Research map / Detection and segmentation / Open-set and few-shot detection

HIRaD: Hidden Interaction Inference from Predictive Radar Dynamics

NeurIPS 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Hand-object and articulated interaction

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes HIRaD, which infers hidden object-related interaction semantics from millimeter-wave radar point cloud dynamics without direct object detection.

Problem

Describing object-related human interactions from sparse millimeter-wave radar point clouds, where the object evidence is often not separable or consistently observable.

Approach

Infers hidden interaction semantics from predictive radar dynamics (the abstract is truncated, so the mechanism beyond this is not stated) instead of relying on direct object detection in radar returns.

Closest papers by meaning

• RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-wave Point Cloud Sequence (AAAI 2026 · similarity 0.91)
• SIRA: Scalable Inter-frame Relation and Association for Radar Perception (CVPR 2024 · similarity 0.84)
• InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction (NeurIPS 2024 · similarity 0.83)
• CG-HOI: Contact-Guided 3D Human-Object Interaction Generation (CVPR 2024 · similarity 0.83)
• HOI-Dyn: Learning Interaction Dynamics for Human-Object Motion Diffusion (NeurIPS 2025 · similarity 0.82)
• EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics (AAAI 2025 · similarity 0.82)