SOON

The 'SOON' dataset is a large-scale benchmark derived from web-based room tour videos, used to evaluate Vision-and-Language Navigation by providing diverse, realistic indoor settings with enriched spatial and semantic supervision.

Papers using SOON (6)

Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos2026Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale2025CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation2025Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation2025FlexVLN: Flexible Adaptation for Diverse Vision-and-Language Navigation Tasks2025RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation2024