# TrackNetV5: Residual-Driven Spatio-Temporal Refinement and Motion Direction Decoupling for Fast Object Tracking

arXiv: https://arxiv.org/abs/2512.02789 · HTML: https://mlsanity.com/paper/2512.02789/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Convolutional Pose Machines](https://mlsanity.com/paper/1602.00134/) (2016)
- [TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications](https://mlsanity.com/paper/1907.03698/) (2019)
- [TrackNetV4: Enhancing Fast Sports Object Tracking with Motion Attention Maps](https://mlsanity.com/paper/2409.14543/) (2024)
- [TOTNet: Occlusion-Aware Temporal Tracking for Robust Ball Detection in Sports Videos](https://mlsanity.com/paper/2508.09650/) (2025)

## Abstract (arXiv)

The TrackNet series has established a strong baseline for fast-moving small object tracking in sports. However, existing iterations face significant limitations: V1-V3 struggle with occlusions due to a reliance on purely visual cues, while TrackNetV4, despite introducing motion inputs, suffers from directional ambiguity as its absolute difference method discards motion polarity. To overcome these bottlenecks, we propose TrackNetV5, a robust architecture integrating two novel mechanisms. First, to recover lost directional priors, we introduce the Motion Direction Decoupling (MDD) module. Unlike V4, MDD decomposes temporal dynamics into signed polarity fields, explicitly encoding both movement occurrence and trajectory direction. Second, we propose the Residual-Driven Spatio-Temporal Refinement (R-STR) head. Operating on a coarse-to-fine paradigm, this Transformer-based module leverages factorized spatio-temporal contexts to estimate a corrective residual, effectively recovering occluded targets. Extensive experiments on the TrackNetV2 dataset demonstrate that TrackNetV5 achieves a new state-of-the-art F1-score of 0.9859 and an accuracy of 0.9733, significantly outperforming previous versions. Notably, this performance leap is achieved with a marginal 3.7% increase in FLOPs compared to V4, maintaining real-time inference capabilities while delivering superior tracking precision.