SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference
Feng Wang, Jieru Mei, Alan Yuille
Topics & Concepts
Computer scienceInferenceArtificial intelligenceCognitive scienceNatural language processingComputer visionHuman–computer interactionPsychologyMultimodal Machine Learning ApplicationsDomain Adaptation and Few-Shot LearningAdvanced Neural Network Applications