OpenCodePapers

visual-question-answering-on-gqa-test-std

Visual Question Answering (VQA)
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
ProTo: Program-Guided Transformer for Program-Guided Tasks✓ Link65.14ProTo2021-10-02
Learning by Abstraction: The Neural State Machine✓ Link63.17NSM2019-07-09
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding✓ Link62.45MDETR-ENB52021-04-26
LXMERT: Learning Cross-Modality Encoder Representations from Transformers✓ Link60.3LXMERT2019-08-20
Language-Conditioned Graph Networks for Relational Reasoning✓ Link56.1single-hop + LCGN (ours)2019-05-10
GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering✓ Link54.06MAC2019-02-25
GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering✓ Link46.55CNN+LSTM2019-02-25