Urban Driving-Face Scene Gaze (UD-FSG) Benchmark

What is Urban Driving-Face Scene Gaze (UD-FSG)?

A driver gaze dataset with synchronized face and scene images, object bounding boxes, and gaze labels used to evaluate a proposed model.

Released

2026-09-09

Evaluates

General AI, Vision & 3D, cs.CV

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.10139

Urban Driving-Face Scene Gaze (UD-FSG) paper

• Paper https://arxiv.org/abs/2609.10139

Which sources cite Urban Driving-Face Scene Gaze (UD-FSG)?

• Urban Driving-Face Scene Gaze (UD-FSG)

Related General AI, Vision & 3D, cs.CV benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 360CityArena
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench