# An Accelerated Correlation Filter Tracker

arXiv: https://arxiv.org/abs/1912.02854 · HTML: https://mlsanity.com/paper/1912.02854/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2019.

## Built on by (most cited first, 12 of 12)

- [One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion](https://mlsanity.com/paper/2502.19854/) (2025)
- [TGFuse: An Infrared and Visible Image Fusion Approach Based on Transformer and Generative Adversarial Network](https://mlsanity.com/paper/2201.10147/) (2022)
- [Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections](https://mlsanity.com/paper/2411.14796/) (2024)
- [Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm](https://mlsanity.com/paper/2509.24741/) (2025)
- [Omni Survey for Multimodality Analysis in Visual Object Tracking](https://mlsanity.com/paper/2508.13000/) (2025)
- [A Tri-Modal Dataset and a Baseline System for Tracking Unmanned Aerial Vehicles](https://mlsanity.com/paper/2511.18344/) (2025)
- [UASTrack: A Unified Adaptive Selection Framework with Modality-Customization in Single Object Tracking](https://mlsanity.com/paper/2502.18220/) (2025)
- [Event Data Association via Robust Model Fitting for Event-based Object Tracking](https://mlsanity.com/paper/2110.12962/) (2021)
- [Unsupervised Image Fusion Method based on Feature Mutual Mapping](https://mlsanity.com/paper/2201.10152/) (2022)
- [Real-Time Siamese Multiple Object Tracker with Enhanced Proposals](https://mlsanity.com/paper/2202.04966/) (2022)
- [CWP: Instance complexity weighted channel-wise soft masks for network pruning](https://mlsanity.com/paper/2209.03534/) (2022)
- [Revisiting RGBT Tracking Benchmarks from the Perspective of Modality Validity: A New Benchmark, Problem, and Solution](https://mlsanity.com/paper/2405.00168/) (2024)

## Abstract (arXiv)

Recent visual object tracking methods have witnessed a continuous improvement in the state-of-the-art with the development of efficient discriminative correlation filters (DCF) and robust deep neural network features. Despite the outstanding performance achieved by the above combination, existing advanced trackers suffer from the burden of high computational complexity of the deep feature extraction and online model learning. We propose an accelerated ADMM optimisation method obtained by adding a momentum to the optimisation sequence iterates, and by relaxing the impact of the error between DCF parameters and their norm. The proposed optimisation method is applied to an innovative formulation of the DCF design, which seeks the most discriminative spatially regularised feature channels. A further speed up is achieved by an adaptive initialisation of the filter optimisation process. The significantly increased convergence of the DCF filter is demonstrated by establishing the optimisation process equivalence with a continuous dynamical system for which the convergence properties can readily be derived. The experimental results obtained on several well-known benchmarking datasets demonstrate the efficiency and robustness of the proposed ACFT method, with a tracking accuracy comparable to the start-of-the-art trackers.