OpenCodePapers
visual-question-answering-on-clevr
Visual Question Answering (VQA)
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
Accuracy
↕
ModelName
ReleaseDate
↕
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
✓ Link
99.8
NS-VQA (1K programs)
2018-10-04
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
✓ Link
99.7
MDETR
2021-04-26
NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization
✓ Link
99.7
NeSyCoCo
2024-12-20
Interpretable Visual Reasoning via Induced Symbolic Space
✓ Link
99.4
OCCAM (ours)
2020-11-23
Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
✓ Link
99.1
TbD + reg + hres
2018-03-14
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
✓ Link
98.9
NS-CL
2019-04-26
Compositional Attention Networks for Machine Reasoning
✓ Link
98.9
MAC
2018-03-08
Learning Visual Question Answering by Bootstrapping Hard Attention
✓ Link
98.8
CNN + LSTM + RN + HAN
2018-08-01
DDRprog: A CLEVR Differentiable Dynamic Reasoning Programmer
98.3
DDRprog*
2018-03-30
Language-Conditioned Graph Networks for Relational Reasoning
✓ Link
97.9
single-hop + LCGN (ours)
2019-05-10
FiLM: Visual Reasoning with a General Conditioning Layer
✓ Link
97.7
CNN+GRU+FiLM
2017-09-22
Explainable and Explicit Visual Reasoning over Scene Graphs
✓ Link
97.7
XNM-Det supervised
2018-12-05
Inferring and Executing Programs for Visual Reasoning
✓ Link
96.9
IEP-700K
2017-05-10
A simple neural network module for relational reasoning
✓ Link
95.50
CNN + LSTM + RN
2017-06-05
Question-Guided Hybrid Convolution for Visual Question Answering
65.90
QGHC+Att+Concat
2018-08-08