论文标题
一个简单的基线，用于在拥挤场景的视频中进行姿势跟踪
A Simple Baseline for Pose Tracking in Videos of Crowded Scenes
论文作者
论文摘要
本文介绍了我们针对ACM MM挑战的解决方案：复杂事件中的大规模以人为中心的视频分析\ Cite {Lin2020Human}；具体来说，在这里，我们专注于Track3：在复杂事件中的人群姿势跟踪。近年来，在多档次培训中取得了显着进展。但是，如何在拥挤且复杂的环境中追踪人姿势尚未得到很好的解决。我们将问题提出为要解决的几个子问题。首先，我们使用多目标跟踪方法将人ID分配给检测模型生成的每个边界框。之后，将姿势生成带有ID的每个边界框。最后，光流用于利用视频中的时间信息，并生成最终的姿势跟踪结果。
This paper presents our solution to ACM MM challenge: Large-scale Human-centric Video Analysis in Complex Events\cite{lin2020human}; specifically, here we focus on Track3: Crowd Pose Tracking in Complex Events. Remarkable progress has been made in multi-pose training in recent years. However, how to track the human pose in crowded and complex environments has not been well addressed. We formulate the problem as several subproblems to be solved. First, we use a multi-object tracking method to assign human ID to each bounding box generated by the detection model. After that, a pose is generated to each bounding box with ID. At last, optical flow is used to take advantage of the temporal information in the videos and generate the final pose tracking result.
