发表机构
Clausthal University of Technology (TU Clausthal)（克劳斯塔尔工业大学（克劳斯塔尔工业大学））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出SPARC，一种贝叶斯-保形不确定性层，在9个数据集-协议模块上的NLL及MPJPE+NLL综合指标优于基线，可作为轻量风险监控工具。
AI 中文摘要
人类运动预测模型的准确性和速度不断提升，但可靠部署需要结构化、校准且高效的不确定性估计。基于贝叶斯和集成的不确定性估计通常需要重复随机推理[15,26]，而仅保形校准无法提供认知信号或保留轨迹协方差结构[14,50]。本文提出SPARC（Single-Pass Adaptive Risk Calibration，单通自适应风险校准），一种用于运动预测的贝叶斯-保形不确定性层。确定性MLP主干预测未来均值，共轭贝叶斯最后层将时域特征杠杆转化为解析的逐时间步认知尺度κ_t(x)；该尺度在不改变图-时间高斯协方差相关结构的前提下对其进行膨胀，且拆分保形校准可生成95%边际预测管，在可交换性下具有有限样本有效性。核心接口为结构化分解κ_t(x)Σ_{str,t}(x)，其无需蒙特卡洛采样即可将特征空间认知不确定性注入轨迹密度。在9个数据集-协议模块及确定性、多模态、校准基线中，SPARC在NLL（负对数似然）和MPJPE+NLL综合指标上排名第一，同时保持有竞争力的点精度和高效的校准管；通过κ进行排名窗口可分离高误差案例，使该尺度可作为轻量风险监控工具使用。
英文摘要
Human motion forecasters are increasingly accurate and fast, but reliable deployment requires uncertainty estimates that are structured, calibrated, and efficient. Bayesian and ensemble-based uncertainty estimates often require repeated stochastic inference [15, 26], while conformal calibration alone does not provide an epistemic signal or preserve trajectory covariance structure [14, 50]. We introduce SPARC (Single-Pass Adaptive Risk Calibration), a Bayesian-conformal uncertainty layer for motion forecasting. A deterministic MLP backbone predicts the future mean, and a conjugate Bayesian last layer converts time-domain feature leverage into an analytic horizon-wise epistemic scale $κ_t(x)$. This scale inflates a graph-temporal Gaussian covariance without changing its correlation structure, and split conformal calibration produces 95% marginal prediction tubes with finite-sample validity under exchangeability. The key interface is the structured factorization $κ_t(x)Σ_{\mathrm{str},t}(x)$, which injects feature-space epistemic uncertainty into trajectory densities without Monte Carlo sampling. Across nine dataset-protocol blocks and deterministic, multimodal, and calibration baselines, SPARC ranks first on NLL and on the combined MPJPE+NLL criterion while retaining competitive point accuracy and efficient calibrated tubes. Ranking windows by $κ$ separates high-error cases, making the scale usable as a lightweight risk monitor.
CommentsAccepted at ECCV 2026
