# Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy

arXiv: https://arxiv.org/abs/2610.02943 · HTML: https://mlsanity.com/paper/2610.02943/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 56 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 30 of 41)

- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose](https://mlsanity.com/paper/1611.07828/) (2016)
- [Differentially Private Learning with Adaptive Clipping](https://mlsanity.com/paper/1905.03871/) (2019)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1907.11346/) (2019)
- [3D Human Pose Estimation = 2D Pose Estimation + Matching](https://mlsanity.com/paper/1612.06524/) (2016)
- [TokenPose: Learning Keypoint Tokens for Human Pose Estimation](https://mlsanity.com/paper/2104.03516/) (2021)
- [DiffPose: Toward More Reliable 3D Pose Estimation](https://mlsanity.com/paper/2211.16940/) (2022)
- [Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification](https://mlsanity.com/paper/2007.03813/) (2020)
- [Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows](https://mlsanity.com/paper/2107.13788/) (2021)
- [Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation](https://mlsanity.com/paper/2303.11579/) (2023)
- [MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing](https://mlsanity.com/paper/2305.10345/) (2023)
- [Attentive Relational Networks for Mapping Images to Scene Graphs](https://mlsanity.com/paper/1811.10696/) (2018)
- [mm-Pose: Real-Time Human Skeletal Posture Estimation using mmWave Radars and CNNs](https://mlsanity.com/paper/1911.09592/) (2019)
- [Mixed Differential Privacy in Computer Vision](https://mlsanity.com/paper/2203.11481/) (2022)
- [SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning](https://mlsanity.com/paper/2212.10986/) (2022)
- [Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving](https://mlsanity.com/paper/2112.12141/) (2021)
- [mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors](https://mlsanity.com/paper/2210.08394/) (2022)
- [KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2404.00658/) (2024)
- [LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds](https://mlsanity.com/paper/2203.14698/) (2022)
- [Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning](https://mlsanity.com/paper/2406.14322/) (2024)
- [Membership Inference Attacks on Deep Regression Models for Neuroimaging](https://mlsanity.com/paper/2105.02866/) (2021)
- [Diffusion Model is a Good Pose Estimator from 3D RF-Vision](https://mlsanity.com/paper/2403.16198/) (2024)
- [Accelerating Minibatch Stochastic Gradient Descent using Stratified Sampling](https://mlsanity.com/paper/1405.3080/) (2014)
- [Subject Membership Inference Attacks in Federated Learning](https://mlsanity.com/paper/2206.03317/) (2022)

## Abstract (arXiv)

Multimodal 3D Human Pose Estimation (3D HPE) combines complementary information from RGB, LiDAR, and mmWave radar, but models trained on correlated observations from the same individuals, raise privacy risks overlooked by record level analysis. We present a unified framework for multimodal 3D HPE that couples kinematics-induced sensor fusion with subject level privacy auditing and private training. First, our multimodal model aligns modality specific joint representation, injects skeletal structure and adaptively aggregates complementary sensor evidence for accurate pose prediction. Second, we formulate a black-box subject membership inference attack for 3D HPE, complemented by an empirical pointwise maximal leakage analysis, which characterizes how individual attack score outcomes change inference about the membership outcome. Third, we instantiate user-level differential privacy via Action Temporal Stratification, a population weighted within-subject sampling strategy that enforces action and temporal coverage. We evaluate our framework on the MM-Fi dataset across three diverse experimental protocols. Source-code will be released upon acceptance.