Litcius/Paper detail

Contrastive Region Guidance: Improving Grounding in Vision-Language Models Without Training

David Wan, Jaemin Cho, Elias Stengel-Eskin, Mohit Bansal

2024Lecture notes in computer science13 citationsDOI

Topics & Concepts

Computer scienceTraining (meteorology)Artificial intelligenceGroundComputer visionNatural language processingElectrical engineeringEngineeringMeteorologyPhysicsMultimodal Machine Learning ApplicationsDomain Adaptation and Few-Shot LearningHuman Pose and Action Recognition
Contrastive Region Guidance: Improving Grounding in Vision-Language Models Without Training | Litcius