mlsanityData to 7 Oct 2026

Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework

arXiv 2203.11991 ↗First posted 22 Mar 2022cs.CVcited by 328

Not on the map. Why?

Abstract (arXiv)

The current popular two-stream, two-stage tracking framework extracts the template and the search region features separately and then performs relation modeling, thus the extracted features lack the awareness of the target and have limited target-background discriminability. To tackle the above issue, we propose a novel one-stream tracking (OSTrack) framework that unifies feature learning and relation modeling by bridging the template-search image pairs with bidirectional information flows. In this way, discriminative target-oriented features can be dynamically extracted by mutual guidance. Since no extra heavy relation modeling module is needed and the implementation is highly parallelized, the proposed tracker runs at a fast speed. To further improve the inference efficiency, an in-network candidate early elimination module is proposed based on the strong similarity prior calculated in the one-stream framework. As a unified framework, OSTrack achieves state-of-the-art performance on multiple benchmarks, in particular, it shows impressive results on the one-shot tracking benchmark GOT-10k, i.e., achieving 73.7% AO, improving the existing best result (SwinTrack) by 4.3%. Besides, our method maintains a good performance-speed trade-off and shows faster convergence. The code and models are available at https://github.com/botaoye/OSTrack.

Key facts. Cited by 328 papers in the map (data through 7 Oct 2026). Builds on 47 of its 57 references that are in the map. First posted on arXiv 22 Mar 2022.

Builds on

47 of 57 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  9. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  10. 2019Objects as Pointscited by 1,172
  11. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  12. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 849
35 more
  1. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  2. 2021ImageNet-21K Pretraining for the Massescited by 607
  3. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  4. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 562
  5. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 471
  6. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
  7. 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 424
  8. 2021Transformer Trackingcited by 412
  9. 2021AdaViT: Adaptive Tokens for Efficient Vision Transformercited by 360
  10. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 348
  11. 2019Learning Discriminative Model Prediction for Trackingcited by 344
  12. 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 342
  13. 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
  14. 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
  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. 2019Siam R-CNN: Visual Tracking by Re-Detectioncited by 174
  21. 2017Need for Speed: A Benchmark for Higher Frame Rate Object Trackingcited by 137
  22. 2021Learning Target Candidate Association to Keep Track of What Not to Trackcited by 131
  23. 2020LaSOT: A High-quality Large-scale Single Object Tracking Benchmarkcited by 130
  24. 2021SwinTrack: A Simple and Strong Baseline for Transformer Trackingcited by 126
  25. 2021Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmarkcited by 124
  26. 2020Know Your Surroundings: Exploiting Scene Information for Object Trackingcited by 119
  27. 2021STMTrack: Template-free Visual Tracking with Space-time Memory Networkscited by 91
  28. 2020Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimationcited by 81
  29. 2020High-Performance Long-Term Tracking with Meta-Updatercited by 79
  30. 2020Graph Attention Trackingcited by 70
  31. 2019D3S -- A Discriminative Single Shot Segmentation Trackercited by 69
  32. 2021Learn to Match: Automatic Matching Network Design for Visual Trackingcited by 67
  33. 2020Tracking by Instance Detection: A Meta-Learning Approachcited by 61
  34. 2018Real-Time MDNetcited by 39
  35. 2021An Informative Tracking Benchmarkcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 59; 2024: 91; 2025: 89; 2026: 79.

328 papers.

Sort:

By area:

  1. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  2. 2023Visual Prompt Multi-Modal Trackingcited by 141
  3. 2024ODTrack: Online Dense Temporal Token Learning for Visual Trackingcited by 129
  4. 2024Large Multimodal Agents: A Surveycited by 99
  5. 2023Generalized Relation Modeling for Transformer Trackingcited by 93
  6. 2024SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memorycited by 91
  7. 2023Robust Object Modeling for Visual Trackingcited by 80
  8. 2024SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Treecited by 77
  9. 2024Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformerscited by 76
  10. 2023Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baselinecited by 73
  11. 2023HIPTrack: Visual Tracking with Historical Promptscited by 71
  12. 2024Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performancecited by 70
38 more
  1. 2023Single-Model and Any-Modality for Video Object Trackingcited by 64
  2. 2024OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuningcited by 64
  3. 2024A Distractor-Aware Memory for Visual Object Tracking with SAM2cited by 63
  4. 2023Towards Unified Token Learning for Vision-Language Trackingcited by 62
  5. 2023Joint Visual Grounding and Tracking with Natural Language Specificationcited by 59
  6. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  7. 2023MixFormerV2: Efficient Fully Transformer Trackingcited by 56
  8. 2024Exploiting Multimodal Spatial-temporal Patterns for Video Object Trackingcited by 55
  9. 2023Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Trackingcited by 53
  10. 2022Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metriccited by 51
  11. 2023Revisiting Token Pruning for Object Detection and Instance Segmentationcited by 50
  12. 2024Explicit Visual Prompts for Visual Object Trackingcited by 50
  13. 2023Bi-directional Adapter for Multi-modal Trackingcited by 46
  14. 2023Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackerscited by 43
  15. 2024SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Trackingcited by 43
  16. 2023CiteTracker: Correlating Image and Text for Visual Trackingcited by 36
  17. 2024Exploring Enhanced Contextual Information for Video-Level Object Trackingcited by 36
  18. 2024Towards Language-Driven Video Inpainting via Multimodal Large Language Modelscited by 33
  19. 2023Tracking with Human-Intent Reasoningcited by 32
  20. 2023Separable Self and Mixed Attention Transformers for Efficient Object Trackingcited by 31
  21. 2024Temporal Adaptive RGBT Tracking with Modality Promptcited by 30
  22. 2025Towards Universal Modal Tracking with Online Dense Temporal Token Learningcited by 30
  23. 2023Scalable Video Object Segmentation with Simplified Frameworkcited by 29
  24. 2022CXTrack: Improving 3D Point Cloud Tracking with Contextual Informationcited by 28
  25. 2023All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignmentcited by 27
  26. 2024Unifying Visual and Vision-Language Tracking via Contrastive Learningcited by 27
  27. 2023ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Trackingcited by 25
  28. 2024VastTrack: Vast Category Visual Object Trackingcited by 25
  29. 2024Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackerscited by 24
  30. 2025SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Trackingcited by 23
  31. 2025Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Trackingcited by 23
  32. 2023DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Taskscited by 22
  33. 2024OmniVid: A Generative Framework for Universal Video Understandingcited by 22
  34. 2025Similarity-Guided Layer-Adaptive Vision Transformer for UAV Trackingcited by 22
  35. 2025Learning Occlusion-Robust Vision Transformers for Real-Time UAV Trackingcited by 22
  36. 2024Mamba-FETrack: Frame-Event Tracking via State Space Modelcited by 21
  37. 2023Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Trackingcited by 20
  38. 2024XTrack: Multimodal Training Boosts RGB-X Video Object Trackerscited by 20

50 most cited of 328 All 328 (JSON)