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: yes/no (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕yes/no▼Extra DataPaperDate↕Code
1ONE-PEACE94.85NoONE-PEACE: Exploring One General Representation ...2023-05-18Code
2mPLUG-Huge94.83NomPLUG: Effective and Efficient Vision-Language L...2022-05-24Code
3VLMo94.68NoVLMo: Unified Vision-Language Pre-Training with ...2021-11-03Code
4OFA94.66NoOFA: Unifying Architectures, Tasks, and Modaliti...2022-02-07Code
5Prismer93.09NoPrismer: A Vision-Language Model with Multi-Task...2023-03-04Code
6MSR + MS Cog. Svcs., X10 models92.38NoVinVL: Revisiting Visual Representations in Visi...2021-01-02Code
7MSR + MS Cog. Svcs.92.04NoVinVL: Revisiting Visual Representations in Visi...2021-01-02Code
8BGN, ensemble90.89NoBilinear Graph Networks for Visual Question Answ...2019-07-23-
9ERNIE-ViL-single model90.83NoERNIE-ViL: Knowledge Enhanced Vision-Language Re...2020-06-30-
10Single, w/o VLP89.46NoDeep Multimodal Neural Architecture Search2020-04-25Code
11Single, w/o VLP89.18NoIn Defense of Grid Features for Visual Question ...2020-01-10Code