% Key papers for Open-vocabulary 3D and world perception (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2023_objaverse_21733,
  title = {{Objaverse: A Universe of Annotated 3D Objects}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22428},
}

@inproceedings{cvpr2022_denseclip_18646,
  title = {{DenseCLIP: Language-Guided Dense Prediction With Context-Aware Prompting}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_eva_20877,
  title = {{EVA: Exploring the Limits of Masked Visual Representation Learning at Scale}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22842},
}

@inproceedings{cvpr2017_relationship_12579,
  title = {{Relationship Proposal Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2024_open3dis_24375,
  title = {{Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31882},
}

@inproceedings{aaai2017_growing_104547,
  title = {{Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10924},
}

@inproceedings{cvpr2022_proposalclip_19630,
  title = {{ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_am_22684,
  title = {{AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30113},
}

@inproceedings{cvpr2024_sai3d_24682,
  title = {{SAI3D: Segment Any Instance in 3D Scenes}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29714},
}

@inproceedings{cvpr2023_learning_21403,
  title = {{Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21107},
}

@inproceedings{cvpr2024_aligning_22750,
  title = {{Aligning and Prompting Everything All at Once for Universal Visual Perception}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29477},
}

@inproceedings{aaai2024_clim_5345,
  title = {{CLIM: Contrastive Language-Image Mosaic for Region Representation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28428},
}

@inproceedings{cvpr2024_open_24369,
  title = {{Open-Vocabulary Object 6D Pose Estimation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31549},
}

@inproceedings{cvpr2025_declip_25861,
  title = {{DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34755},
}

@inproceedings{cvpr2024_see_24764,
  title = {{See Say and Segment: Teaching LMMs to Overcome False Premises}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31231},
}

@inproceedings{cvpr2025_onlineanyseg_27150,
  title = {{OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35233},
}

@inproceedings{neurips2024_training_72617,
  title = {{Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94761},
}

@inproceedings{aaai2016_representing_105170,
  title = {{Representing Verbs as Argument Concepts}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10324},
}

@inproceedings{aaai2017_vision_104609,
  title = {{Vision-Language Fusion for Object Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11187},
}

@inproceedings{cvpr2025_mosaic3d_26999,
  title = {{Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32731},
}

@inproceedings{aaai2025_maskprompt_9911,
  title = {{MaskPrompt: Open-Vocabulary Affordance Segmentation with Object Shape Mask Prompts}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32200},
}

@inproceedings{cvpr2025_relationfield_27426,
  title = {{RelationField: Relate Anything in Radiance Fields}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35013},
}

@inproceedings{iclr2024_the_33602,
  title = {{The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19473},
}

@inproceedings{neurips2025_vl_76574,
  title = {{VL-SAM-V2: Open-World Object Detection with General and Specific Query Fusion}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=KoCytqC9gx},
}

@inproceedings{neurips2025_openlex3d_77788,
  title = {{OpenLex3D: A Tiered Benchmark for Open-Vocabulary 3D Scene Representations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=XZPGUWOXeP},
}

@inproceedings{cvpr2025_compositional_25752,
  title = {{Compositional Caching for Training-free Open-vocabulary Attribute Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32802},
}

@inproceedings{neurips2025_interaction_78664,
  title = {{Interaction-Centric Knowledge Infusion and Transfer for Open Vocabulary Scene Graph Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=h2kwURAFkJ},
}

@inproceedings{iclr2025_3d_81501,
  title = {{3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30275},
}

@inproceedings{iclr2026_person_88956,
  title = {{Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=t3ZMiHhqXm},
}