# CREST: Convolutional Residual Learning for Visual Tracking

arXiv: https://arxiv.org/abs/1708.00225 · HTML: https://mlsanity.com/paper/1708.00225/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2017.

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

- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking](https://mlsanity.com/paper/2103.11681/) (2021)
- [VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples](https://mlsanity.com/paper/2103.05905/) (2021)
- [Parser-Free Virtual Try-on via Distilling Appearance Flows](https://mlsanity.com/paper/2103.04559/) (2021)
- [ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows](https://mlsanity.com/paper/2103.16877/) (2021)
- [PD-GAN: Probabilistic Diverse GAN for Image Inpainting](https://mlsanity.com/paper/2105.02201/) (2021)
- [Disentangled Cycle Consistency for Highly-realistic Virtual Try-On](https://mlsanity.com/paper/2103.09479/) (2021)
- [Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning](https://mlsanity.com/paper/2110.03909/) (2021)
- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [Saliency-Associated Object Tracking](https://mlsanity.com/paper/2108.03637/) (2021)
- [DeFLOCNet: Deep Image Editing via Flexible Low-level Controls](https://mlsanity.com/paper/2103.12723/) (2021)
- [IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking](https://mlsanity.com/paper/2103.14938/) (2021)
- [RTracker: Recoverable Tracking via PN Tree Structured Memory](https://mlsanity.com/paper/2403.19242/) (2024)
- [Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking](https://mlsanity.com/paper/2104.03114/) (2021)
- [Deep Snapshot HDR Reconstruction Based on the Polarization Camera](https://mlsanity.com/paper/2105.05824/) (2021)
- [Tracking by Joint Local and Global Search: A Target-aware Attention based Approach](https://mlsanity.com/paper/2106.04840/) (2021)
- [UHP-SOT: An Unsupervised High-Performance Single Object Tracker](https://mlsanity.com/paper/2110.01812/) (2021)
- [Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search](https://mlsanity.com/paper/2205.09676/) (2022)
- [Adaptive Siamese Tracking with a Compact Latent Network](https://mlsanity.com/paper/2302.00930/) (2023)
- [Distilling Channels for Efficient Deep Tracking](https://mlsanity.com/paper/2409.11785/) (2024)
- [Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression](https://mlsanity.com/paper/2110.06155/) (2021)
- [GUSOT: Green and Unsupervised Single Object Tracking for Long Video Sequences](https://mlsanity.com/paper/2207.07629/) (2022)
- [Unsupervised Lightweight Single Object Tracking with UHP-SOT++](https://mlsanity.com/paper/2111.07548/) (2021)
- [Efficient Light Field Reconstruction via Spatio-Angular Dense Network](https://mlsanity.com/paper/2108.03635/) (2021)
- [Single Object Tracking Research: A Survey](https://mlsanity.com/paper/2204.11410/) (2022)
- [UniSOT: A Unified Framework for Multi-Modality Single Object Tracking](https://mlsanity.com/paper/2511.01427/) (2025)
- [Deep Convolutional Correlation Iterative Particle Filter for Visual Tracking](https://mlsanity.com/paper/2107.02984/) (2021)
- [Context-aware Visual Tracking with Joint Meta-updating](https://mlsanity.com/paper/2204.01513/) (2022)
- [DCFG: Diverse Cross-Channel Fine-Grained Feature Learning and Progressive Fusion Siamese Tracker for Thermal Infrared Target Tracking](https://mlsanity.com/paper/2504.14311/) (2025)

## Abstract (arXiv)

Discriminative correlation filters (DCFs) have been shown to perform superiorly in visual tracking. They only need a small set of training samples from the initial frame to generate an appearance model. However, existing DCFs learn the filters separately from feature extraction, and update these filters using a moving average operation with an empirical weight. These DCF trackers hardly benefit from the end-to-end training. In this paper, we propose the CREST algorithm to reformulate DCFs as a one-layer convolutional neural network. Our method integrates feature extraction, response map generation as well as model update into the neural networks for an end-to-end training. To reduce model degradation during online update, we apply residual learning to take appearance changes into account. Extensive experiments on the benchmark datasets demonstrate that our CREST tracker performs favorably against state-of-the-art trackers.