# Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking

arXiv: https://arxiv.org/abs/1707.02309 · HTML: https://mlsanity.com/paper/1707.02309/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2017.

## Built on by (most cited first, 8 of 8)

- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [MovieChat+: Question-aware Sparse Memory for Long Video Question Answering](https://mlsanity.com/paper/2404.17176/) (2024)
- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [GridDehazeNet+: An Enhanced Multi-Scale Network with Intra-Task Knowledge Transfer for Single Image Dehazing](https://mlsanity.com/paper/2103.13998/) (2021)
- [OnlineHOI: Towards Online Human-Object Interaction Generation and Perception](https://mlsanity.com/paper/2509.12250/) (2025)
- [Learning Frequency and Memory-Aware Prompts for Multi-Modal Object Tracking](https://mlsanity.com/paper/2506.23972/) (2025)
- [Sparse Regularized Correlation Filter for UAV Object Tracking with adaptive Contextual Learning and Keyfilter Selection](https://mlsanity.com/paper/2205.03627/) (2022)
- [LSDM: Long-Short Diffeomorphic Motion for Weakly-Supervised Ultrasound Landmark Tracking](https://mlsanity.com/paper/2301.04748/) (2023)

## Abstract (arXiv)

Object tracking is challenging as target objects often undergo drastic appearance changes over time. Recently, adaptive correlation filters have been successfully applied to object tracking. However, tracking algorithms relying on highly adaptive correlation filters are prone to drift due to noisy updates. Moreover, as these algorithms do not maintain long-term memory of target appearance, they cannot recover from tracking failures caused by heavy occlusion or target disappearance in the camera view. In this paper, we propose to learn multiple adaptive correlation filters with both long-term and short-term memory of target appearance for robust object tracking. First, we learn a kernelized correlation filter with an aggressive learning rate for locating target objects precisely. We take into account the appropriate size of surrounding context and the feature representations. Second, we learn a correlation filter over a feature pyramid centered at the estimated target position for predicting scale changes. Third, we learn a complementary correlation filter with a conservative learning rate to maintain long-term memory of target appearance. We use the output responses of this long-term filter to determine if tracking failure occurs. In the case of tracking failures, we apply an incrementally learned detector to recover the target position in a sliding window fashion. Extensive experimental results on large-scale benchmark datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods in terms of efficiency, accuracy, and robustness.