% Key papers for Open-vocabulary alignment from VLMs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2021_learning_39537,
  title = {{Learning Transferable Visual Models From Natural Language Supervision}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9193},
}

@inproceedings{neurips2016_matching_55862,
  title = {{Matching Networks for One Shot Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/6999},
}

@inproceedings{cvpr2024_florence_23485,
  title = {{Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30529},
}

@inproceedings{cvpr2023_ulip_22435,
  title = {{ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22250},
}

@inproceedings{cvpr2023_generalized_21065,
  title = {{Generalized Decoding for Pixel, Image, and Language}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23105},
}

@inproceedings{cvpr2024_cat_22902,
  title = {{CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31291},
}

@inproceedings{cvpr2017_link_12433,
  title = {{Link the Head to the "Beak": Zero Shot Learning From Noisy Text Description at Part Precision}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{neurips2022_glipv2_66370,
  title = {{GLIPv2: Unifying Localization and Vision-Language Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55017},
}

@inproceedings{cvpr2023_pla_21814,
  title = {{PLA: Language-Driven Open-Vocabulary 3D Scene Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22986},
}

@inproceedings{cvpr2022_clip_18414,
  title = {{CLIP-Event: Connecting Text and Images With Event Structures}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2023_revisiting_4528,
  title = {{Revisiting Classifier: Transferring Vision-Language Models for Video Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25386},
}

@inproceedings{cvpr2022_retrieval_19730,
  title = {{Retrieval Augmented Classification for Long-Tail Visual Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2016_fast_11551,
  title = {{Fast Zero-Shot Image Tagging}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
  url = {https://openaccess.thecvf.com/content_cvpr_2016/html/Zhang_Fast_Zero-Shot_Image_CVPR_2016_paper.html},
}

@inproceedings{neurips2022_elevater_65676,
  title = {{ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55674},
}

@inproceedings{cvpr2024_general_23591,
  title = {{General Object Foundation Model for Images and Videos at Scale}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29939},
}

@inproceedings{cvpr2024_a_22644,
  title = {{A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30861},
}

@inproceedings{neurips2022_k_65639,
  title = {{K-LITE: Learning Transferable Visual Models with External Knowledge}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53138},
}

@inproceedings{neurips2022_dualcoop_64907,
  title = {{DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54575},
}

@inproceedings{aaai2024_a_5043,
  title = {{A Multimodal, Multi-Task Adapting Framework for Video Action Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28361},
}

@inproceedings{cvpr2025_dinov2_25826,
  title = {{DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33482},
}

@inproceedings{cvpr2024_generalizable_23595,
  title = {{Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29944},
}

@inproceedings{iclr2024_emu_35175,
  title = {{Emu: Generative Pretraining in Multimodality}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17898},
}

@inproceedings{cvpr2024_open_24373,
  title = {{Open-World Human-Object Interaction Detection via Multi-modal Prompts}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31520},
}

@inproceedings{cvpr2024_split_24882,
  title = {{Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30062},
}

@inproceedings{cvpr2024_internvl_23832,
  title = {{InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30014},
}

@inproceedings{aaai2024_instructdoc_6329,
  title = {{InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29874},
}

@inproceedings{cvpr2024_emergent_23356,
  title = {{Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29843},
}

@inproceedings{cvpr2024_describing_23154,
  title = {{Describing Differences in Image Sets with Natural Language}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29301},
}

@inproceedings{cvpr2024_one_24357,
  title = {{One-Shot Open Affordance Learning with Foundation Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30384},
}

@inproceedings{iclr2024_matcher_35677,
  title = {{Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17396},
}

@inproceedings{cvpr2024_vit_25210,
  title = {{ViT-Lens: Towards Omni-modal Representations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30695},
}

@inproceedings{cvpr2025_understanding_27990,
  title = {{Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33984},
}

@inproceedings{cvpr2024_synthesize_24929,
  title = {{Synthesize Diagnose and Optimize: Towards Fine-Grained Vision-Language Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31306},
}

@inproceedings{iclr2024_remote_35570,
  title = {{Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17503},
}