ML Research Wiki / Benchmarks / Vision and Language Navigation / Touchdown Dataset

Touchdown Dataset

Vision and Language Navigation Benchmark

Performance Over Time

📊 Showing 12 results | 📏 Metric: Task Completion (TC)

Top Performing Models

Rank Model Paper Task Completion (TC) Date Code
1 FLAME FLAME: Learning to Navigate with Multimodal LLM in Urban Environments 40.20 2024-08-20 📦 xyz9911/FLAME
2 ORAR + junction type + heading delta Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas 29.10 2022-03-25 📦 raphael-sch/map2seq_vln
3 ORAR Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas 24.20 2022-03-25 📦 raphael-sch/map2seq_vln
4 ARC + L2STOP Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation 16.68 2020-09-28 -
5 VLN Transformer +M-50 +style 📚 Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation 16.20 2020-07-01 📦 VegB/VLN-Transformer
6 VLN Transformer Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation 14.90 2020-07-01 📦 VegB/VLN-Transformer
7 ARC Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation 14.13 2020-09-28 -
8 Retouch-RConcat Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View 12.80 2020-01-10 📦 clic-lab/touchdown 📦 lil-lab/touchdown 📦 google-research/valan 📦 VegB/VLN-Transformer
9 Gated Attention (GA) Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation 11.90 2020-07-01 📦 VegB/VLN-Transformer
10 RConcat Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation 11.80 2020-07-01 📦 VegB/VLN-Transformer

All Papers (12)

xyz9911/FLAME
raphael-sch/map2seq_vln
raphael-sch/map2seq_vln
VegB/VLN-Transformer
VegB/VLN-Transformer
clic-lab/touchdown lil-lab/touchdown
VegB/VLN-Transformer
VegB/VLN-Transformer
lil-lab/touchdown lil-lab/ciff
lil-lab/touchdown lil-lab/ciff