SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
Ming Dai, Zhenhua Feng, Yihao Xu, Lingfeng Yang, Wankou Yang
Topics & Concepts
Simple (philosophy)Computer scienceComputer visionFusionArtificial intelligenceSensor fusionAlgorithmVisualizationControl theory (sociology)MathematicsGroundRedundancy (engineering)Object (grammar)Multimodal Machine Learning ApplicationsAdvanced Vision and ImagingAdvanced Image and Video Retrieval Techniques