# Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy

arXiv: https://arxiv.org/abs/2104.12041 · HTML: https://mlsanity.com/paper/2104.12041/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 25 Apr 2021.

## Builds on (most cited first, 30 of 33)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking](https://mlsanity.com/paper/1809.07845/) (2018)
- [Learning Discriminative Model Prediction for Tracking](https://mlsanity.com/paper/1904.07220/) (2019)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [Towards Real-Time Multi-Object Tracking](https://mlsanity.com/paper/1909.12605/) (2019)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [ECO: Efficient Convolution Operators for Tracking](https://mlsanity.com/paper/1611.09224/) (2016)
- [Ocean: Object-aware Anchor-free Tracking](https://mlsanity.com/paper/2006.10721/) (2020)
- [Learning Multi-Domain Convolutional Neural Networks for Visual Tracking](https://mlsanity.com/paper/1510.07945/) (2015)
- [Joint Detection and Identification Feature Learning for Person Search](https://mlsanity.com/paper/1604.01850/) (2016)
- [Siamese Box Adaptive Network for Visual Tracking](https://mlsanity.com/paper/2003.06761/) (2020)
- [Distractor-aware Siamese Networks for Visual Object Tracking](https://mlsanity.com/paper/1808.06048/) (2018)
- [Siam R-CNN: Visual Tracking by Re-Detection](https://mlsanity.com/paper/1911.12836/) (2019)
- [FCOS: A simple and strong anchor-free object detector](https://mlsanity.com/paper/2006.09214/) (2020)
- [Person Re-identification in the Wild](https://mlsanity.com/paper/1604.02531/) (2016)
- [Deeper and Wider Siamese Networks for Real-Time Visual Tracking](https://mlsanity.com/paper/1901.01660/) (2019)
- [YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video](https://mlsanity.com/paper/1702.00824/) (2017)
- [High-Performance Long-Term Tracking with Meta-Updater](https://mlsanity.com/paper/2004.00305/) (2020)
- [Learning Spatially Regularized Correlation Filters for Visual Tracking](https://mlsanity.com/paper/1608.05571/) (2016)
- [GlobalTrack: A Simple and Strong Baseline for Long-term Tracking](https://mlsanity.com/paper/1912.08531/) (2019)
- [Long-term Tracking in the Wild: A Benchmark](https://mlsanity.com/paper/1803.09502/) (2018)
- [Real-Time MDNet](https://mlsanity.com/paper/1808.08834/) (2018)
- [SOLOv2: Dynamic and Fast Instance Segmentation](https://mlsanity.com/paper/2003.10152/) (2020)

## Built on by (most cited first, 11 of 11)

- [Transforming Model Prediction for Tracking](https://mlsanity.com/paper/2203.11192/) (2022)
- [Survival Prediction Across Diverse Cancer Types Using Neural Networks](https://mlsanity.com/paper/2404.08713/) (2024)
- [Robust Visual Tracking by Segmentation](https://mlsanity.com/paper/2203.11191/) (2022)
- [Task-Agnostic Detector for Insertion-Based Backdoor Attacks](https://mlsanity.com/paper/2403.17155/) (2024)
- [Global Tracking via Ensemble of Local Trackers](https://mlsanity.com/paper/2203.16092/) (2022)
- [Ensemble Methodology:Innovations in Credit Default Prediction Using LightGBM, XGBoost, and LocalEnsemble](https://mlsanity.com/paper/2402.17979/) (2024)
- [NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets](https://mlsanity.com/paper/2211.06663/) (2022)
- [CoCoLoT: Combining Complementary Trackers in Long-Term Visual Tracking](https://mlsanity.com/paper/2205.04261/) (2022)
- [Optimizing Contrail Detection: A Deep Learning Approach with EfficientNet-b4 Encoding](https://mlsanity.com/paper/2404.14441/) (2024)
- [STEP: Simultaneous Tracking and Estimation of Pose for Animals and Humans](https://mlsanity.com/paper/2503.13344/) (2025)
- [Spatio-Temporal Bi-directional Cross-frame Memory for Distractor Filtering Point Cloud Single Object Tracking](https://mlsanity.com/paper/2403.15831/) (2024)

## Abstract (arXiv)

A practical long-term tracker typically contains three key properties, i.e. an efficient model design, an effective global re-detection strategy and a robust distractor awareness mechanism. However, most state-of-the-art long-term trackers (e.g., Pseudo and re-detecting based ones) do not take all three key properties into account and therefore may either be time-consuming or drift to distractors. To address the issues, we propose a two-task tracking frame work (named DMTrack), which utilizes two core components (i.e., one-shot detection and re-identification (re-id) association) to achieve distractor-aware fast tracking via Dynamic convolutions (d-convs) and Multiple object tracking (MOT) philosophy. To achieve precise and fast global detection, we construct a lightweight one-shot detector using a novel dynamic convolutions generation method, which provides a unified and more flexible way for fusing target information into the search field. To distinguish the target from distractors, we resort to the philosophy of MOT to reason distractors explicitly by maintaining all potential similarities' tracklets. Benefited from the strength of high recall detection and explicit object association, our tracker achieves state-of-the-art performance on the LaSOT, OxUvA, TLP, VOT2018LT and VOT2019LT benchmarks and runs in real-time (3x faster than comparisons).