% Key papers for Multimodal question answering datasets (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2016_stacked_11887,
  title = {{Stacked Attention Networks for Image Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2019_gqa_14234,
  title = {{GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2016_visual7w_11962,
  title = {{Visual7W: Grounded Question Answering in Images}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2019_towards_14935,
  title = {{Towards VQA Models That Can Read}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2017_tgif_12680,
  title = {{TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2018_iqa_13198,
  title = {{IQA: Visual Question Answering in Interactive Environments}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Gordon_IQA_Visual_Question_CVPR_2018_paper.html},
}

@inproceedings{cvpr2018_embodied_13065,
  title = {{Embodied Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Das_Embodied_Question_Answering_CVPR_2018_paper.html},
}

@inproceedings{cvpr2019_heterogeneous_14278,
  title = {{Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{neurips2016_multimodal_55883,
  title = {{Multimodal Residual Learning for Visual QA}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7176},
}

@inproceedings{aaai2020_reasoning_103660,
  title = {{Reasoning with Heterogeneous Graph Alignment for Video Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6767},
}

@inproceedings{aaai2017_leveraging_103959,
  title = {{Leveraging Video Descriptions to Learn Video Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11238},
}

@inproceedings{cvpr2019_recursive_14716,
  title = {{Recursive Visual Attention in Visual Dialog}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2022_invariant_19101,
  title = {{Invariant Grounding for Video Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_learning_19211,
  title = {{Learning To Answer Questions in Dynamic Audio-Visual Scenarios}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2018_focal_13125,
  title = {{Focal Visual-Text Attention for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Liang_Focal_Visual-Text_Attention_CVPR_2018_paper.html},
}

@inproceedings{aaai2022_video_2936,
  title = {{Video as Conditional Graph Hierarchy for Multi-Granular Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/02804-video-as-conditional-graph-hierarchy-for-multi-granular-question-answering/},
}

@inproceedings{cvpr2019_information_14319,
  title = {{Information Maximizing Visual Question Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2019_progressive_14671,
  title = {{Progressive Attention Memory Network for Movie Story Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2018_differential_13015,
  title = {{Differential Attention for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Patro_Differential_Attention_for_CVPR_2018_paper.html},
}

@inproceedings{neurips2017_visual_56770,
  title = {{Visual Reference Resolution using Attention Memory for Visual Dialog}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9154},
}

@inproceedings{cvpr2024_can_22946,
  title = {{Can I Trust Your Answer? Visually Grounded Video Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31031},
}

@inproceedings{cvpr2024_morevqa_24164,
  title = {{MoReVQA: Exploring Modular Reasoning Models for Video Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31420},
}

@inproceedings{aaai2024_object_6811,
  title = {{Object-Aware Adaptive-Positivity Learning for Audio-Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28116},
}

@inproceedings{cvpr2025_vdocrag_28041,
  title = {{VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34926},
}

@inproceedings{aaai2025_grounded_9374,
  title = {{Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32214},
}

@inproceedings{cvpr2025_cross_25799,
  title = {{Cross-modal Causal Relation Alignment for Video Question Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32924},
}

@inproceedings{cvpr2024_vtqa_25198,
  title = {{VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30970},
}

@inproceedings{iclr2024_davidsonian_34112,
  title = {{Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18963},
}

@inproceedings{cvpr2025_question_27342,
  title = {{Question-Aware Gaussian Experts for Audio-Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32451},
}

@inproceedings{cvpr2024_language_23921,
  title = {{Language-aware Visual Semantic Distillation for Video Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30991},
}

@inproceedings{neurips2024_right_70645,
  title = {{Right this way: Can VLMs Guide Us to See More to Answer Questions?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96477},
}

@inproceedings{aaai2025_assessing_8147,
  title = {{Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34183},
}

@inproceedings{cvpr2025_commonsense_25744,
  title = {{Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33105},
}

@inproceedings{cvpr2025_zero_28181,
  title = {{Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33335},
}

@inproceedings{neurips2024_look_74253,
  title = {{Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93303},
}

@inproceedings{aaai2024_convqg_5458,
  title = {{ConVQG: Contrastive Visual Question Generation with Multimodal Guidance}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28216},
}

@inproceedings{aaai2025_explicitly_9059,
  title = {{Explicitly Guided Difficulty-Controllable Visual Question Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34745},
}

@inproceedings{neurips2025_benchmarking_77653,
  title = {{Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=W4b3v9jx1p},
}

@inproceedings{aaai2025_audio_8178,
  title = {{Audio-Visual Adaptive Fusion Network for Question Answering Based on Contrastive Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33138},
}

@inproceedings{neurips2024_causalchaos_73297,
  title = {{CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97580},
}