% Key papers for Language-grounded scene text and structure (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2020_x_16499,
  title = {{X-Linear Attention Networks for Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2021_conceptual_16732,
  title = {{Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2016_jointly_11632,
  title = {{Jointly Modeling Embedding and Translation to Bridge Video and Language}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{aaai2016_text_105187,
  title = {{Text Matching as Image Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10341},
}

@inproceedings{aaai2019_show_103484,
  title = {{Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4881},
}

@inproceedings{cvpr2021_read_17706,
  title = {{Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2020_towards_16350,
  title = {{Towards Accurate Scene Text Recognition With Semantic Reasoning Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2021_similarity_1386,
  title = {{Similarity Reasoning and Filtration for Image-Text Matching}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/01218-similarity-reasoning-and-filtration-for-image-text-matching/},
}

@inproceedings{cvpr2018_aon_12816,
  title = {{AON: Towards Arbitrarily-Oriented Text Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Cheng_AON_Towards_Arbitrarily-Oriented_CVPR_2018_paper.html},
}

@inproceedings{cvpr2020_seed_16158,
  title = {{SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2016_reading_105412,
  title = {{Reading Scene Text in Deep Convolutional Sequences}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10465},
}

@inproceedings{aaai2020_decoupled_103796,
  title = {{Decoupled Attention Network for Text Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6903},
}

@inproceedings{aaai2019_scene_103497,
  title = {{Scene Text Recognition from Two-Dimensional Perspective}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4895},
}

@inproceedings{cvpr2017_instance_12357,
  title = {{Instance-Aware Image and Sentence Matching With Selective Multimodal LSTM}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{aaai2021_ernie_491,
  title = {{ERNIE-ViL: Knowledge Enhanced Vision-Language Representations through Scene Graphs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/03208-ernie-vil-knowledge-enhanced-vision-language-representations-through-scene-graphs/},
}

@inproceedings{cvpr2021_seeing_17837,
  title = {{Seeing Out of the Box: End-to-End Pre-Training for Vision-Language Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_winoground_20228,
  title = {{Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_negative_19419,
  title = {{Negative-Aware Attention Framework for Image-Text Matching}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2018_char_103987,
  title = {{Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12246},
}

@inproceedings{cvpr2019_unified_14962,
  title = {{Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning Representations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2024_context_23024,
  title = {{Context-Aware Integration of Language and Visual References for Natural Language Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29839},
}

@inproceedings{cvpr2024_ote_24319,
  title = {{OTE: Exploring Accurate Scene Text Recognition Using One Token}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31404},
}

@inproceedings{cvpr2024_a_22653,
  title = {{A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31604},
}

@inproceedings{cvpr2024_multi_24216,
  title = {{Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29497},
}

@inproceedings{aaai2024_image_6272,
  title = {{Image as a Language: Revisiting Scene Text Recognition via Balanced, Unified and Synchronized Vision-Language Reasoning Network}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28402},
}

@inproceedings{cvpr2025_resclip_27434,
  title = {{ResCLIP: Residual Attention for Training-free Dense Vision-language Inference}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32791},
}

@inproceedings{aaai2024_identification_6264,
  title = {{Identification of Necessary Semantic Undertakers in the Causal View for Image-Text Matching}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28538},
}

@inproceedings{cvpr2025_mambavlt_26915,
  title = {{MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33167},
}

@inproceedings{icml2024_image_44975,
  title = {{Image Fusion via Vision-Language Model}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33477},
}

@inproceedings{aaai2025_asymmetric_8157,
  title = {{Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32605},
}

@inproceedings{cvpr2024_u_25098,
  title = {{U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29191},
}

@inproceedings{cvpr2025_linguistics_26800,
  title = {{Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32539},
}

@inproceedings{neurips2024_countgd_73168,
  title = {{CountGD: Multi-Modal Open-World Counting}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94265},
}

@inproceedings{aaai2025_instructocr_9573,
  title = {{InstructOCR: Instruction Boosting Scene Text Spotting}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32286},
}

@inproceedings{cvpr2025_enhancing_26147,
  title = {{Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34390},
}

@inproceedings{cvpr2025_hyperbolic_26555,
  title = {{Hyperbolic Safety-Aware Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35085},
}

@inproceedings{aaai2025_bimac_8264,
  title = {{BiMAC: Bidirectional Multimodal Alignment in Contrastive Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34384},
}

@inproceedings{cvpr2024_semantic_24797,
  title = {{Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29569},
}

@inproceedings{cvpr2025_recurrence_27417,
  title = {{Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32962},
}

@inproceedings{aaai2025_exploring_9089,
  title = {{Exploring the Potential of Large Vision-Language Models for Unsupervised Text-Based Person Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32543},
}