mlsanityData to 7 Oct 2026

Efficient Visual Tracking with Exemplar Transformers

arXiv 2112.09686 ↗First posted 17 Dec 2021cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

The design of more complex and powerful neural network models has significantly advanced the state-of-the-art in visual object tracking. These advances can be attributed to deeper networks, or the introduction of new building blocks, such as transformers. However, in the pursuit of increased tracking performance, runtime is often hindered. Furthermore, efficient tracking architectures have received surprisingly little attention. In this paper, we introduce the Exemplar Transformer, a transformer module utilizing a single instance level attention layer for realtime visual object tracking. E.T.Track, our visual tracker that incorporates Exemplar Transformer modules, runs at 47 FPS on a CPU. This is up to 8x faster than other transformer-based models. When compared to lightweight trackers that can operate in realtime on standard CPUs, E.T.Track consistently outperforms all other methods on the LaSOT, OTB-100, NFS, TrackingNet, and VOT-ST2020 datasets. Code and models are available at https://github.com/pblatter/ettrack.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 52 of its 65 references that are in the map. First posted on arXiv 17 Dec 2021.

Builds on

52 of 65 references.

References · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  8. 2016Layer Normalizationcited by 5,579
  9. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  10. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  11. 2020Longformer: The Long-Document Transformercited by 3,362
  12. 2017Non-local Neural Networkscited by 2,290
38 more
  1. 2019Searching for MobileNetV3cited by 1,984
  2. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  3. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  4. 2020Reformer: The Efficient Transformercited by 1,658
  5. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  6. 2016An overview of gradient descent optimization algorithmscited by 1,021
  7. 2020Efficient Transformers: A Surveycited by 784
  8. 2018Image Transformercited by 770
  9. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  10. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  11. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 471
  12. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
  13. 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 424
  14. 2021Transformer Trackingcited by 412
  15. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  16. 2019Attention Augmented Convolutional Networkscited by 363
  17. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 348
  18. 2019Learning Discriminative Model Prediction for Trackingcited by 344
  19. 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 342
  20. 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
  21. 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
  22. 2016ECO: Efficient Convolution Operators for Trackingcited by 239
  23. 2020Probabilistic Regression for Visual Trackingcited by 231
  24. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
  25. 2020Ocean: Object-aware Anchor-free Trackingcited by 212
  26. 2016UnitBox: An Advanced Object Detection Networkcited by 205
  27. 2019Siam R-CNN: Visual Tracking by Re-Detectioncited by 174
  28. 2019Blockwise Self-Attention for Long Document Understandingcited by 158
  29. 2017Need for Speed: A Benchmark for Higher Frame Rate Object Trackingcited by 137
  30. 2021Patch Slimming for Efficient Vision Transformerscited by 131
  31. 2021TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?cited by 127
  32. 2020Fast Transformers with Clustered Attentioncited by 123
  33. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  34. 2020Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimationcited by 81
  35. 2021ResT: An Efficient Transformer for Visual Recognitioncited by 79
  36. 2019Learning the Model Update for Siamese Trackerscited by 75
  37. 2021Exploring Relational Context for Multi-Task Dense Predictioncited by 71
  38. 2018Learning Dynamic Memory Networks for Object Trackingcited by 58

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 11; 2024: 17; 2025: 11; 2026: 6.

48 papers.

Sort:

By area:

  1. 2023MixFormerV2: Efficient Fully Transformer Trackingcited by 56
  2. 2023Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Trackingcited by 53
  3. 2022Exemplar Guided Deep Neural Network for Spatial Transcriptomics Analysis of Gene Expression Predictioncited by 39
  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. 2022Efficient Visual Tracking via Hierarchical Cross-Attention Transformercited by 24
  7. 2024EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Drivingcited by 18
  8. 2023LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Trackingcited by 16
  9. 2025Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Trackingcited by 15
  10. 2024RTracker: Recoverable Tracking via PN Tree Structured Memorycited by 12
  11. 2022ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretizationcited by 10
  12. 2024General Compression Framework for Efficient Transformer Object Trackingcited by 10
36 more
  1. 2024Correlation-Embedded Transformer Tracking: A Single-Branch Frameworkcited by 9
  2. 2023Lightweight Full-Convolutional Siamese Trackercited by 8
  3. 2024Exploring Dynamic Transformer for Efficient Object Trackingcited by 7
  4. 2024RGB-Sonar Tracking Benchmark and Spatial Cross-Attention Transformer Trackercited by 6
  5. 2023Adaptive Siamese Tracking with a Compact Latent Networkcited by 5
  6. 2025FocusTrack: A Self-Adaptive Local Sampling Algorithm for Efficient Anti-UAV Trackingcited by 5
  7. 2024An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Trainingcited by 4
  8. 2024BihoT: A Large-Scale Dataset and Benchmark for Hyperspectral Camouflaged Object Trackingcited by 4
  9. 2024Multi-step Temporal Modeling for UAV Trackingcited by 3
  10. 2024SSF-Net: Spatial-Spectral Fusion Network with Spectral Angle Awareness for Hyperspectral Object Trackingcited by 3
  11. 2024LoReTrack: Efficient and Accurate Low-Resolution Transformer Trackingcited by 3
  12. 2024NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Trackingcited by 3
  13. 2024Improving Accuracy and Generalization for Efficient Visual Trackingcited by 3
  14. 2025Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approachcited by 3
  15. 2025Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Trackingcited by 3
  16. 2025Track-On2: Enhancing Online Point Tracking with Memorycited by 3
  17. 2023Mobile Vision Transformer-based Visual Object Trackingcited by 2
  18. 2023AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Trackingcited by 2
  19. 2024Low-Light Object Tracking: A Benchmarkcited by 2
  20. 2024Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operationscited by 2
  21. 2026FARTrack: Fast Autoregressive Visual Tracking with High Performancecited by 2
  22. 2026UETrack: A Unified and Efficient Framework for Single Object Trackingcited by 2
  23. 2026RELO: Reinforcement Learning to Localize for Visual Object Trackingcited by 2
  24. 2024Adaptively Bypassing Vision Transformer Blocks for Efficient Visual Trackingcited by 1
  25. 2025LightFC-X: Lightweight Convolutional Tracker for RGB-X Trackingcited by 1
  26. 2025CFTrack: Enhancing Lightweight Visual Tracking through Contrastive Learning and Feature Matchingcited by 1
  27. 2025MVTD: A Benchmark Dataset for Maritime Visual Object Trackingcited by 1
  28. 2025Learning Frequency and Memory-Aware Prompts for Multi-Modal Object Trackingcited by 1
  29. 2025Multi-State Tracker: Enhancing Efficient Object Tracking via Multi-State Specialization and Interactioncited by 1
  30. 2023Robust Visual Tracking by Motion Analyzingcited by 0
  31. 2023Unsupervised Green Object Tracker (GOT) without Offline Pre-trainingcited by 0
  32. 2024Interpretable Dynamic Graph Neural Networks for Small Occluded Object Detection and Trackingcited by 0
  33. 2025Target-aware Bidirectional Fusion Transformer for Aerial Object Trackingcited by 0
  34. 2026Exploring Reliable Spatiotemporal Dependencies for Efficient Visual Trackingcited by 0
  35. 2026Search Multilayer Perceptron-Based Fusion for Efficient and Accurate Siamese Trackingcited by 0
  36. 2026MaST: Motion-aware Sparse Pipeline for Lightweight Object Trackingcited by 0