.png){kind=icon}
返回
RelationTrack: Relation-Aware Multiple Object Tracking With Decoupled Representation
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2022.3150169.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Existing online multiple object tracking (MOT) algorithms often consist of two subtasks, detection and re-identification (ReID). In order to enhance the inference speed and reduce the complexity, current methods commonly integrate these double subtasks into a unified framework. Nevertheless, detection and ReID demand diverse features. This issue results in an optimization contradiction during the training procedure. With the target of alleviating this contradiction, we devise a module named Global Context Disentangling (GCD) that decouples the learned representation into detection-specific and ReID-specific embeddings. As such, this module provides an implicit manner to balance the different requirements of these two subtasks. Moreover, we observe that preceding MOT methods typically leverage local information to associate the detected targets and neglect to consider the global semantic relation. To resolve this limitation, we develop a module, referred to as Guided Transformer Encoder (GTE), by combining the powerful reasoning ability of Transformer encoder and deformable attention. Unlike previous works, GTE avoids analyzing all the pixels and only attends to capture the relation between query nodes and a few self-adaptively selected key samples. Therefore, it is computationally efficient. Extensive experiments have been conducted on the MOT16, MOT17 and MOT20 benchmarks to demonstrate the superiority of the proposed MOT framework, namely RelationTrack. The experimental results indicate that RelationTrack has surpassed preceding methods significantly and established a new state-of-the-art performance, e.g., IDF1 of 70.5% and MOTA of 67.2% on MOT20.
Keyword:
Decoupling representation
deformable attention
multiple object tracking
optimization contradiction
transformer encoder
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
Role of Urban Landscapes in Changing the Irrigation Water Requirements in Arid Climate.png)
GeosciencesOAAI
GeosciencesIF0
OAAI分享收藏
查看更多内容