Current popular online multi-object tracking (MOT) solutions apply single
object trackers (SOTs) to capture object motions, while often requiring an
extra affinity network to associate objects, especially for the occluded ones.
This brings extra computational overhead due to repetitive feature extraction
for SOT and affinity computation. Meanwhile, the model size of the
sophisticated affinity network is usually non-trivial. In this paper, we
propose a novel MOT framework that unifies object motion and affinity model
into a single network, named UMA, in order to learn a compact feature that is
discriminative for both object motion and affinity measure. In particular, UMA
integrates single object tracking and metric learning into a unified triplet
network by means of multi-task learning. Such design brings advantages of
improved computation efficiency, low memory requirement and simplified training
procedure. In addition, we equip our model with a task-specific attention
module, which is used to boost task-aware feature learning. The proposed UMA
can be easily trained end-to-end, and is elegant - requiring only one training
stage. Experimental results show that it achieves promising performance on
several MOT Challenge benchmarks.

本论文提出了一种新的 MOT 框架，即 UMA，该框架将对象运动和亲和模型统一到一个网络中，通过多任务学习，将单目标跟踪和度量学习集成在一个统一的三元组网络中。实验结果表明，UMA 在几个 MOT 挑战基准上取得了有希望的性能。

面向在线多目标跟踪的统一目标运动和相似性模型

A Unified Object Motion and Affinity Model for Online Multi-Object  Tracking

Data association-based multiple object tracking (MOT) involves multiple
separated modules processed or optimized differently, which results in complex
method design and requires non-trivial tuning of parameters. In this paper, we
present an end-to-end model, named FAMNet, where Feature extraction, Affinity
estimation and Multi-dimensional assignment are refined in a single network.
All layers in FAMNet are designed differentiable thus can be optimized jointly
to learn the discriminative features and higher-order affinity model for robust
MOT, which is supervised by the loss directly from the assignment ground truth.
We also integrate single object tracking technique and a dedicated target
management scheme into the FAMNet-based tracking system to further recover
false negatives and inhibit noisy target candidates generated by the external
detector. The proposed method is evaluated on a diverse set of benchmarks
including MOT2015, MOT2017, KITTI-Car and UA-DETRAC, and achieves promising
performance on all of them in comparison with state-of-the-arts.

本文提出了一种名为 FAMNet 的端到端模型，其中特征提取、亲和性估计和多维分配都在单个网络中优化，通过直接从分配标准答案中监督学习来实现鲁棒 MOT 的区分性特征和高阶亲和性模型。同时，将单目标跟踪技术和专用目标管理方案集成到 FAMNet 跟踪系统中，进一步恢复假阴性和抑制外部检测器生成的噪声目标候选项。在 MOT2015、MOT2017、KITTI-Car 和 UA-DETRAC 等多个基准测试上进行了评估，并与现有技术进行比较，在所有测试中均取得了出色表现。