PT cubed: Prototype-Guided Self-Supervised Pretraining for Generalizable mmWave Human Point Cloud Representation
cs.AI
Submitted: 2026-10-28
Updated: 2026-10-28
Comments: 30 pages
License: http://creativecommons.org/licenses/by/4.0/
The gist: Multi-source millimeter-wave (mmWave) observations offer an opportunity to learn human representations reusable across sensing tasks.
Terminology
Abstract
Multi-source millimeter-wave (mmWave) observations offer an opportunity to learn human representations reusable across sensing tasks. However, sparse detections and multipath effects make these observations unstable, challenging existing point cloud pretraining methods. We propose PT cubed, a prototype-guided self-supervised pretraining framework for mmWave human point clouds. PT cubed represents local states in spatial regions as sparse compositions of shared prototypes and learns their temporal evolution through autoregressive prediction. Observation consistency further stabilizes representations under radar perturbations. After pretraining on unlabeled sequences from multiple sources, the same frozen encoder supports action classification, dense point generation, joint pose estimation, and future motion prediction on datasets not used for pretraining. Across these tasks, PT cubed outperforms the compared pretraining baselines and achieves competitive or superior performance to task-specific models.
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents