TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Natural Language Processing/Visual Question Answering (VQA)/VQA v2 test-std

Visual Question Answering (VQA) on VQA v2 test-std

Metric: number (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕number▼Extra DataPaperDate↕Code
1ONE-PEACE72.24NoONE-PEACE: Exploring One General Representation ...2023-05-18Code
2OFA71.44NoOFA: Unifying Architectures, Tasks, and Modaliti...2022-02-07Code
3mPLUG-Huge69.82NomPLUG: Effective and Efficient Vision-Language L...2022-05-24Code
4VLMo67.26NoVLMo: Unified Vision-Language Pre-Training with ...2021-11-03Code
5MSR + MS Cog. Svcs., X10 models62.55NoVinVL: Revisiting Visual Representations in Visi...2021-01-02Code
6MSR + MS Cog. Svcs.61.5NoVinVL: Revisiting Visual Representations in Visi...2021-01-02Code
7Prismer61.39NoPrismer: A Vision-Language Model with Multi-Task...2023-03-04Code
8BGN, ensemble61.13NoBilinear Graph Networks for Visual Question Answ...2019-07-23-
9Single, w/o VLP58.62NoDeep Multimodal Neural Architecture Search2020-04-25Code
10Single, w/o VLP58.01NoIn Defense of Grid Features for Visual Question ...2020-01-10Code
11ERNIE-ViL-single model56.79NoERNIE-ViL: Knowledge Enhanced Vision-Language Re...2020-06-30-