mlsanityData to 14 Oct 2026

Efficient Visual Tracking via Hierarchical Cross-Attention Transformer

arXiv 2203.13537 ↗First posted 25 Mar 2022cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

In recent years, target tracking has made great progress in accuracy. This development is mainly attributed to powerful networks (such as transformers) and additional modules (such as online update and refinement modules). However, less attention has been paid to tracking speed. Most state-of-the-art trackers are satisfied with the real-time speed on powerful GPUs. However, practical applications necessitate higher requirements for tracking speed, especially when edge platforms with limited resources are used. In this work, we present an efficient tracking method via a hierarchical cross-attention transformer named HCAT. Our model runs about 195 fps on GPU, 45 fps on CPU, and 55 fps on the edge AI platform of NVidia Jetson AGX Xavier. Experiments show that our HCAT achieves promising results on LaSOT, GOT-10k, TrackingNet, NFS, OTB100, UAV123, and VOT2020. Code and models are available at https://github.com/chenxin-dlut/HCAT.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 38 of its 47 references that are in the map. First posted on arXiv 25 Mar 2022.

Builds on

38 of 47 references.

References · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  8. 2020End-to-End Object Detection with Transformerscited by 7,414
  9. 2014Going Deeper with Convolutionscited by 4,241
  10. 2022A ConvNet for the 2020scited by 3,579
  11. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  12. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 568
26 more
  1. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 475
  2. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 446
  3. 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 429
  4. 2021Transformer Trackingcited by 412
  5. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 350
  6. 2019Learning Discriminative Model Prediction for Trackingcited by 344
  7. 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 343
  8. 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
  9. 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
  10. 2016ECO: Efficient Convolution Operators for Trackingcited by 239
  11. 2020Probabilistic Regression for Visual Trackingcited by 231
  12. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
  13. 2020Ocean: Object-aware Anchor-free Trackingcited by 212
  14. 2015Learning Multi-Domain Convolutional Neural Networks for Visual Trackingcited by 209
  15. 2020Siamese Box Adaptive Network for Visual Trackingcited by 189
  16. 2019SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelinescited by 177
  17. 2019Siam R-CNN: Visual Tracking by Re-Detectioncited by 174
  18. 2019Deeper and Wider Siamese Networks for Real-Time Visual Trackingcited by 156
  19. 2019SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Trackingcited by 148
  20. 2017Need for Speed: A Benchmark for Higher Frame Rate Object Trackingcited by 137
  21. 2020Deformable Siamese Attention Networks for Visual Object Trackingcited by 97
  22. 2021STMTrack: Template-free Visual Tracking with Space-time Memory Networkscited by 91
  23. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  24. 2020Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimationcited by 81
  25. 2021Efficient Visual Tracking with Exemplar Transformerscited by 48
  26. 2021Learning Tracking Representations via Dual-Branch Fully Transformer Networkscited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 8; 2025: 6; 2026: 5.

24 papers.

Sort:

By area:

  1. 2023MixFormerV2: Efficient Fully Transformer Trackingcited by 57
  2. 2023Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Trackingcited by 53
  3. 2023Separable Self and Mixed Attention Transformers for Efficient Object Trackingcited by 31
  4. 2025Similarity-Guided Layer-Adaptive Vision Transformer for UAV Trackingcited by 23
  5. 2023LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Trackingcited by 16
  6. 2024General Compression Framework for Efficient Transformer Object Trackingcited by 10
  7. 2024Improving Visual Object Tracking through Visual Promptingcited by 9
  8. 2024Exploring Dynamic Transformer for Efficient Object Trackingcited by 7
  9. 2024An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Trainingcited by 4
  10. 2024LoReTrack: Efficient and Accurate Low-Resolution Transformer Trackingcited by 3
  11. 2024Improving Accuracy and Generalization for Efficient Visual Trackingcited by 3
  12. 2025Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Trackingcited by 3
12 more
  1. 2024TReX- Reusing Vision Transformer's Attention for Efficient Xbar-based Computingcited by 2
  2. 2026FARTrack: Fast Autoregressive Visual Tracking with High Performancecited by 2
  3. 2026UETrack: A Unified and Efficient Framework for Single Object Trackingcited by 2
  4. 2024Labeling Comic Mischief Content in Online Videos with a Multimodal Hierarchical-Cross-Attention Modelcited by 1
  5. 2025TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Trackingcited by 1
  6. 2025SUIT: Spatial-Spectral Union-Intersection Interaction Network for Hyperspectral Object Trackingcited by 1
  7. 2023Unsupervised Green Object Tracker (GOT) without Offline Pre-trainingcited by 0
  8. 2025Lightweight RGB-T Tracking with Mobile Vision Transformerscited by 0
  9. 2025Infrared UAV Target Tracking with Dynamic Feature Refinement and Global Contextual Attention Knowledge Distillationcited by 0
  10. 2026Exploring Reliable Spatiotemporal Dependencies for Efficient Visual Trackingcited by 0
  11. 2026MaST: Motion-aware Sparse Pipeline for Lightweight Object Trackingcited by 0
  12. 2026LoopTrack: A Simple Baseline for Parameter-Efficient Transformer Trackingcited by 0