mlsanityData to 7 Oct 2026

ODTrack: Online Dense Temporal Token Learning for Visual Tracking

arXiv 2401.01686 ↗First posted 3 Jan 2024cs.CVcited by 129

Not on the map. Why?

Abstract (arXiv)

Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between reference and search frames via an offline mode. Consequently, they can only interact independently within each image-pair and establish limited temporal correlations. To alleviate the above problem, we propose a simple, flexible and effective video-level tracking pipeline, named ODTrack, which densely associates the contextual relationships of video frames in an online token propagation manner. ODTrack receives video frames of arbitrary length to capture the spatio-temporal trajectory relationships of an instance, and compresses the discrimination features (localization information) of a target into a token sequence to achieve frame-to-frame association. This new solution brings the following benefits: 1) the purified token sequences can serve as prompts for the inference in the next video frame, whereby past information is leveraged to guide future inference; 2) the complex online update strategies are effectively avoided by the iterative propagation of token sequences, and thus we can achieve more efficient model representation and computation. ODTrack achieves a new textitSOTA performance on seven benchmarks, while running at real-time speed. Code and models are available at urlhttps://github.com/GXNU-ZhongLab/ODTrack.

Key facts. Cited by 129 papers in the map (data through 7 Oct 2026). Builds on 30 of its 40 references that are in the map. First posted on arXiv 3 Jan 2024.

Builds on

30 of 40 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  6. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  7. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 471
  8. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
  9. 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 424
  10. 2021Transformer Trackingcited by 412
  11. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  12. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 348
18 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 342
  3. 2022Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Frameworkcited by 328
  4. 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
  5. 2022MixFormer: End-to-End Tracking with Iterative Mixed Attentioncited by 278
  6. 2020Probabilistic Regression for Visual Trackingcited by 231
  7. 2020Siamese Box Adaptive Network for Visual Trackingcited by 189
  8. 2019Siam R-CNN: Visual Tracking by Re-Detectioncited by 174
  9. 2022AiATrack: Attention in Attention for Transformer Visual Trackingcited by 137
  10. 2021Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmarkcited by 124
  11. 2023Generalized Relation Modeling for Transformer Trackingcited by 93
  12. 2021STMTrack: Template-free Visual Tracking with Space-time Memory Networkscited by 91
  13. 2020Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimationcited by 81
  14. 2019Learning the Model Update for Siamese Trackerscited by 75
  15. 2020Graph Attention Trackingcited by 70
  16. 2022TCTrack: Temporal Contexts for Aerial Trackingcited by 69
  17. 2022Learning Target-aware Representation for Visual Tracking via Informative Interactionscited by 25
  18. 2020Learning to Fuse Asymmetric Feature Maps in Siamese Trackerscited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 21; 2025: 53; 2026: 55.

129 papers.

Sort:

By area:

  1. 2024SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memorycited by 91
  2. 2024SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Treecited by 77
  3. 2024A Distractor-Aware Memory for Visual Object Tracking with SAM2cited by 63
  4. 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 59
  5. 2024Exploring Enhanced Contextual Information for Video-Level Object Trackingcited by 36
  6. 2025HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrievalcited by 32
  7. 2025Towards Universal Modal Tracking with Online Dense Temporal Token Learningcited by 30
  8. 2025SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Trackingcited by 23
  9. 2025Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Trackingcited by 23
  10. 2025SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overheadcited by 23
  11. 2024Mamba-FETrack: Frame-Event Tracking via State Space Modelcited by 21
  12. 2024Efficient Fine-Tuning of Large Language Models for Automated Medical Documentationcited by 16
38 more
  1. 2024Robust Tracking via Mamba-based Context-aware Token Learningcited by 15
  2. 2025MUST: The First Dataset and Unified Framework for Multispectral UAV Single Object Trackingcited by 15
  3. 2024MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Trackingcited by 14
  4. 2025RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditionscited by 13
  5. 2024MambaEVT: Event Stream based Visual Object Tracking using State Space Modelcited by 11
  6. 2024MambaLCT: Boosting Tracking via Long-term Context State Space Modelcited by 11
  7. 2025SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networkscited by 11
  8. 2025UncTrack: Reliable Visual Object Tracking with Uncertainty-Aware Prototype Memory Networkcited by 11
  9. 2024General Compression Framework for Efficient Transformer Object Trackingcited by 10
  10. 2024How Texts Help? A Fine-grained Evaluation to Reveal the Role of Language in Vision-Language Trackingcited by 10
  11. 2025CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Featurescited by 10
  12. 2025ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Trackingcited by 10
  13. 2025ReasoningTrack: Chain-of-Thought Reasoning for Long-term Vision-Language Trackingcited by 9
  14. 2024Long-Term Visual Object Tracking with Event Cameras: An Associative Memory Augmented Tracker and A Benchmark Datasetcited by 8
  15. 2024Enhancing Vision-Language Tracking by Effectively Converting Textual Cues into Visual Cuescited by 8
  16. 2024RGB-Sonar Tracking Benchmark and Spatial Cross-Attention Transformer Trackercited by 6
  17. 2024A GEN AI Framework for Medical Note Generationcited by 6
  18. 2025MITracker: Multi-View Integration for Visual Object Trackingcited by 5
  19. 2025HiM2SAM: Enhancing SAM2 with Hierarchical Motion Estimation and Memory Optimization towards Long-term Trackingcited by 5
  20. 2025CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Frameworkcited by 4
  21. 2025TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Trackingcited by 4
  22. 2025SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Trackingcited by 4
  23. 2025Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignmentcited by 4
  24. 2025Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Trackingcited by 4
  25. 2026TP-Spikformer: Token Pruned Spiking Transformercited by 4
  26. 2024XS-VID: A Large-Scale Benchmark for Small Object Detection and Tracking in Videoscited by 3
  27. 2025Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approachcited by 3
  28. 2025Efficient Motion Prompt Learning for Robust Visual Trackingcited by 3
  29. 2025Explicit Context Reasoning with Supervision for Visual Trackingcited by 3
  30. 2025Track-On2: Enhancing Online Point Tracking with Memorycited by 3
  31. 2025UAV-MM3D: A Large-Scale Synthetic Benchmark for 3D Perception of Unmanned Aerial Vehicles with Multi-Modal Datacited by 3
  32. 2025VPTracker: Global Vision-Language Tracking via Visual Promptcited by 3
  33. 2024Cross Fusion RGB-T Tracking with Bi-directional Adaptercited by 2
  34. 2024Visual Object Tracking across Diverse Data Modalities: A Reviewcited by 2
  35. 2025MrTrack: Register Mamba for Needle Tracking with Rapid Reciprocating Motion during Ultrasound-Guided Aspiration Biopsycited by 2
  36. 2025Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object Trackingcited by 2
  37. 2025ATSTrack: Enhancing Visual-Language Tracking by Aligning Temporal and Spatial Scalescited by 2
  38. 2025UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditionscited by 2

50 most cited of 129 All 129 (JSON)