mlsanityData to 14 Oct 2026

SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

arXiv 1812.11703 ↗First posted 31 Dec 2018cs.CVcited by 446

Not on the map. Why?

Abstract (arXiv)

Siamese network based trackers formulate tracking as convolutional feature cross-correlation between target template and searching region. However, Siamese trackers still have accuracy gap compared with state-of-the-art algorithms and they cannot take advantage of feature from deep networks, such as ResNet-50 or deeper. In this work we prove the core reason comes from the lack of strict translation invariance. By comprehensive theoretical analysis and experimental validations, we break this restriction through a simple yet effective spatial aware sampling strategy and successfully train a ResNet-driven Siamese tracker with significant performance gain. Moreover, we propose a new model architecture to perform depth-wise and layer-wise aggregations, which not only further improves the accuracy but also reduces the model size. We conduct extensive ablation studies to demonstrate the effectiveness of the proposed tracker, which obtains currently the best results on four large tracking benchmarks, including OTB2015, VOT2018, UAV123, and LaSOT. Our model will be released to facilitate further studies based on this problem.

Key facts. Cited by 446 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 111; 2022: 92; 2023: 76; 2024: 78; 2025: 55; 2026: 34.

446 papers.

Sort:

By area:

  1. 2021Transformer Trackingcited by 412
  2. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 350
  3. 2022Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Frameworkcited by 330
  4. 2022Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detectioncited by 317
  5. 2022MixFormer: End-to-End Tracking with Iterative Mixed Attentioncited by 281
  6. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
  7. 2025InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modelingcited by 211
  8. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  9. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 192
  10. 2023Visual Prompt Multi-Modal Trackingcited by 142
  11. 2022AiATrack: Attention in Attention for Transformer Visual Trackingcited by 137
  12. 2021Learning Target Candidate Association to Keep Track of What Not to Trackcited by 131
38 more
  1. 2021VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flowscited by 129
  2. 2024ODTrack: Online Dense Temporal Token Learning for Visual Trackingcited by 129
  3. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  4. 2021Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmarkcited by 126
  5. 2021SwinTrack: A Simple and Strong Baseline for Transformer Trackingcited by 126
  6. 2022Backbone is All Your Need: A Simplified Architecture for Visual Object Trackingcited by 119
  7. 2022Transforming Model Prediction for Trackingcited by 117
  8. 2024SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memorycited by 94
  9. 2022Towards Grand Unification of Object Trackingcited by 93
  10. 2023Generalized Relation Modeling for Transformer Trackingcited by 93
  11. 2021STMTrack: Template-free Visual Tracking with Space-time Memory Networkscited by 91
  12. 2022Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baselinecited by 91
  13. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  14. 2023Robust Object Modeling for Visual Trackingcited by 80
  15. 2024Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformerscited by 76
  16. 2022Transformer Tracking with Cyclic Shifting Window Attentioncited by 75
  17. 2021HiFT: Hierarchical Feature Transformer for Aerial Trackingcited by 72
  18. 2023HIPTrack: Visual Tracking with Historical Promptscited by 71
  19. 2024Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performancecited by 70
  20. 2022TCTrack: Temporal Contexts for Aerial Trackingcited by 69
  21. 2021Learn to Match: Automatic Matching Network Design for Visual Trackingcited by 67
  22. 2021Box-Aware Feature Enhancement for Single Object Tracking on Point Cloudscited by 66
  23. 2021PTTR: Relational 3D Point Cloud Object Tracking with Transformercited by 65
  24. 2023Single-Model and Any-Modality for Video Object Trackingcited by 65
  25. 2024OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuningcited by 65
  26. 2021SiamMOT: Siamese Multi-Object Trackingcited by 62
  27. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  28. 2022Correlation-Aware Deep Trackingcited by 62
  29. 2023Towards Unified Token Learning for Vision-Language Trackingcited by 62
  30. 2023Joint Visual Grounding and Tracking with Natural Language Specificationcited by 59
  31. 2022Accelerating DETR Convergence via Semantic-Aligned Matchingcited by 58
  32. 2023MixFormerV2: Efficient Fully Transformer Trackingcited by 57
  33. 2022Unsupervised Domain Adaptation for Nighttime Aerial Trackingcited by 56
  34. 2022APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Trackingcited by 56
  35. 2022Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Cloudscited by 55
  36. 20213D Siamese Voxel-to-BEV Tracker for Sparse Point Cloudscited by 54
  37. 2023Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Trackingcited by 53
  38. 2021RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representationcited by 52

50 most cited of 446 All 446 (JSON)