% Key papers for Referring expression comprehension (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2018_mattnet_13352,
  title = {{MAttNet: Modular Attention Network for Referring Expression Comprehension}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Yu_MAttNet_Modular_Attention_CVPR_2018_paper.html},
}

@inproceedings{cvpr2017_modeling_12460,
  title = {{Modeling Relationships in Referential Expressions With Compositional Modular Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2022_lavt_19142,
  title = {{LAVT: Language-Aware Vision Transformer for Referring Image Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2020_multi_15922,
  title = {{Multi-Task Collaborative Network for Joint Referring Expression Comprehension and Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2017_a_12012,
  title = {{A Joint Speaker-Listener-Reinforcer Model for Referring Expressions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2020_referring_16100,
  title = {{Referring Image Segmentation via Cross-Modal Progressive Comprehension}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2019_improving_14312,
  title = {{Improving Referring Expression Grounding With Cross-Modal Attention-Guided Erasing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2019_cross_13984,
  title = {{Cross-Modal Relationship Inference for Grounding Referring Expressions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2020_graph_15618,
  title = {{Graph-Structured Referring Expression Reasoning in the Wild}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2021_referring_61880,
  title = {{Referring Transformer: A One-step Approach to Multi-task Visual Grounding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26095},
}

@inproceedings{cvpr2020_cops_15289,
  title = {{Cops-Ref: A New Dataset and Task on Compositional Referring Expression Comprehension}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2024_mask_24109,
  title = {{Mask Grounding for Referring Image Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30999},
}

@inproceedings{cvpr2022_rex_19659,
  title = {{REX: Reasoning-Aware and Grounded Explanation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2023_referring_4496,
  title = {{Referring Expression Comprehension Using Language Adaptive Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25331},
}

@inproceedings{cvpr2024_lqmformer_23904,
  title = {{LQMFormer: Language-aware Query Mask Transformer for Referring Image Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31268},
}

@inproceedings{aaai2025_multi_10053,
  title = {{Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32265},
}

@inproceedings{cvpr2021_learning_17260,
  title = {{Learning Better Visual Dialog Agents With Pretrained Visual-Linguistic Representation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{neurips2024_oneref_74164,
  title = {{OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93378},
}

@inproceedings{cvpr2024_scanformer_24748,
  title = {{ScanFormer: Referring Expression Comprehension by Iteratively Scanning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31612},
}

@inproceedings{aaai2025_hierarchical_9430,
  title = {{Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32867},
}

@inproceedings{cvpr2024_revisiting_24652,
  title = {{Revisiting Counterfactual Problems in Referring Expression Comprehension}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30410},
}

@inproceedings{cvpr2025_dvin_25848,
  title = {{DViN: Dynamic Visual Routing Network for Weakly Supervised Referring Expression Comprehension}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32531},
}

@inproceedings{cvpr2025_exploring_26186,
  title = {{Exploring Contextual Attribute Density in Referring Expression Counting}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33723},
}

@inproceedings{neurips2024_a_70633,
  title = {{A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97836},
}

@inproceedings{aaai2026_pc_104365,
  title = {{PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37892},
}

@inproceedings{aaai2026_decoupling_105667,
  title = {{Decoupling What to Count and Where to See for Referring Expression Counting}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38423},
}