mlsanityData to 14 Oct 2026

GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild

arXiv 1810.11981 ↗First posted 29 Oct 2018cs.CVcited by 475

Not on the map. Why?

Abstract (arXiv)

We introduce here a large tracking database that offers an unprecedentedly wide coverage of common moving objects in the wild, called GOT-10k. Specifically, GOT-10k is built upon the backbone of WordNet structure and it populates the majority of over 560 classes of moving objects and 87 motion patterns, magnitudes wider than the most recent similar-scale counterparts. The contributions of this paper are summarized in the following: (1) GOT-10k offers over 10,000 video segments with more than 1.5 million manually labeled bounding boxes, enabling unified training and stable evaluation of deep trackers. (2) GOT-10k is by far the first video trajectory dataset that uses the semantic hierarchy of WordNet to guide class population. (3) For the first time, GOT-10k introduces the one-shot protocol for tracker evaluation, where the training and test classes are zero-overlapped. The protocol avoids biased evaluation results towards familiar objects and it promotes generalization in tracker development. (4) We conduct extensive tracking experiments with 39 typical tracking algorithms on GOT-10k and analyze their results in this paper. (5) Finally, we develop a comprehensive platform for the tracking community that offers full-featured evaluation toolkits, an online evaluation server, and a responsive leaderboard. The annotations of GOT-10k's test data are kept private to avoid tuning parameters on it. The database, toolkits, evaluation server and baseline results are available at http://got-10k.aitestunion.com.

Key facts. Cited by 475 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 77; 2022: 66; 2023: 83; 2024: 87; 2025: 89; 2026: 73.

475 papers.

Sort:

By area:

  1. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  2. 2021Transformer Trackingcited by 412
  3. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 350
  4. 2022Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Frameworkcited by 330
  5. 2023Perception Test: A Diagnostic Benchmark for Multimodal Video Modelscited by 314
  6. 2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 302
  7. 2022MixFormer: End-to-End Tracking with Iterative Mixed Attentioncited by 281
  8. 2022TAP-Vid: A Benchmark for Tracking Any Point in a Videocited by 263
  9. 2025VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuningcited by 255
  10. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
  11. 2023Video Understanding with Large Language Models: A Surveycited by 206
  12. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 192
38 more
  1. 2023Visual Prompt Multi-Modal Trackingcited by 142
  2. 2022AiATrack: Attention in Attention for Transformer Visual Trackingcited by 137
  3. 2021VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flowscited by 129
  4. 2024ODTrack: Online Dense Temporal Token Learning for Visual Trackingcited by 129
  5. 2021Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmarkcited by 126
  6. 2021SwinTrack: A Simple and Strong Baseline for Transformer Trackingcited by 126
  7. 2022Backbone is All Your Need: A Simplified Architecture for Visual Object Trackingcited by 119
  8. 2022Transforming Model Prediction for Trackingcited by 117
  9. 2022Revealing the Dark Secrets of Masked Image Modelingcited by 117
  10. 2025Streaming Video Question-Answering with In-context Video KV-Cache Retrievalcited by 117
  11. 2022Global Tracking Transformerscited by 110
  12. 2024SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memorycited by 94
  13. 2022Towards Grand Unification of Object Trackingcited by 93
  14. 2023Generalized Relation Modeling for Transformer Trackingcited by 93
  15. 2022ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wildcited by 92
  16. 2021STMTrack: Template-free Visual Tracking with Space-time Memory Networkscited by 91
  17. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  18. 2021Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspectivecited by 81
  19. 2023Robust Object Modeling for Visual Trackingcited by 80
  20. 2024SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Treecited by 80
  21. 2025StreamForest: Efficient Online Video Understanding with Persistent Event Memorycited by 78
  22. 2024Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformerscited by 76
  23. 2022Transformer Tracking with Cyclic Shifting Window Attentioncited by 75
  24. 2021HiFT: Hierarchical Feature Transformer for Aerial Trackingcited by 72
  25. 2023HIPTrack: Visual Tracking with Historical Promptscited by 71
  26. 2024Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performancecited by 70
  27. 2022TCTrack: Temporal Contexts for Aerial Trackingcited by 69
  28. 2025V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoningcited by 68
  29. 2021Learn to Match: Automatic Matching Network Design for Visual Trackingcited by 67
  30. 2021DepthTrack : Unveiling the Power of RGBD Trackingcited by 67
  31. 2024A Distractor-Aware Memory for Visual Object Tracking with SAM2cited by 66
  32. 2023Single-Model and Any-Modality for Video Object Trackingcited by 65
  33. 2024OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuningcited by 65
  34. 2025VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perceptioncited by 65
  35. 2022Correlation-Aware Deep Trackingcited by 62
  36. 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 62
  37. 2024Online Video Understanding: OVBench and VideoChat-Onlinecited by 61
  38. 2022Prompting for Multi-Modal Trackingcited by 59

50 most cited of 475 All 475 (JSON)