发表机构
Huazhong University of Science and Technology; Jiangxi University of Water Resources and Electric Power; Zhongnan University of Economics and Law（华中科技大学; 江西水利电力大学; 中南财经政法大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出递归事件世界模型ReWorld-Track，通过携带关联不确定性并利用后验更新信念，在语言引导多摄像机跟踪中改善身份连续性，在CityFlowV2和MTMMC上取得领先HOTA分数。
AI 中文摘要
语言引导的多摄像机跟踪必须在未观测的间隙中保持目标身份一致，其中相似候选和不确定返回可能使早期关联不可靠。错误的匹配会污染用于预测后续观测的历史，并在后续摄像机切换中传播身份错误。我们提出ReWorld-Track，一种递归事件世界模型，将关联不确定性带入未来预测。候选匹配和持续等待定义了替代目标状态，其后验概率用于更新持久递归信念。这种表示通过连续观测保留了关于替代轨迹的不确定性。该信念预测下一个摄像机、到达时间和进入区域，而外观和语言证据引导关联。通过在连续切换上进行训练，模型学会保留对后续预测和身份决策有用的不确定性。ReWorld-Track在CityFlowV2上取得65.19的HOTA分数，在MTMMC上取得45.36，并在重复切换中改善了身份连续性。在MTMMC上，其结构化后验更新比类似规模的通用更新器高出0.50 HOTA点，比固定时刻软关联高出0.94点，将下一摄像机准确率从86.03%提高到87.41%，并将后续目标返回的中位到达时间误差从0.78秒降低到0.71秒。
英文摘要
Language-guided multi-camera tracking must preserve a target identity across unobserved gaps, where similar candidates and uncertain returns can make early associations unreliable. A wrong match can corrupt the history used to predict later observations and propagate identity errors across subsequent camera handoffs. We propose ReWorld-Track, a recursive event world model that carries association uncertainty into future predictions. Candidate matches and continued waiting define alternative target states, whose posterior probabilities are used to update a persistent recurrent belief. This representation preserves uncertainty about alternative trajectories through successive observations. This belief predicts the next camera, arrival time, and entry region, while appearance and language evidence guide association. By training across successive handoffs, the model learns to retain uncertainty that remains useful for later predictions and identity decisions. ReWorld-Track achieves HOTA scores of 65.19 on CityFlowV2 and 45.36 on MTMMC, with improved identity continuity across repeated handoffs. On MTMMC, its structured posterior update gains 0.50 HOTA points over a similarly sized generic updater and 0.94 points over fixed-moment soft association, raising next-camera accuracy from 86.03% to 87.41% and reducing median arrival-time error from 0.78 s to 0.71 s for subsequent target returns.
Comments41 pages, 8 figures. Corrected an author name; scientific content unchanged
