ML Research Wiki / Benchmarks / Vision and Language Navigation / RxR

RxR

Vision and Language Navigation Benchmark

Performance Over Time

📊 Showing 6 results | 📏 Metric: ndtw

Top Performing Models

Rank Model Paper ndtw Date Code
1 MARVAL 📚 A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning 66.76 2022-10-06 -
2 EnvEdit-PT 📚 EnvEdit: Environment Editing for Vision-and-Language Navigation 64.61 2022-03-29 📦 jialuli-luka/envedit
3 HAMT History Aware Multimodal Transformer for Vision-and-Language Navigation 59.94 2021-10-25 📦 cshizhe/vln-hamt
4 CLEAR-CLIP 📚 How Much Can CLIP Benefit Vision-and-Language Tasks? 53.69 2021-07-13 📦 clip-vil/CLIP-ViL 📦 jianjieluo/openai-clip-feature 📦 facebookresearch/reliable_vqa 📦 gchhablani/multilingual-vqa
5 Monolingual Baseline Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding 41.05 2020-10-15 📦 jacobkrantz/VLN-CE 📦 google-research-datasets/RxR 📦 VegB/Diagnose_VLN
6 Multilingual Baseline Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding 36.81 2020-10-15 📦 jacobkrantz/VLN-CE 📦 google-research-datasets/RxR 📦 VegB/Diagnose_VLN

All Papers (6)

jialuli-luka/envedit
cshizhe/vln-hamt
clip-vil/CLIP-ViL jianjieluo/openai-clip-feature
jacobkrantz/VLN-CE google-research-datasets/RxR VegB/Diagnose_VLN
jacobkrantz/VLN-CE google-research-datasets/RxR VegB/Diagnose_VLN