The Progression of Transformers from Language to Vision to MOT: A Literature Review on Multi-Object Tracking with Transformers
It provides a synthesis of existing research for practitioners in computer vision and MOT, highlighting incremental progress rather than new breakthroughs.
This literature review examines the application of transformer architectures from natural language processing to computer vision, specifically in Multi-Object Tracking (MOT), where they are becoming competitive but still lag behind traditional deep learning methods.
The transformer neural network architecture allows for autoregressive sequence-to-sequence modeling through the use of attention layers. It was originally created with the application of machine translation but has revolutionized natural language processing. Recently, transformers have also been applied across a wide variety of pattern recognition tasks, particularly in computer vision. In this literature review, we describe major advances in computer vision utilizing transformers. We then focus specifically on Multi-Object Tracking (MOT) and discuss how transformers are increasingly becoming competitive in state-of-the-art MOT works, yet still lag behind traditional deep learning methods.