# ECO: Efficient Convolution Operators for Tracking

arXiv: https://arxiv.org/abs/1611.09224 · HTML: https://mlsanity.com/paper/1611.09224/

## Key facts

- Cited by 239 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2016.

## Built on by (most cited first, 30 of 239)

- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Transformer Tracking](https://mlsanity.com/paper/2103.15436/) (2021)
- [Learning Spatio-Temporal Transformer for Visual Tracking](https://mlsanity.com/paper/2103.17154/) (2021)
- [Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework](https://mlsanity.com/paper/2203.11991/) (2022)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking](https://mlsanity.com/paper/2103.11681/) (2021)
- [Low-Light Image and Video Enhancement Using Deep Learning: A Survey](https://mlsanity.com/paper/2104.10729/) (2021)
- [Learning Target Candidate Association to Keep Track of What Not to Track](https://mlsanity.com/paper/2103.16556/) (2021)
- [Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark](https://mlsanity.com/paper/2103.16746/) (2021)
- [Transforming Model Prediction for Tracking](https://mlsanity.com/paper/2203.11192/) (2022)
- [DREAM: Efficient Dataset Distillation by Representative Matching](https://mlsanity.com/paper/2302.14416/) (2023)
- [Towards Grand Unification of Object Tracking](https://mlsanity.com/paper/2207.07078/) (2022)
- [Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline](https://mlsanity.com/paper/2204.04120/) (2022)
- [Object Tracking by Jointly Exploiting Frame and Event Domain](https://mlsanity.com/paper/2109.09052/) (2021)
- [LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search](https://mlsanity.com/paper/2104.14545/) (2021)
- [Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers](https://mlsanity.com/paper/2403.10574/) (2024)
- [Transformer Tracking with Cyclic Shifting Window Attention](https://mlsanity.com/paper/2205.03806/) (2022)
- [HiFT: Hierarchical Feature Transformer for Aerial Tracking](https://mlsanity.com/paper/2108.00202/) (2021)
- [Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance](https://mlsanity.com/paper/2403.05231/) (2024)
- [TCTrack: Temporal Contexts for Aerial Tracking](https://mlsanity.com/paper/2203.01885/) (2022)
- [Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2108.04728/) (2021)
- [Do Different Tracking Tasks Require Different Appearance Models?](https://mlsanity.com/paper/2107.02156/) (2021)
- [Correlation-Aware Deep Tracking](https://mlsanity.com/paper/2203.01666/) (2022)
- [Joint Inductive and Transductive Learning for Video Object Segmentation](https://mlsanity.com/paper/2108.03679/) (2021)
- [Joint Visual Grounding and Tracking with Natural Language Specification](https://mlsanity.com/paper/2303.12027/) (2023)
- [3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds](https://mlsanity.com/paper/2111.04426/) (2021)
- [Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking](https://mlsanity.com/paper/2308.06904/) (2023)
- [Adversarial Example Detection for DNN Models: A Review and Experimental Comparison](https://mlsanity.com/paper/2105.00203/) (2021)
- [Compact Transformer Tracker with Correlative Masked Modeling](https://mlsanity.com/paper/2301.10938/) (2023)
- [Explicit Visual Prompts for Visual Object Tracking](https://mlsanity.com/paper/2401.03142/) (2024)

## Abstract (arXiv)

In recent years, Discriminative Correlation Filter (DCF) based methods have significantly advanced the state-of-the-art in tracking. However, in the pursuit of ever increasing tracking performance, their characteristic speed and real-time capability have gradually faded. Further, the increasingly complex models, with massive number of trainable parameters, have introduced the risk of severe over-fitting. In this work, we tackle the key causes behind the problems of computational complexity and over-fitting, with the aim of simultaneously improving both speed and performance. We revisit the core DCF formulation and introduce: (i) a factorized convolution operator, which drastically reduces the number of parameters in the model; (ii) a compact generative model of the training sample distribution, that significantly reduces memory and time complexity, while providing better diversity of samples; (iii) a conservative model update strategy with improved robustness and reduced complexity. We perform comprehensive experiments on four benchmarks: VOT2016, UAV123, OTB-2015, and TempleColor. When using expensive deep features, our tracker provides a 20-fold speedup and achieves a 13.0% relative gain in Expected Average Overlap compared to the top ranked method in the VOT2016 challenge. Moreover, our fast variant, using hand-crafted features, operates at 60 Hz on a single CPU, while obtaining 65.0% AUC on OTB-2015.