# Real-Time MDNet

arXiv: https://arxiv.org/abs/1808.08834 · HTML: https://mlsanity.com/paper/1808.08834/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2018.

## Built on by (most cited first, 30 of 39)

- [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)
- [VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows](https://mlsanity.com/paper/2108.05015/) (2021)
- [Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark](https://mlsanity.com/paper/2103.16746/) (2021)
- [Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline](https://mlsanity.com/paper/2204.04120/) (2022)
- [LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search](https://mlsanity.com/paper/2104.14545/) (2021)
- [Transformer Tracking with Cyclic Shifting Window Attention](https://mlsanity.com/paper/2205.03806/) (2022)
- [Elysium: Exploring Object-level Perception in Videos via MLLM](https://mlsanity.com/paper/2403.16558/) (2024)
- [Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers](https://mlsanity.com/paper/2307.04129/) (2023)
- [MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking](https://mlsanity.com/paper/2107.10433/) (2021)
- [Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking](https://mlsanity.com/paper/2101.08466/) (2021)
- [IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking](https://mlsanity.com/paper/2103.14938/) (2021)
- [Mamba-FETrack: Frame-Event Tracking via State Space Model](https://mlsanity.com/paper/2404.18174/) (2024)
- [Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking](https://mlsanity.com/paper/2304.14394/) (2023)
- [Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking](https://mlsanity.com/paper/2103.16086/) (2021)
- [Towards Sequence-Level Training for Visual Tracking](https://mlsanity.com/paper/2208.05810/) (2022)
- [Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy](https://mlsanity.com/paper/2104.12041/) (2021)
- [Tiny Object Tracking: A Large-scale Dataset and A Baseline](https://mlsanity.com/paper/2202.05659/) (2022)
- [Dynamic Fusion Network for RGBT Tracking](https://mlsanity.com/paper/2109.07662/) (2021)
- [Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset](https://mlsanity.com/paper/2312.14446/) (2023)
- [Tracking by Joint Local and Global Search: A Target-aware Attention based Approach](https://mlsanity.com/paper/2106.04840/) (2021)
- [Cross-Modal Object Tracking: Modality-Aware Representations and A Unified Benchmark](https://mlsanity.com/paper/2111.04264/) (2021)
- [RGB-T Tracking Based on Mixed Attention](https://mlsanity.com/paper/2304.04264/) (2023)
- [Prototype-based Cross-Modal Object Tracking](https://mlsanity.com/paper/2312.14471/) (2023)
- [SiamCorners: Siamese Corner Networks for Visual Tracking](https://mlsanity.com/paper/2104.07303/) (2021)
- [Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking](https://mlsanity.com/paper/2108.04521/) (2021)
- [Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search](https://mlsanity.com/paper/2205.09676/) (2022)
- [Unified Single-Stage Transformer Network for Efficient RGB-T Tracking](https://mlsanity.com/paper/2308.13764/) (2023)
- [Single Object Tracking: A Survey of Methods, Datasets, and Evaluation Metrics](https://mlsanity.com/paper/2201.13066/) (2022)
- [A comprehensive survey on recent deep learning-based methods applied to surgical data](https://mlsanity.com/paper/2209.01435/) (2022)

## Abstract (arXiv)

We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet). The proposed approach accelerates feature extraction procedure and learns more discriminative models for instance classification; it enhances representation quality of target and background by maintaining a high resolution feature map with a large receptive field per activation. We also introduce a novel loss term to differentiate foreground instances across multiple domains and learn a more discriminative embedding of target objects with similar semantics. The proposed techniques are integrated into the pipeline of a well known CNN-based visual tracking algorithm, MDNet. We accomplish approximately 25 times speed-up with almost identical accuracy compared to MDNet. Our algorithm is evaluated in multiple popular tracking benchmark datasets including OTB2015, UAV123, and TempleColor, and outperforms the state-of-the-art real-time tracking methods consistently even without dataset-specific parameter tuning.