mlsanityData to 7 Oct 2026

TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild

arXiv 1803.10794 ↗First posted 28 Mar 2018cs.CV cs.ROcited by 342

Not on the map. Why?

Abstract (arXiv)

Despite the numerous developments in object tracking, further development of current tracking algorithms is limited by small and mostly saturated datasets. As a matter of fact, data-hungry trackers based on deep-learning currently rely on object detection datasets due to the scarcity of dedicated large-scale tracking datasets. In this work, we present TrackingNet, the first large-scale dataset and benchmark for object tracking in the wild. We provide more than 30K videos with more than 14 million dense bounding box annotations. Our dataset covers a wide selection of object classes in broad and diverse context. By releasing such a large-scale dataset, we expect deep trackers to further improve and generalize. In addition, we introduce a new benchmark composed of 500 novel videos, modeled with a distribution similar to our training dataset. By sequestering the annotation of the test set and providing an online evaluation server, we provide a fair benchmark for future development of object trackers. Deep trackers fine-tuned on a fraction of our dataset improve their performance by up to 1.6% on OTB100 and up to 1.7% on TrackingNet Test. We provide an extensive benchmark on TrackingNet by evaluating more than 20 trackers. Our results suggest that object tracking in the wild is far from being solved.

Key facts. Cited by 342 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 56; 2022: 53; 2023: 56; 2024: 67; 2025: 65; 2026: 45.

342 papers.

Sort:

By area:

  1. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  2. 2021Transformer Trackingcited by 412
  3. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 348
  4. 2022Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Frameworkcited by 328
  5. 2022MixFormer: End-to-End Tracking with Iterative Mixed Attentioncited by 278
  6. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
  7. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  8. 2023Visual Prompt Multi-Modal Trackingcited by 141
  9. 2022AiATrack: Attention in Attention for Transformer Visual Trackingcited by 137
  10. 2023SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenescited by 130
  11. 2024ODTrack: Online Dense Temporal Token Learning for Visual Trackingcited by 129
  12. 2021SwinTrack: A Simple and Strong Baseline for Transformer Trackingcited by 126
38 more
  1. 2021Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmarkcited by 124
  2. 2022Backbone is All Your Need: A Simplified Architecture for Visual Object Trackingcited by 119
  3. 2022Transforming Model Prediction for Trackingcited by 117
  4. 2022Revealing the Dark Secrets of Masked Image Modelingcited by 117
  5. 2025Streaming Video Question-Answering with In-context Video KV-Cache Retrievalcited by 112
  6. 2021LasHeR: A Large-scale High-diversity Benchmark for RGBT Trackingcited by 94
  7. 2022Towards Grand Unification of Object Trackingcited by 93
  8. 2023Generalized Relation Modeling for Transformer Trackingcited by 93
  9. 2021STMTrack: Template-free Visual Tracking with Space-time Memory Networkscited by 91
  10. 2024SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memorycited by 91
  11. 2022Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baselinecited by 90
  12. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  13. 2023Robust Object Modeling for Visual Trackingcited by 80
  14. 2024Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformerscited by 76
  15. 2022Transformer Tracking with Cyclic Shifting Window Attentioncited by 75
  16. 2023HIPTrack: Visual Tracking with Historical Promptscited by 71
  17. 2024Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performancecited by 70
  18. 2021Learn to Match: Automatic Matching Network Design for Visual Trackingcited by 67
  19. 2021DepthTrack : Unveiling the Power of RGBD Trackingcited by 66
  20. 2023Single-Model and Any-Modality for Video Object Trackingcited by 64
  21. 2024OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuningcited by 64
  22. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  23. 2022Correlation-Aware Deep Trackingcited by 62
  24. 2023Joint Visual Grounding and Tracking with Natural Language Specificationcited by 59
  25. 2022Prompting for Multi-Modal Trackingcited by 58
  26. 2023MixFormerV2: Efficient Fully Transformer Trackingcited by 56
  27. 2024Exploiting Multimodal Spatial-temporal Patterns for Video Object Trackingcited by 55
  28. 2023Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Trackingcited by 53
  29. 2022Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metriccited by 51
  30. 2023Compact Transformer Tracker with Correlative Masked Modelingcited by 50
  31. 2024Explicit Visual Prompts for Visual Object Trackingcited by 50
  32. 2021Efficient Visual Tracking with Exemplar Transformerscited by 48
  33. 2024Elysium: Exploring Object-level Perception in Videos via MLLMcited by 48
  34. 2021Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlookcited by 45
  35. 2022RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Trackingcited by 42
  36. 2021FEAR: Fast, Efficient, Accurate and Robust Visual Trackercited by 38
  37. 2022Robust Visual Tracking by Segmentationcited by 38
  38. 2022SparseTT: Visual Tracking with Sparse Transformerscited by 36

50 most cited of 342 All 342 (JSON)