R.I.P.
๐ป
Ghosted
PoseRefer: Pathway-Local Parameters for Semantically Grounded Reference Resolution
May 23, 2026 ยท Grace Period ยท ๐ ICRA 2026 Workshop
Authors
Anna Deichler
arXiv ID
2605.24622
Category
cs.RO: Robotics
Cross-listed
cs.CV
Citations
0
Venue
ICRA 2026 Workshop
Abstract
A robot resolving ``put the cup on that one'' must fuse gesture, language, and scene geometry, yet 3D grounding benchmarks only partially capture this regime: descriptions are written post-hoc, gestures are templated, or pointing is staged for the camera. MM-Conv captures natural co-speech gesture from dyadic VR interaction alongside full-body motion capture and 3D scene graphs. We use it to evaluate pose-language fusion with a decoupled late-fusion architecture in which pose and text pathways share no learned parameters. The two choices together make category, pose, and text contributions easier to isolate through controlled ablations. Fusion with frozen MiniLM category embeddings exceeds pose alone and the best text-only pathway on every reference type, reaching 31.9% top-1. The learned scalar gate flips between opposing policies depending on whether the text pathway has category access. This is a reliability diagnostic: fusion-accuracy claims for semantic grounding systems are indistinguishable from category-representation artifacts unless pathways are architecturally decoupled.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Robotics
R.I.P.
๐ป
Ghosted
AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
๐
๐
The Cartographer
A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles
๐
๐
The Cartographer
Unmanned Aerial Vehicles: A Survey on Civil Applications and Key Research Challenges
๐
๐
The Cartographer
A Survey of Autonomous Driving: Common Practices and Emerging Technologies
R.I.P.
๐ป
Ghosted