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

@inproceedings{cvpr2019_attention_13865,
  title = {{Attention Branch Network: Learning of Attention Mechanism for Visual Explanation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2018_diverse_104081,
  title = {{Diverse Beam Search for Improved Description of Complex Scenes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12340},
}

@inproceedings{neurips2019_visualizing_59188,
  title = {{Visualizing and Measuring the Geometry of BERT}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13917},
}

@inproceedings{cvpr2021_causal_16695,
  title = {{Causal Attention for Vision-Language Tasks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2016_large_11642,
  title = {{Large-Scale Location Recognition and the Geometric Burstiness Problem}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2022_stacked_19930,
  title = {{Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2019_context_13968,
  title = {{Context-Aware Visual Compatibility Prediction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2024_hiptrack_23661,
  title = {{HIPTrack: Visual Tracking with Historical Prompts}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30245},
}

@inproceedings{cvpr2021_siamese_17894,
  title = {{Siamese Natural Language Tracker: Tracking by Natural Language Descriptions With Siamese Trackers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2021_learning_900,
  title = {{Learning Visual Context for Group Activity Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/03261-learning-visual-context-for-group-activity-recognition/},
}

@inproceedings{cvpr2022_mdan_19288,
  title = {{MDAN: Multi-Level Dependent Attention Network for Visual Emotion Analysis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_linguistic_17356,
  title = {{Linguistic Structures As Weak Supervision for Visual Scene Graph Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2024_from_23522,
  title = {{From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29596},
}

@inproceedings{cvpr2020_learning_15791,
  title = {{Learning Visual Emotion Representations From Web Data}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2023_autoad_20415,
  title = {{AutoAD: Movie Description in Context}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22346},
}

@inproceedings{aaai2024_structure_7432,
  title = {{Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-Modal Structured Representations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28017},
}

@inproceedings{cvpr2023_top_22355,
  title = {{Top-Down Visual Attention From Analysis by Synthesis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23262},
}

@inproceedings{cvpr2022_learning_19203,
  title = {{Learning Program Representations for Food Images and Cooking Recipes}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_uncurated_22449,
  title = {{Uncurated Image-Text Datasets: Shedding Light on Demographic Bias}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22375},
}

@inproceedings{aaai2022_sgeitl_2676,
  title = {{SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/05914-sgeitl-scene-graph-enhanced-image-text-learning-for-visual-commonsense-reasoning/},
}

@inproceedings{cvpr2024_llm4sgg_23894,
  title = {{LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29777},
}

@inproceedings{aaai2024_learning_6458,
  title = {{Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28387},
}

@inproceedings{neurips2024_vrsbench_73630,
  title = {{VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97530},
}

@inproceedings{aaai2025_game4loc_9299,
  title = {{Game4Loc: A UAV Geo-Localization Benchmark from Game Data}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32409},
}

@inproceedings{cvpr2024_multi_24205,
  title = {{Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29746},
}

@inproceedings{aaai2025_motion_9995,
  title = {{Motion Prior Knowledge Learning with Homogeneous Language Descriptions for Moving Infrared Small Target Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32217},
}

@inproceedings{cvpr2024_leveraging_24001,
  title = {{Leveraging Predicate and Triplet Learning for Scene Graph Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29570},
}

@inproceedings{cvpr2025_lscenellm_26707,
  title = {{LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35004},
}

@inproceedings{cvpr2024_question_24554,
  title = {{Question Aware Vision Transformer for Multimodal Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31218},
}

@inproceedings{cvpr2024_socialcounterfactual_24850,
  title = {{SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29820},
}

@inproceedings{aaai2025_awracle_7992,
  title = {{AWRaCLe: All-Weather Image Restoration Using Visual In-Context Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32716},
}

@inproceedings{cvpr2025_4d_25344,
  title = {{4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34514},
}

@inproceedings{neurips2024_sugarcrepe_70746,
  title = {{SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97833},
}

@inproceedings{neurips2024_memvlt_72748,
  title = {{MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94643},
}

@inproceedings{neurips2024_chattracker_71462,
  title = {{ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95794},
}

@inproceedings{aaai2025_pedestrian_10279,
  title = {{Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32434},
}

@inproceedings{cvpr2024_cyclic_23075,
  title = {{Cyclic Learning for Binaural Audio Generation and Localization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30517},
}