mlsanityData to 14 Oct 2026

SparseTT: Visual Tracking with Sparse Transformers

arXiv 2205.03776 ↗First posted 8 May 2022cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers. However, self-attention lacks focusing on the most relevant information in the search regions, making it easy to be distracted by background. In this paper, we relieve this issue with a sparse attention mechanism by focusing the most relevant information in the search regions, which enables a much accurate tracking. Furthermore, we introduce a double-head predictor to boost the accuracy of foreground-background classification and regression of target bounding boxes, which further improve the tracking performance. Extensive experiments show that, without bells and whistles, our method significantly outperforms the state-of-the-art approaches on LaSOT, GOT-10k, TrackingNet, and UAV123, while running at 40 FPS. Notably, the training time of our method is reduced by 75% compared to that of TransT. The source code and models are available at https://github.com/fzh0917/SparseTT.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 29 of its 35 references that are in the map. First posted on arXiv 8 May 2022.

Builds on

29 of 35 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 568
  8. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 475
  9. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 446
  10. 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 429
  11. 2021Transformer Trackingcited by 412
  12. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 350
17 more
  1. 2019Learning Discriminative Model Prediction for Trackingcited by 344
  2. 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 343
  3. 2020Probabilistic Regression for Visual Trackingcited by 231
  4. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
  5. 2020Ocean: Object-aware Anchor-free Trackingcited by 212
  6. 2016UnitBox: An Advanced Object Detection Networkcited by 205
  7. 2019SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelinescited by 177
  8. 2020Know Your Surroundings: Exploiting Scene Information for Object Trackingcited by 119
  9. 2019Rethinking Classification and Localization for Object Detectioncited by 98
  10. 2021STMTrack: Template-free Visual Tracking with Space-time Memory Networkscited by 91
  11. 2020Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimationcited by 81
  12. 2020High-Performance Long-Term Tracking with Meta-Updatercited by 80
  13. 2020Graph Attention Trackingcited by 70
  14. 2021Learn to Match: Automatic Matching Network Design for Visual Trackingcited by 67
  15. 2019Explicit Sparse Transformer: Concentrated Attention Through Explicit Selectioncited by 62
  16. 2021Saliency-Associated Object Trackingcited by 30
  17. 2021SiamRCR: Reciprocal Classification and Regression for Visual Object Trackingcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 8; 2024: 12; 2025: 7; 2026: 7.

36 papers.

Sort:

By area:

  1. 2023Learning A Sparse Transformer Network for Effective Image Derainingcited by 205
  2. 2023Generalized Relation Modeling for Transformer Trackingcited by 93
  3. 2024Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformerscited by 76
  4. 2023HIPTrack: Visual Tracking with Historical Promptscited by 71
  5. 2024Scene Adaptive Sparse Transformer for Event-based Object Detectioncited by 39
  6. 2025SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Trackingcited by 24
  7. 2025Learning Occlusion-Robust Vision Transformers for Real-Time UAV Trackingcited by 22
  8. 2024XTrack: Multimodal Training Boosts RGB-X Video Object Trackerscited by 21
  9. 2026Does Your Reasoning Model Implicitly Know When to Stop Thinking?cited by 19
  10. 2025Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimizationcited by 17
  11. 2024Robust Tracking via Mamba-based Context-aware Token Learningcited by 15
  12. 2025What You Have is What You Track: Adaptive and Robust Multimodal Trackingcited by 15
24 more
  1. 2026Heterogeneous Agent Collaborative Reinforcement Learningcited by 15
  2. 2024Cross-modulated Attention Transformer for RGBT Trackingcited by 14
  3. 2026Real-Time Aligned Reward Model beyond Semanticscited by 13
  4. 2023Improving Underwater Visual Tracking With a Large Scale Dataset and Image Enhancementcited by 11
  5. 2023Transformers in Single Object Tracking: An Experimental Surveycited by 10
  6. 2023Towards Discriminative Representations with Contrastive Instances for Real-Time UAV Trackingcited by 9
  7. 2023Learning Disentangled Representation with Mutual Information Maximization for Real-Time UAV Trackingcited by 5
  8. 2026Video Understanding: From Geometry and Semantics to Unified Modelscited by 5
  9. 2025Large Language models for Time Series Analysis: Techniques, Applications, and Challengescited by 3
  10. 2022SRRT: Exploring Search Region Regulation for Visual Object Trackingcited by 2
  11. 2022Rethinking Batch Sample Relationships for Data Representation: A Batch-Graph Transformer based Approachcited by 2
  12. 2024Camouflaged Object Tracking: A Benchmarkcited by 2
  13. 2024Visual Object Tracking across Diverse Data Modalities: A Reviewcited by 2
  14. 2024Multi-attention Associate Prediction Network for Visual Trackingcited by 1
  15. 2024Tracking Reflected Objects: A Benchmarkcited by 1
  16. 2024Learning Motion Blur Robust Vision Transformers for Real-Time UAV Trackingcited by 1
  17. 2024Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Trackingcited by 1
  18. 2026Uni-MDTrack: Learning Decoupled Memory and Dynamic States for Parameter-Efficient Visual Tracking in All Modalitycited by 1
  19. 2023RTrack: Accelerating Convergence for Visual Object Tracking via Pseudo-Boxes Explorationcited by 0
  20. 2024Optimized Information Flow for Transformer Trackingcited by 0
  21. 2025Context-Aware Token Pruning and Discriminative Selective Attention for Transformer Trackingcited by 0
  22. 2025Infrared UAV Target Tracking with Dynamic Feature Refinement and Global Contextual Attention Knowledge Distillationcited by 0
  23. 2026GOT-JEPA: Generic Object Tracking with Model Adaptation and Occlusion Handling using Joint-Embedding Predictive Architecturecited by 0
  24. 2026STATrack: A Target-Aware Fully Spiking Neural Network for Efficient UAV Trackingcited by 0