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

@inproceedings{cvpr2018_grounding_13172,
  title = {{Grounding Referring Expressions in Images by Variational Context}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Grounding_Referring_Expressions_CVPR_2018_paper.html},
}

@inproceedings{cvpr2018_visual_13709,
  title = {{Visual Grounding via Accumulated Attention}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Deng_Visual_Grounding_via_CVPR_2018_paper.html},
}

@inproceedings{cvpr2022_improving_19067,
  title = {{Improving Visual Grounding With Visual-Linguistic Verification and Iterative Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_joint_21294,
  title = {{Joint Visual Grounding and Tracking With Natural Language Specification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22595},
}

@inproceedings{cvpr2018_knowledge_13248,
  title = {{Knowledge Aided Consistency for Weakly Supervised Phrase Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Chen_Knowledge_Aided_Consistency_CVPR_2018_paper.html},
}

@inproceedings{neurips2020_counterfactual_59612,
  title = {{Counterfactual Contrastive Learning for Weakly-Supervised Vision-Language Grounding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18392},
}

@inproceedings{aaai2020_learning_103726,
  title = {{Learning Cross-Modal Context Graph for Visual Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6833},
}

@inproceedings{cvpr2019_multi_14541,
  title = {{Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2022_pseudo_19634,
  title = {{Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_language_21319,
  title = {{Language Adaptive Weight Generation for Multi-Task Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21453},
}

@inproceedings{cvpr2017_generating_12305,
  title = {{Generating Descriptions With Grounded and Co-Referenced People}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2019_neural_14570,
  title = {{Neural Sequential Phrase Grounding (SeqGROUND)}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2018_unsupervised_13691,
  title = {{Unsupervised Textual Grounding: Linking Words to Image Concepts}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Yeh_Unsupervised_Textual_Grounding_CVPR_2018_paper.html},
}

@inproceedings{cvpr2023_ns3d_21645,
  title = {{NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22774},
}

@inproceedings{cvpr2019_modularized_14528,
  title = {{Modularized Textual Grounding for Counterfactual Resilience}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2022_deconfounded_1930,
  title = {{Deconfounded Visual Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/00998-deconfounded-visual-grounding/},
}

@inproceedings{aaai2024_parallel_6922,
  title = {{Parallel Vertex Diffusion for Unified Visual Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27896},
}

@inproceedings{neurips2024_simvg_73227,
  title = {{SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94210},
}

@inproceedings{cvpr2022_multi_19386,
  title = {{Multi-Modal Dynamic Graph Transformer for Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_improving_21241,
  title = {{Improving Visual Grounding by Encouraging Consistent Gradient-Based Explanations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21569},
}

@inproceedings{cvpr2024_g_23566,
  title = {{G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29251},
}

@inproceedings{cvpr2024_improved_23766,
  title = {{Improved Visual Grounding through Self-Consistent Explanations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30072},
}

@inproceedings{cvpr2025_your_28169,
  title = {{Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33098},
}

@inproceedings{cvpr2024_investigating_23840,
  title = {{Investigating Compositional Challenges in Vision-Language Models for Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29329},
}

@inproceedings{cvpr2024_towards_25034,
  title = {{Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31698},
}

@inproceedings{aaai2024_cycle_5544,
  title = {{Cycle-Consistency Learning for Captioning and Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28363},
}

@inproceedings{cvpr2024_multi_24202,
  title = {{Multi-Attribute Interactions Matter for 3D Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29285},
}

@inproceedings{aaai2024_scaneru_7269,
  title = {{ScanERU: Interactive 3D Visual Grounding Based on Embodied Reference Understanding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28186},
}

@inproceedings{cvpr2024_when_25283,
  title = {{When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31496},
}

@inproceedings{aaai2024_improving_6304,
  title = {{Improving Panoptic Narrative Grounding by Harnessing Semantic Relationships and Visual Confirmation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27969},
}

@inproceedings{aaai2025_augrefer_8181,
  title = {{AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32863},
}

@inproceedings{neurips2025_scaling_76094,
  title = {{Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=FS0voKxELr},
}

@inproceedings{cvpr2024_naturally_24254,
  title = {{Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31288},
}

@inproceedings{cvpr2025_reasongrounder_27400,
  title = {{ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35062},
}

@inproceedings{aaai2024_beyond_5284,
  title = {{Beyond Grounding: Extracting Fine-Grained Event Hierarchies across Modalities}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29718},
}

@inproceedings{aaai2025_look_9818,
  title = {{Look Around Before Locating: Considering Content and Structure Information for Visual Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32158},
}

@inproceedings{iclr2024_cot3dref_34333,
  title = {{CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18742},
}

@inproceedings{neurips2024_referencing_73883,
  title = {{Referencing Where to Focus: Improving Visual Grounding with Referential Query}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93628},
}