% Key papers for Transformer-based video object tracking (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2016_siamese_11858,
  title = {{Siamese Instance Search for Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2022_trackformer_20070,
  title = {{TrackFormer: Multi-Object Tracking With Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_transformer_18048,
  title = {{Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2020_autotrack_15170,
  title = {{AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2019_graph_14259,
  title = {{Graph Convolutional Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2022_tctrack_19975,
  title = {{TCTrack: Temporal Contexts for Aerial Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2020_globaltrack_103651,
  title = {{GlobalTrack: A Simple and Strong Baseline for Long-Term Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6758},
}

@inproceedings{aaai2024_odtrack_6803,
  title = {{ODTrack: Online Dense Temporal Token Learning for Visual Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28591},
}

@inproceedings{cvpr2024_autoregressive_22802,
  title = {{Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30736},
}

@inproceedings{cvpr2020_detecting_15404,
  title = {{Detecting Attended Visual Targets in Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2020_cross_15310,
  title = {{Cross-Modal Pattern-Propagation for RGB-T Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2024_ucmctrack_7667,
  title = {{UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28493},
}

@inproceedings{cvpr2024_single_24827,
  title = {{Single-Model and Any-Modality for Video Object Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31696},
}

@inproceedings{aaai2024_explicit_5900,
  title = {{Explicit Visual Prompts for Visual Object Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28286},
}

@inproceedings{cvpr2023_unifying_22470,
  title = {{Unifying Short and Long-Term Tracking With Graph Hierarchies}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22733},
}

@inproceedings{cvpr2023_videotrack_22523,
  title = {{VideoTrack: Learning To Track Objects via Video Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23003},
}

@inproceedings{cvpr2021_tracking_18036,
  title = {{Tracking Pedestrian Heads in Dense Crowd}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2024_temporal_7512,
  title = {{Temporal Adaptive RGBT Tracking with Modality Prompt}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28352},
}

@inproceedings{cvpr2022_unsupervised_20145,
  title = {{Unsupervised Learning of Accurate Siamese Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_rotation_17782,
  title = {{Rotation Equivariant Siamese Networks for Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2025_exploring_9071,
  title = {{Exploring Enhanced Contextual Information for Video-Level Object Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32440},
}

@inproceedings{aaai2025_exploiting_9065,
  title = {{Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32372},
}

@inproceedings{cvpr2024_leap_23886,
  title = {{LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29776},
}

@inproceedings{aaai2025_mambalct_9902,
  title = {{MambaLCT: Boosting Tracking via Long-term Context State Space Model}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32528},
}

@inproceedings{aaai2025_less_9769,
  title = {{Less Is More: Token Context-Aware Learning for Object Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32954},
}

@inproceedings{neurips2024_webuot_72993,
  title = {{WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97605},
}

@inproceedings{aaai2025_temporal_10939,
  title = {{Temporal Coherent Object Flow for Multi-Object Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32749},
}

@inproceedings{cvpr2025_autoregressive_25544,
  title = {{Autoregressive Sequential Pretraining for Visual Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34853},
}

@inproceedings{aaai2025_patch_10276,
  title = {{Patch-level Sounding Object Tracking for Audio-Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32538},
}

@inproceedings{cvpr2024_gigatraj_23628,
  title = {{GigaTraj: Predicting Long-term Trajectories of Hundreds of Pedestrians in Gigapixel Complex Scenes}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30583},
}

@inproceedings{cvpr2024_sira_24712,
  title = {{SIRA: Scalable Inter-frame Relation and Association for Radar Perception}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31642},
}

@inproceedings{cvpr2024_drivetrack_23271,
  title = {{DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30851},
}

@inproceedings{cvpr2024_mtmmc_24085,
  title = {{MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30668},
}

@inproceedings{aaai2024_sampling_7256,
  title = {{Sampling-Resilient Multi-Object Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28115},
}