mlsanityData to 14 Oct 2026

FEAR: Fast, Efficient, Accurate and Robust Visual Tracker

arXiv 2112.07957 ↗First posted 15 Dec 2021cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

We present FEAR, a family of fast, efficient, accurate, and robust Siamese visual trackers. We present a novel and efficient way to benefit from dual-template representation for object model adaption, which incorporates temporal information with only a single learnable parameter. We further improve the tracker architecture with a pixel-wise fusion block. By plugging-in sophisticated backbones with the abovementioned modules, FEAR-M and FEAR-L trackers surpass most Siamese trackers on several academic benchmarks in both accuracy and efficiency. Employed with the lightweight backbone, the optimized version FEAR-XS offers more than 10 times faster tracking than current Siamese trackers while maintaining near state-of-the-art results. FEAR-XS tracker is 2.4x smaller and 4.3x faster than LightTrack with superior accuracy. In addition, we expand the definition of the model efficiency by introducing FEAR benchmark that assesses energy consumption and execution speed. We show that energy consumption is a limiting factor for trackers on mobile devices. Source code, pretrained models, and evaluation protocol are available at https://github.com/PinataFarms/FEARTracker.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 53 of its 75 references that are in the map. First posted on arXiv 15 Dec 2021.

Builds on

53 of 75 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  7. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  9. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  10. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  11. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  12. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
38 more
  1. 2017Focal Loss for Dense Object Detectioncited by 752
  2. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 664
  3. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 568
  4. 2018Albumentations: fast and flexible image augmentationscited by 560
  5. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
  6. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 475
  7. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 446
  8. 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 429
  9. 2014Deep metric learning using Triplet networkcited by 422
  10. 2021Transformer Trackingcited by 412
  11. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 350
  12. 2019Learning Discriminative Model Prediction for Trackingcited by 344
  13. 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 343
  14. 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
  15. 2016ECO: Efficient Convolution Operators for Trackingcited by 239
  16. 2020Probabilistic Regression for Visual Trackingcited by 231
  17. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
  18. 2020Ocean: Object-aware Anchor-free Trackingcited by 212
  19. 2015Learning Multi-Domain Convolutional Neural Networks for Visual Trackingcited by 209
  20. 2018Distractor-aware Siamese Networks for Visual Object Trackingcited by 187
  21. 2019SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelinescited by 177
  22. 2019Deeper and Wider Siamese Networks for Real-Time Visual Trackingcited by 156
  23. 2017Need for Speed: A Benchmark for Higher Frame Rate Object Trackingcited by 137
  24. 2020LaSOT: A High-quality Large-scale Single Object Tracking Benchmarkcited by 132
  25. 2020Know Your Surroundings: Exploiting Scene Information for Object Trackingcited by 119
  26. 2015A Novel Performance Evaluation Methodology for Single-Target Trackerscited by 113
  27. 2017YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Videocited by 109
  28. 2017Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutionscited by 93
  29. 2016Learning to Track at 100 FPS with Deep Regression Networkscited by 89
  30. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  31. 2019DetNAS: Backbone Search for Object Detectioncited by 81
  32. 2020Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimationcited by 81
  33. 2018SqueezeNext: Hardware-Aware Neural Network Designcited by 61
  34. 2019Deep Learning for Visual Tracking: A Comprehensive Surveycited by 61
  35. 2015Staple: Complementary Learners for Real-Time Trackingcited by 60
  36. 2016Siamese Instance Search for Trackingcited by 60
  37. 2021RegNet: Self-Regulated Network for Image Classificationcited by 44
  38. 2015Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Treecited by 36

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 12; 2024: 10; 2025: 9; 2026: 5.

38 papers.

Sort:

By area:

  1. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 276
  2. 2023MixFormerV2: Efficient Fully Transformer Trackingcited by 57
  3. 2023Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Trackingcited by 53
  4. 2023Separable Self and Mixed Attention Transformers for Efficient Object Trackingcited by 31
  5. 2023ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Trackingcited by 25
  6. 2023LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Trackingcited by 16
  7. 2025Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Trackingcited by 15
  8. 2024Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokenscited by 11
  9. 2024General Compression Framework for Efficient Transformer Object Trackingcited by 10
  10. 2024Correlation-Embedded Transformer Tracking: A Single-Branch Frameworkcited by 9
  11. 2025CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Trackingcited by 9
  12. 2023Lightweight Full-Convolutional Siamese Trackercited by 8
26 more
  1. 2024Exploring Dynamic Transformer for Efficient Object Trackingcited by 7
  2. 2023Tracking Skiers from the Top to the Bottomcited by 6
  3. 2024RGB-Sonar Tracking Benchmark and Spatial Cross-Attention Transformer Trackercited by 6
  4. 2023Adaptive Siamese Tracking with a Compact Latent Networkcited by 5
  5. 2024An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Trainingcited by 4
  6. 2024SSF-Net: Spatial-Spectral Fusion Network with Spectral Angle Awareness for Hyperspectral Object Trackingcited by 3
  7. 2024LoReTrack: Efficient and Accurate Low-Resolution Transformer Trackingcited by 3
  8. 2024Improving Accuracy and Generalization for Efficient Visual Trackingcited by 3
  9. 2025Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approachcited by 3
  10. 2025Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Trackingcited by 3
  11. 2025Track-On2: Enhancing Online Point Tracking with Memorycited by 3
  12. 2026RELO: Reinforcement Learning to Localize for Visual Object Trackingcited by 3
  13. 2022SRRT: Exploring Search Region Regulation for Visual Object Trackingcited by 2
  14. 2023Mobile Vision Transformer-based Visual Object Trackingcited by 2
  15. 2023AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Trackingcited by 2
  16. 2026FARTrack: Fast Autoregressive Visual Tracking with High Performancecited by 2
  17. 2026UETrack: A Unified and Efficient Framework for Single Object Trackingcited by 2
  18. 2022On Designing Light-Weight Object Trackers through Network Pruning: Use CNNs or Transformers?cited by 1
  19. 2024Adaptively Bypassing Vision Transformer Blocks for Efficient Visual Trackingcited by 1
  20. 2025LightFC-X: Lightweight Convolutional Tracker for RGB-X Trackingcited by 1
  21. 2025CFTrack: Enhancing Lightweight Visual Tracking through Contrastive Learning and Feature Matchingcited by 1
  22. 2025Learning Frequency and Memory-Aware Prompts for Multi-Modal Object Trackingcited by 1
  23. 2025Multi-State Tracker: Enhancing Efficient Object Tracking via Multi-State Specialization and Interactioncited by 1
  24. 2023Unsupervised Green Object Tracker (GOT) without Offline Pre-trainingcited by 0
  25. 2026Search Multilayer Perceptron-Based Fusion for Efficient and Accurate Siamese Trackingcited by 0
  26. 2026MaST: Motion-aware Sparse Pipeline for Lightweight Object Trackingcited by 0