% Key papers for Fine-grained improvements to CLIP (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2023_exploring_3617,
  title = {{Exploring CLIP for Assessing the Look and Feel of Images}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25353},
}

@inproceedings{cvpr2022_cris_18428,
  title = {{CRIS: CLIP-Driven Referring Image Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2023_clip_3217,
  title = {{CLIP-ReID: Exploiting Vision-Language Model for Image Re-identification without Concrete Text Labels}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25225},
}

@inproceedings{cvpr2023_scaling_22130,
  title = {{Scaling Language-Image Pre-Training via Masking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23014},
}

@inproceedings{aaai2024_vadclip_7753,
  title = {{VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28423},
}

@inproceedings{cvpr2023_crowdclip_20672,
  title = {{CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23133},
}

@inproceedings{cvpr2024_alpha_22755,
  title = {{Alpha-CLIP: A CLIP Model Focusing on Wherever You Want}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31492},
}

@inproceedings{cvpr2024_mobileclip_24168,
  title = {{MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30022},
}

@inproceedings{cvpr2024_rethinking_24637,
  title = {{Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30426},
}

@inproceedings{aaai2024_softclip_7365,
  title = {{SoftCLIP: Softer Cross-Modal Alignment Makes CLIP Stronger}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27955},
}

@inproceedings{neurips2022_cloob_66067,
  title = {{CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53353},
}

@inproceedings{cvpr2023_learning_21355,
  title = {{Learning Customized Visual Models With Retrieval-Augmented Knowledge}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22807},
}

@inproceedings{cvpr2025_saist_27492,
  title = {{SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32729},
}

@inproceedings{cvpr2024_amu_22685,
  title = {{AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31326},
}

@inproceedings{cvpr2024_mope_24163,
  title = {{MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30442},
}

@inproceedings{cvpr2024_openess_24379,
  title = {{OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29439},
}

@inproceedings{neurips2022_quality_64664,
  title = {{Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53131},
}

@inproceedings{cvpr2025_flair_26216,
  title = {{FLAIR: VLM with Fine-grained Language-informed Image Representations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33533},
}

@inproceedings{neurips2023_geodesic_69134,
  title = {{Geodesic Multi-Modal Mixup for Robust Fine-Tuning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70749},
}

@inproceedings{iclr2023_is_32880,
  title = {{Is a Caption Worth a Thousand Images? A Study on Representation Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11417},
}

@inproceedings{cvpr2025_seeing_27608,
  title = {{Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34695},
}

@inproceedings{cvpr2025_discovla_25955,
  title = {{DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32425},
}

@inproceedings{cvpr2025_get_26356,
  title = {{GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34519},
}

@inproceedings{cvpr2025_bringing_25625,
  title = {{Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32959},
}

@inproceedings{icml2024_robust_44577,
  title = {{Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33875},
}

@inproceedings{iclr2024_interpreting_33639,
  title = {{Interpreting CLIP's Image Representation via Text-Based Decomposition}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19436},
}

@inproceedings{neurips2024_clipceil_71807,
  title = {{CLIPCEIL: Domain Generalization through CLIP via Channel rEfinement and Image-text aLignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95489},
}

@inproceedings{aaai2025_unified_11157,
  title = {{Unified Coding for Both Human Perception and Generalized Machine Analytics with CLIP Supervision}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33031},
}

@inproceedings{cvpr2024_explaining_23405,
  title = {{Explaining CLIP's Performance Disparities on Data from Blind/Low Vision Users}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30937},
}

@inproceedings{cvpr2025_clip_25654,
  title = {{CLIP-driven Coarse-to-fine Semantic Guidance for Fine-grained Open-set Semi-supervised Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32494},
}