabasePhysicsOperating systemGeometryPhilosophyVoltageMathematicsQuantum mechanicsLinguisticsMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot Learning