Papers with Code · CC BY-SA 4.0

Visual Question Answering (VQA)

1,282 평가 기록 141 datasets

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

하위 태스크

VQ Visual Question Answering 48 데이터셋 · 358 rows GV Generative Visual Question Answering 7 데이터셋 · 116 rows CQ Chart Question Answering 3 데이터셋 · 38 rows 3Q 3D Question Answering (3D-QA) 3 데이터셋 · 36 rows MR Machine Reading Comprehension 4 데이터셋 · 9 rows CU Chart Understanding 0 데이터셋 · 0 rows EQ Embodied Question Answering 0 데이터셋 · 0 rows FV Factual Visual Question Answering 0 데이터셋 · 0 rows MC Multimodal Colonoscopy 0 데이터셋 · 0 rows