OpenCodePapers
visual-question-answering-on-a-okvqa
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
MC Accuracy
↕
DA VQA Score
↕
ModelName
ReleaseDate
↕
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts
83.75
70.55
SMoLA-PaLI-X Specialist Model
2023-12-01
Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models
80.4
68.2
PaLI-X-VPD
2023-12-05
Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering
✓ Link
75.1
58.5
Prophet
2023-03-03
PromptCap: Prompt-Guided Task-Aware Image Captioning
✓ Link
73.2
59.6
PromptCap
2022-11-15
Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training
✓ Link
71
MC-CoT
2023-11-23
HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning
✓ Link
56.35
HYDRA
2024-03-19
Webly Supervised Concept Expansion for General Purpose Vision Models
53.7
40.7
GPV-2
2022-02-04
KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA
42.2
42.2
KRISP
2020-12-20
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
✓ Link
42.1
12.0
ViLBERT - VQA
2019-08-06
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
✓ Link
41.6
25.9
LXMERT
2019-08-20
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
✓ Link
41.5
25.9
ViLBERT
2019-08-06
Pythia v0.1: the Winning Entry to the VQA Challenge 2018
✓ Link
40.1
21.9
Pythia
2018-07-26
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
✓ Link
34.1
9.2
ViLBERT - OK-VQA
2019-08-06
A Simple Baseline for Knowledge-Based Visual Question Answering
57.5
A Simple Baseline for KB-VQA
2023-10-20
VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge
✓ Link
38.05
VLC-BERT
2022-10-24