发表机构
University of Ljubljana（卢布尔雅那大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
UGO提出统一分割架构，结合示例条件检测与实例传播头，通过能量最小化整合和分层记忆，在GMOT基准和视频计数上达到新最优，并可与专业MOT方法竞争。
AI 中文摘要
通用多目标跟踪（GMOT）旨在从单个首帧示例中跟踪用户指定类别的所有实例。先前的工作依赖边界框和代理训练，难以处理非刚性物体、拥挤场景和干扰物。我们提出UGO，一种统一的GMOT跟踪器，在通用架构中配对预训练的示例条件检测头与实例传播头。一种新颖的无需训练、能量最小化整合方法将重叠提议转换为独占的像素级掩码和检测，解决过分割、重复和冲突问题。跨越全局和实例级别的分层记忆通过新的记忆管理协议提高召回率和逐实例分割精度。UGO在GMOT基准和视频对象计数上创下新的最先进水平，并与专业MOT方法竞争，为统一、开放类别的多目标跟踪建立了强有力的范式。
英文摘要
General multi-object tracking (GMOT) tracks all instances of a user-specified category from a single first-frame exemplar. Prior work relies on bounding boxes and surrogate training, and struggles with non-rigid objects, crowded scenes, and distractors. We introduce UGO, a unified GMOT tracker that pairs a pretrained exemplar-conditioned detection head with an instance-propagation head in a common architecture. A novel training-free, energy-minimization consolidation method converts overlapping proposals into exclusive pixel-wise masks and detections, resolving over-segmentation, duplicates, and conflicts. A hierarchical memory spanning global and instance levels improves recall and per-instance segmentation accuracy using a new memory management protocol. UGO sets a new state-of-the-art on GMOT benchmarks and video object counting, and is competitive with specialist MOT methods, establishing a strong paradigm for unified, open-category multi-object tracking.
CommentsAccepted to NeurIPS2026
