Graph-Structured Representations for Visual Question Answering

CVPR 2017 Damien TeneyLingqiao LiuAnton van den Hengel

This paper proposes to improve visual question answering (VQA) with structured representations of both scene contents and questions. A key challenge in VQA is to require joint reasoning over the visual and text domains... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Visual Question Answering COCO Visual Question Answering (VQA) abstract 1.0 multiple choice Graph VQA Percentage correct 74.37 # 1
Visual Question Answering COCO Visual Question Answering (VQA) abstract images 1.0 open ended Graph VQA Percentage correct 70.42 # 1