% Key papers for Multimodal and affective interaction modeling (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2016_building_104744,
  title = {{Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/9987},
}

@inproceedings{cvpr2021_artemis_16607,
  title = {{ArtEmis: Affective Language for Visual Art}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{neurips2020_the_60946,
  title = {{The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17923},
}

@inproceedings{cvpr2019_connecting_13959,
  title = {{Connecting Touch and Vision via Cross-Modal Prediction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2017_connecting_12121,
  title = {{Connecting Look and Feel: Associating the Visual and Tactile Properties of Physical Materials}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2020_multimodal_15925,
  title = {{Multimodal Categorization of Crisis Events in Social Media}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2024_embodiedscan_23354,
  title = {{EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31304},
}

@inproceedings{neurips2020_a_59227,
  title = {{A Benchmark for Systematic Generalization in Grounded Language Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18200},
}

@inproceedings{aaai2017_towards_100316,
  title = {{Towards Better Understanding the Clothing Fashion Styles: A Multimodal Deep Learning Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10509},
}

@inproceedings{aaai2022_numhtml_2480,
  title = {{NumHTML: Numeric-Oriented Hierarchical Transformer Model for Multi-Task Financial Forecasting}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/11604-numhtml-numeric-oriented-hierarchical-transformer-model-for-multi-task-financial-forecasting/},
}

@inproceedings{cvpr2021_intentonomy_17194,
  title = {{Intentonomy: A Dataset and Study Towards Human Intent Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_it_19106,
  title = {{It Is Okay To Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_learning_21362,
  title = {{Learning Emotion Representations From Verbal and Nonverbal Communication}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21983},
}

@inproceedings{cvpr2024_inter_23827,
  title = {{Inter-X: Towards Versatile Human-Human Interaction Analysis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30386},
}

@inproceedings{cvpr2020_from_15568,
  title = {{From Paris to Berlin: Discovering Fashion Style Influences Around the World}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2024_unveiling_7726,
  title = {{Unveiling Implicit Deceptive Patterns in Multi-Modal Fake News via Neuro-Symbolic Reasoning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28677},
}

@inproceedings{aaai2025_each_8885,
  title = {{Each Fake News Is Fake in Its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/31999},
}

@inproceedings{neurips2022_touch_65297,
  title = {{Touch and Go: Learning from Human-Collected Vision and Touch}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55766},
}

@inproceedings{cvpr2023_affection_20369,
  title = {{Affection: Learning Affective Explanations for Real-World Visual Data}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21204},
}

@inproceedings{aaai2021_ideography_744,
  title = {{Ideography Leads Us to the Field of Cognition: A Radical-Guided Associative Model for Chinese Text Classification}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/13898-ideography-leads-us-to-the-field-of-cognition-a-radical-guided-associative-model-for-chinese-text-classification/},
}

@inproceedings{cvpr2024_narrative_24253,
  title = {{Narrative Action Evaluation with Prompt-Guided Multimodal Interaction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29587},
}

@inproceedings{cvpr2024_jrdb_23848,
  title = {{JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31714},
}

@inproceedings{cvpr2024_polos_24490,
  title = {{Polos: Multimodal Metric Learning from Human Feedback for Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29779},
}

@inproceedings{cvpr2025_aipparel_25396,
  title = {{AIpparel: A Multimodal Foundation Model for Digital Garments}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35255},
}

@inproceedings{cvpr2024_modeling_24178,
  title = {{Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30193},
}

@inproceedings{icml2024_a_45579,
  title = {{A Touch, Vision, and Language Dataset for Multimodal Alignment}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32873},
}

@inproceedings{icml2024_the_45714,
  title = {{The Good, The Bad, and Why: Unveiling Emotions in Generative AI}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32738},
}

@inproceedings{cvpr2025_ego4o_26108,
  title = {{Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33185},
}

@inproceedings{neurips2025_spot_80210,
  title = {{Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=xLFYd1owiP},
}

@inproceedings{aaai2024_image_6271,
  title = {{Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27835},
}

@inproceedings{aaai2024_well_7804,
  title = {{Well, Now We Know! Unveiling Sarcasm: Initiating and Exploring Multimodal Conversations with Reasoning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29864},
}

@inproceedings{aaai2025_multimodal_10066,
  title = {{Multimodal Fine-Grained Apparent Personality Trait Recognition: Joint Modeling of Big Five and Questionnaire Item-level Scores}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32136},
}

@inproceedings{aaai2025_texttoucher_10963,
  title = {{TextToucher: Fine-Grained Text-to-Touch Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32802},
}

@inproceedings{neurips2024_what_74063,
  title = {{What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97489},
}

@inproceedings{aaai2025_debiased_8655,
  title = {{Debiased Multimodal Understanding for Human Language Sequences}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33583},
}

@inproceedings{neurips2024_wonderbread_74103,
  title = {{WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://openreview.net/forum?id=rZlLfa81D8},
}