Vision and Language Navigation on RxR

Metric: ndtw (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	ndtw▼	Extra Data	Paper	Date↕	Code
1	MARVAL	66.76	Yes	A New Path: Scaling Vision-and-Language Navigati...	2022-10-06	-
2	EnvEdit-PT	64.61	Yes	EnvEdit: Environment Editing for Vision-and-Lang...	2022-03-29	Code
3	HAMT	59.94	No	History Aware Multimodal Transformer for Vision-...	2021-10-25	Code
4	CLEAR-CLIP	53.69	Yes	How Much Can CLIP Benefit Vision-and-Language Ta...	2021-07-13	Code
5	Monolingual Baseline	41.05	No	Room-Across-Room: Multilingual Vision-and-Langua...	2020-10-15	Code
6	Multilingual Baseline	36.81	No	Room-Across-Room: Multilingual Vision-and-Langua...	2020-10-15	Code

#1MARVALSOTA
66.76
ndtw· Extra Data· 2022-10-06
A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning
#2EnvEdit-PTSOTA
64.61
ndtw· Extra Data· 2022-03-29
EnvEdit: Environment Editing for Vision-and-Language Navigation Code
#3HAMTSOTA
59.94
ndtw· 2021-10-25
History Aware Multimodal Transformer for Vision-and-Language Navigation Code
#4CLEAR-CLIPSOTA
53.69
ndtw· Extra Data· 2021-07-13
How Much Can CLIP Benefit Vision-and-Language Tasks?Code
#5Monolingual BaselineSOTA
41.05
ndtw· 2020-10-15
Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding Code
#6Multilingual Baseline
36.81
ndtw· 2020-10-15
Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding Code