论文标题
链式跟踪器：终端关节多对象检测和跟踪的链式配对的细心回归结果
Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking
论文作者
论文摘要
现有的多对象跟踪（MOT）方法遵循按检测范式进行跟踪，以分别进行对象检测，特征提取和数据关联，或者具有集成的三个子任务中的两个以形成部分端到端的解决方案。除了这些次优框架之外，我们提出了一个名为Chared-tracker（Ctracker）的简单在线模型，该模型自然地将所有三个子任务集成到端到端解决方案（据我们所知）。它是由重叠节点估算的链条边界框回归结果，每个节点涵盖了两个相邻的帧。配对回归是通过对象注意（由检测模块带来的）和身份注意（通过ID验证模块确保）的注意。这两个主要新颖性：链式结构和配对的细心回归，使Ctracker简单，快速有效，在MOT16和MOT17挑战数据集（分别为67.6和66.6）上设置了新的MOTA记录，而无需依靠任何额外的培训数据。可以在以下网址找到Ctracker的源代码：github.com/pjl1995/ctracker。
Existing Multiple-Object Tracking (MOT) methods either follow the tracking-by-detection paradigm to conduct object detection, feature extraction and data association separately, or have two of the three subtasks integrated to form a partially end-to-end solution. Going beyond these sub-optimal frameworks, we propose a simple online model named Chained-Tracker (CTracker), which naturally integrates all the three subtasks into an end-to-end solution (the first as far as we know). It chains paired bounding boxes regression results estimated from overlapping nodes, of which each node covers two adjacent frames. The paired regression is made attentive by object-attention (brought by a detection module) and identity-attention (ensured by an ID verification module). The two major novelties: chained structure and paired attentive regression, make CTracker simple, fast and effective, setting new MOTA records on MOT16 and MOT17 challenge datasets (67.6 and 66.6, respectively), without relying on any extra training data. The source code of CTracker can be found at: github.com/pjl1995/CTracker.
