BAL:在潜空间做双向自回归的自监督人体动作表征框架
BAL: Bidirectional Autoregression in Latent Space for Learning Human Movement Representations
做人体动作建模、行为预测的值得关注:这篇论文用双向时序预测当自监督信号,不用再调增强和掩码那些超参数,在动作描述、预测、插值上指标普遍超过基线。方法证明部分也写得扎实,适合做表征学习的人参考。
BAL 是一个自监督人体动作表征学习框架,核心思路是从日常行为的自然时序结构中获取监督信号,替代依赖数据增强不变性或掩码恢复这类人工假设的方法。
它在语义抽象的潜空间中做自回归预测,同时向前和向后双向预测时间序列,推理时可以同时利用过去与未来上下文提取表征。为抑制表征塌缩,BAL 把每个预测目标拆解为捕捉序列级语义的全局分量和捕捉上下文无关运动的局部分量,并证明除非表征完全塌缩,局部目标仍保有非平凡的角多样性,从而维持有效训练信号。
在多个大规模数据集上的实验显示,BAL 的表征在动作描述、运动预测和插值任务上均表现良好,大多数评估指标超过基线方法。相比现有需要调节启发式超参数的自监督方案,BAL 减少了对超参数设置的敏感性。
BAL: Bidirectional Autoregression in Latent Space for Learning Human Movement Representations
Learning semantically meaningful human movement representations from 3D pose sequences is essential for human behavior modeling. Existing self-supervised methods derive supervision from artificial assumptions, e.g., invariance to augmentation within a certain range or recoverability of masked regions at a certain temporal scale, introducing heuristic hyperparameters that make the learned semantics sensitive to their settings. We propose BAL, a self-supervised framework that instead exploits supervision intrinsic to human movement: the natural ordering structure of everyday behavior. BAL autoregressively predicts in a semantically abstract latent space, analogous to how humans anticipate others' actions rather than their precise joint configurations. Bidirectional autoregressive prediction, both forward and backward in time, fully leverages these ordering constraints while enabling representation extraction using both past and future context at inference. To suppress representation collapse, BAL decomposes each prediction target into a global component capturing sequence-level semantics and a local component capturing context-independent movement. We prove that the local targets retain nontrivial angular diversity unless the representations are completely collapsed, preserving a meaningful training signal. Experiments on large-scale datasets demonstrate that BAL's representations are highly effective for motion captioning, forecasting, and interpolation, outperforming baselines on most evaluation metrics.
本条情报归属 AITOP「论文」核心追踪栏目。涉及核心实体与技术议题包括:自监督学习、动作识别、表征学习、时序建模,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Genki Kinoshita, Ko Nishino),经 AITOP 多维评分管线结构化提炼。