用点标注替代框标注，实现高效多目标追踪。
PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking
- 从点出发构建实例，通过时序反馈与波浪注意力增强定位
- 在四个数据集上达新纪录，点监督追踪性能超越现有方法
- 适合标注成本敏感、需轻量标注的视频追踪场景
我们提出点监督多目标追踪（PS-MOT），作为一种低成本替代传统框标注的方法，将关注点从空间拟合转向以拓扑中心为核心的表征。然而，由于缺乏显式几何结构和尺度约束，PS-MOT面临空间模糊和身份漂移等问题。为此，我们提出PS-Track，一个在数据、模型和损失层面均实现从点到实例演化的分层流程。在数据层面，引入时序反馈提示（TFP），利用负向空间线索和运动先验将点演化为时序一致的伪标签；在模型层面，设计点激发小波注意力（PEWA）模块，借助语义相关性激活高频成分，‘幻化’出物体边界；在损失层面，采用不确定性引导高斯学习（UGL），将伪标签建模为概率分布，动态调节监督强度。在DanceTrack、EmboTrack、SportsMOT和JRDB上的实验表明，PS-Track在多种追踪场景下均表现可行且有效，建立了点监督追踪的新基准。代码已开源。
原文摘要 · Abstract (English)
We introduce Point-supervised Multi-Object Tracking (PS-MOT) as a cost-effective alternative to traditional bounding box supervision, shifting the focus from spatial fitting to topological center-driven representation. However, PS-MOT faces challenges, e.g., spatial ambiguity and identity drift due to the lack of explicit geometric structure and scale constraints. To address these, we propose PS-Track, a hierarchical pipeline transitioning from points to instances across data, model, and loss levels. At the data level, we introduce Temporal-Feedback Prompting (TFP) to evolve points into temporally consistent pseudo-labels using negative spatial cues and motion priors. At the model level, we design the Point-Excited Wavelet Attention (PEWA) module, which leverages semantic correlations to activate high-frequency components, ``hallucinating'' object boundaries. At the loss level, Uncertainty-Guided Gaussian Learning (UGL) models pseudo-labels as probabilistic distributions, dynamically calibrating supervision intensity. Experiments on DanceTrack, EmboTrack, SportsMOT, and JRDB demonstrate that PS-Track provides a feasible and effective point-supervised alternative across diverse tracking scenarios, establishing a new state-of-the-art for point-supervised tracking. The source code is available at https://github.com/xifen523/PS-MOT.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。