用语义查询监控点跟踪，抑制长时间运动中的漂移问题。
QueST: Persistent Queries as Semantic Monitors for Drift Suppression in Long-Horizon Tracking
- 将跟踪点视为持久语义查询，全局关注时空特征而非局部匹配。
- 在PartNet-Mobility数据集上比TAP-Net降低67.7%的终点绝对误差。
- 适合需要长期稳定跟踪的机器人视觉与视频分析场景。
视频中点的跟踪通常被建模为帧间局部对应关系，但面对形变、遮挡和视角变化时，错误会累积导致无声的语义漂移，现有追踪器无法检测或纠正。本文从监控视角重新思考长时跟踪，提出QueST框架，将相关实体视为持续的语义查询，而非瞬时轨迹。每个查询在每一步时间都全局关注时空视频特征，提供跨时间的稳定语义锚点。进一步通过轻量级3D物理约束，利用几何合理性抑制遮挡下的无界漂移。在SAPIEN的PartNet-Mobility长时形变序列上评估，相比RAFT-3D、CoTracker和TAP-Net，QueST显著降低终端漂移，较TAP-Net实现67.7%的绝对点误差（APE）改进，并更好保持目标身份。结果表明，将语义监控直接嵌入感知可提升分布偏移下的长时跟踪可靠性。
原文摘要 · Abstract (English)
Tracking points in videos is typically formulated as frame-to-frame correspondence, where each point is matched locally to the next frame. While this works over short horizons, errors accumulate under articulation, occlusion, and viewpoint change, leading to silent semantic drift that existing trackers cannot detect or correct. In this work, we revisit long-horizon tracking from a monitoring perspective and introduce QueST, a monitoring-by-design framework that treats interaction-relevant entities as persistent semantic queries rather than transient point tracks. Instead of local propagation, each query attends globally over spatio-temporal video features at every time-step, providing a stable semantic anchor across time. We further constrain query trajectories with lightweight 3D physical grounding, using geometric plausibility to suppress unbounded drift under occlusion. We evaluate QueST on long-horizon articulated sequences from PartNet-Mobility in SAPIEN and compare against RAFT-3D, CoTracker, and TAP-Net. QueST substantially reduces terminal drift achieving a 67.7% Absolute Point Error (APE) improvement over TAP-Net while better preserving identity over extended horizons. Our results show that embedding semantic monitoring directly into perception enables more reliable long-horizon tracking under distribution shift.
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。