# SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking

arXiv: https://arxiv.org/abs/1904.04452 · HTML: https://mlsanity.com/paper/1904.04452/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2019.

## Built on by (most cited first, 29 of 29)

- [Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking](https://mlsanity.com/paper/2103.11681/) (2021)
- [STMTrack: Template-free Visual Tracking with Space-time Memory Networks](https://mlsanity.com/paper/2104.00324/) (2021)
- [Disentangled Representation Learning for Text-Video Retrieval](https://mlsanity.com/paper/2203.07111/) (2022)
- [Correlation-Aware Deep Tracking](https://mlsanity.com/paper/2203.01666/) (2022)
- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking](https://mlsanity.com/paper/2101.08466/) (2021)
- [Saliency-Associated Object Tracking](https://mlsanity.com/paper/2108.03637/) (2021)
- [VastTrack: Vast Category Visual Object Tracking](https://mlsanity.com/paper/2403.03493/) (2024)
- [Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization](https://mlsanity.com/paper/2211.10528/) (2022)
- [Active Learning for Deep Visual Tracking](https://mlsanity.com/paper/2110.13259/) (2021)
- [Learning to Filter: Siamese Relation Network for Robust Tracking](https://mlsanity.com/paper/2104.00829/) (2021)
- [SiamMask: A Framework for Fast Online Object Tracking and Segmentation](https://mlsanity.com/paper/2207.02088/) (2022)
- [Ranking-Based Siamese Visual Tracking](https://mlsanity.com/paper/2205.11761/) (2022)
- [eMoE-Tracker: Environmental MoE-based Transformer for Robust Event-guided Object Tracking](https://mlsanity.com/paper/2406.20024/) (2024)
- [SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking](https://mlsanity.com/paper/2105.11237/) (2021)
- [Correlation-Embedded Transformer Tracking: A Single-Branch Framework](https://mlsanity.com/paper/2401.12743/) (2024)
- [Learning Localization-aware Target Confidence for Siamese Visual Tracking](https://mlsanity.com/paper/2204.14093/) (2022)
- [Adaptive Siamese Tracking with a Compact Latent Network](https://mlsanity.com/paper/2302.00930/) (2023)
- [Benchmarking Deep Trackers on Aerial Videos](https://mlsanity.com/paper/2103.12924/) (2021)
- [Updatable Siamese Tracker with Two-stage One-shot Learning](https://mlsanity.com/paper/2104.15049/) (2021)
- [Domain Adaptive SiamRPN++ for Object Tracking in the Wild](https://mlsanity.com/paper/2106.07862/) (2021)
- [Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking](https://mlsanity.com/paper/2111.11625/) (2021)
- [Single Object Tracking Research: A Survey](https://mlsanity.com/paper/2204.11410/) (2022)
- [Real-Time Visual Object Tracking via Few-Shot Learning](https://mlsanity.com/paper/2103.10130/) (2021)
- [Learning Online for Unified Segmentation and Tracking Models](https://mlsanity.com/paper/2111.06994/) (2021)
- [Higher Performance Visual Tracking with Dual-Modal Localization](https://mlsanity.com/paper/2103.10089/) (2021)
- [Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking](https://mlsanity.com/paper/2112.14016/) (2021)
- [Staged Depthwise Correlation and Feature Fusion for Siamese Object Tracking](https://mlsanity.com/paper/2310.09747/) (2023)
- [Dynamic Attention Mechanism in Spatiotemporal Memory Networks for Object Tracking](https://mlsanity.com/paper/2503.16768/) (2025)

## Abstract (arXiv)

The greatest challenge facing visual object tracking is the simultaneous requirements on robustness and discrimination power. In this paper, we propose a SiamFC-based tracker, named SPM-Tracker, to tackle this challenge. The basic idea is to address the two requirements in two separate matching stages. Robustness is strengthened in the coarse matching (CM) stage through generalized training while discrimination power is enhanced in the fine matching (FM) stage through a distance learning network. The two stages are connected in series as the input proposals of the FM stage are generated by the CM stage. They are also connected in parallel as the matching scores and box location refinements are fused to generate the final results. This innovative series-parallel structure takes advantage of both stages and results in superior performance. The proposed SPM-Tracker, running at 120fps on GPU, achieves an AUC of 0.687 on OTB-100 and an EAO of 0.434 on VOT-16, exceeding other real-time trackers by a notable margin.