Papers with Code · CC BY-SA 4.0
Visual Question Answering (VQA)
Visual Question Answering (VQA) is a task in computer vision that involves answering questions about an image. The goal of VQA is to teach machines to understand the content of an image and answer questions about it in natural language.
Image Source: visualqa.org
데이터셋
141개VQA v2 valBenchLMMCOCO Visual Question Answering (VQA) real images 1.0 multiple choiceVQA-CPVizWiz 2018VLM2-BenchVQA-CEVCR (QA-R) test6-DoF SpatialBenchGQA test-stdIllusionVQAInfoSeekSMEVCR (Q-AR) testVQA v1 test-devPlotQAVQA v1 test-stdVizWiz 2020 AnswerabilityWHOOPS!3D MM-VetAutoHallusionCLEVR-HumansEmbSpatial-BenchGQA-REXMMBenchQLEVRRealCQAV*benchAI2DCOCO Visual Question Answering (VQA) abstract 1.0 multiple choice