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

@inproceedings{cvpr2016_a_11353,
  title = {{A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2017_one_12512,
  title = {{One-Shot Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2021_end_16951,
  title = {{End-to-End Video Instance Segmentation With Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2019_feelvos_14180,
  title = {{FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2016_video_11955,
  title = {{Video Segmentation via Object Flow}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{iclr2025_sam_81557,
  title = {{SAM 2: Segment Anything in Images and Videos}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30219},
}

@inproceedings{cvpr2019_rvos_14699,
  title = {{RVOS: End-To-End Recurrent Network for Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2021_modular_17422,
  title = {{Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2021_efficient_16937,
  title = {{Efficient Regional Memory Network for Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2020_state_16280,
  title = {{State-Aware Tracker for Real-Time Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2021_temporal_1478,
  title = {{Temporal ROI Align for Video Object Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/01442-temporal-roi-align-for-video-object-recognition/},
}

@inproceedings{cvpr2022_implicit_19055,
  title = {{Implicit Motion Handling for Video Camouflaged Object Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_recurrent_19687,
  title = {{Recurrent Dynamic Embedding for Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_reciprocal_17712,
  title = {{Reciprocal Transformations for Unsupervised Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_temporally_19997,
  title = {{Temporally Efficient Vision Transformer for Video Instance Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_language_19159,
  title = {{Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2020_an_15142,
  title = {{An End-to-End Edge Aggregation Network for Moving Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2024_memsam_24132,
  title = {{MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29582},
}

@inproceedings{aaai2021_compfeat_274,
  title = {{CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/01361-compfeat-comprehensive-feature-aggregation-for-video-instance-segmentation/},
}

@inproceedings{cvpr2023_look_21464,
  title = {{Look Before You Match: Instance Understanding Matters in Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23202},
}

@inproceedings{cvpr2024_decoupling_23126,
  title = {{Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30990},
}

@inproceedings{aaai2024_referred_7087,
  title = {{Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28465},
}

@inproceedings{cvpr2024_rmem_24569,
  title = {{RMem: Restricted Memory Banks Improve Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31200},
}

@inproceedings{cvpr2024_dual_23282,
  title = {{Dual Prototype Attention for Unsupervised Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29987},
}

@inproceedings{cvpr2024_event_23394,
  title = {{Event-assisted Low-Light Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31308},
}

@inproceedings{cvpr2024_univs_25135,
  title = {{UniVS: Unified and Universal Video Segmentation with Prompts as Queries}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31859},
}

@inproceedings{cvpr2024_losh_24018,
  title = {{LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29472},
}

@inproceedings{cvpr2025_semantic_27635,
  title = {{Semantic and Sequential Alignment for Referring Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33595},
}

@inproceedings{cvpr2024_audio_22796,
  title = {{Audio-Visual Segmentation via Unlabeled Frame Exploitation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30564},
}

@inproceedings{cvpr2025_edgetam_26082,
  title = {{EdgeTAM: On-Device Track Anything Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34242},
}

@inproceedings{cvpr2025_livos_26786,
  title = {{LiVOS: Light Video Object Segmentation with Gated Linear Matching}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33090},
}

@inproceedings{cvpr2025_sam_27495,
  title = {{SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2\% Training Cost}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33495},
}

@inproceedings{cvpr2025_decoupled_25878,
  title = {{Decoupled Motion Expression Video Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34597},
}

@inproceedings{cvpr2025_segment_27616,
  title = {{Segment Any Motion in Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32979},
}

@inproceedings{cvpr2024_point_24481,
  title = {{Point-VOS: Pointing Up Video Object Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30300},
}

@inproceedings{aaai2026_open_100367,
  title = {{Open-World Object Counting in Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37214},
}

@inproceedings{neurips2025_camsam2_77696,
  title = {{CamSAM2: Segment Anything Accurately in Camouflaged Videos}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=WbpzGpVWVx},
}

@inproceedings{aaai2026_segment_100745,
  title = {{Segment Anything Across Shots: A Method and Benchmark}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/42485},
}