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)/ScanQA Test w/ objects

Visual Question Answering (VQA) on ScanQA Test w/ objects

Metric: BLEU-1 (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕BLEU-1▼Extra DataPaperDate↕Code
1NaviLLM39.73NoTowards Learning a Generalist Model for Embodied...2023-12-04Code
23D-LLM (BLIP2-flant5)38.3No3D-LLM: Injecting the 3D World into Large Langua...2023-07-24Code
33D-LLM (BLIP2-opt)37.3No3D-LLM: Injecting the 3D World into Large Langua...2023-07-24Code
4BridgeQA34.49NoBridging the Gap between 2D and 3D Visual Questi...2024-02-24Code
53D-LLM (flamingo)32.6No3D-LLM: Injecting the 3D World into Large Langua...2023-07-24Code
6ScanQA31.56NoScanQA: 3D Question Answering for Spatial Scene ...2021-12-20Code
7VoteNet+MCAN29.46NoScanQA: 3D Question Answering for Spatial Scene ...2021-12-20Code
8ScanRefer+MCAN27.85NoScanQA: 3D Question Answering for Spatial Scene ...2021-12-20Code