@proceedings{maiworkshop-2021-multimodal,
    title = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.0/"
}
@inproceedings{rodriguez-bribiesca-etal-2021-multimodal,
    title = "Multimodal Weighted Fusion of Transformers for Movie Genre Classification",
    author = "Rodr{\'i}guez Bribiesca, Isaac  and
      L{\'o}pez Monroy, Adri{\'a}n Pastor  and
      Montes-y-G{\'o}mez, Manuel",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.1/",
    doi = "10.18653/v1/2021.maiworkshop-1.1",
    pages = "1--5"
}
@inproceedings{shalev-etal-2021-randomized,
    title = "On Randomized Classification Layers and Their Implications in Natural Language Generation",
    author = "Shalev, Gal-Lev  and
      Shalev, Gabi  and
      Keshet, Joseph",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.2/",
    doi = "10.18653/v1/2021.maiworkshop-1.2",
    pages = "6--11"
}
@inproceedings{zhang-chai-2021-coin,
    title = "{COIN}: Conversational Interactive Networks for Emotion Recognition in Conversation",
    author = "Zhang, Haidong  and
      Chai, Yekun",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.3/",
    doi = "10.18653/v1/2021.maiworkshop-1.3",
    pages = "12--18"
}
@inproceedings{nagaraj-rao-etal-2021-first,
    title = "A First Look: Towards Explainable {T}ext{VQA} Models via Visual and Textual Explanations",
    author = "Nagaraj Rao, Varun  and
      Zhen, Xingjian  and
      Hovsepian, Karen  and
      Shen, Mingwei",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.4/",
    doi = "10.18653/v1/2021.maiworkshop-1.4",
    pages = "19--29"
}
@inproceedings{zeng-2021-multi,
    title = "Multi Task Learning based Framework for Multimodal Classification",
    author = "Zeng, Danting",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.5/",
    doi = "10.18653/v1/2021.maiworkshop-1.5",
    pages = "30--35"
}
@inproceedings{nagasawa-etal-2021-validity,
    title = "Validity-Based Sampling and Smoothing Methods for Multiple Reference Image Captioning",
    author = "Nagasawa, Shunta  and
      Watanabe, Yotaro  and
      Iyatomi, Hitoshi",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.6/",
    doi = "10.18653/v1/2021.maiworkshop-1.6",
    pages = "36--41"
}
@inproceedings{jin-etal-2021-modality,
    title = "Modality-specific Distillation",
    author = "Jin, Woojeong  and
      Sanjabi, Maziar  and
      Nie, Shaoliang  and
      Tan, Liang  and
      Ren, Xiang  and
      Firooz, Hamed",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.7/",
    doi = "10.18653/v1/2021.maiworkshop-1.7",
    pages = "42--53"
}
@inproceedings{wu-etal-2021-cold,
    title = "Cold Start Problem For Automated Live Video Comments",
    author = "Wu, Hao  and
      Pitie, Fran{\c{c}}ois  and
      Jones, Gareth",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.8/",
    doi = "10.18653/v1/2021.maiworkshop-1.8",
    pages = "54--62"
}
@inproceedings{alnajjar-hamalainen-2021-que,
    title = "{\textexclamdown}{Q}u{\'e} maravilla! Multimodal Sarcasm Detection in {S}panish: a Dataset and a Baseline",
    author = {Alnajjar, Khalid  and
      H{\"a}m{\"a}l{\"a}inen, Mika},
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.9/",
    doi = "10.18653/v1/2021.maiworkshop-1.9",
    pages = "63--68"
}
@inproceedings{gu-budhkar-2021-package,
    title = "A Package for Learning on Tabular and Text Data with Transformers",
    author = "Gu, Ken  and
      Budhkar, Akshay",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.10/",
    doi = "10.18653/v1/2021.maiworkshop-1.10",
    pages = "69--73"
}
@inproceedings{ding-etal-2021-semantic,
    title = "Semantic Aligned Multi-modal Transformer for Vision-{L}anguage{U}nderstanding: A Preliminary Study on Visual {QA}",
    author = "Ding, Han  and
      Li, Li Erran  and
      Hu, Zhiting  and
      Xu, Yi  and
      Hakkani-Tur, Dilek  and
      Du, Zheng  and
      Zeng, Belinda",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.11/",
    doi = "10.18653/v1/2021.maiworkshop-1.11",
    pages = "74--78"
}
@inproceedings{liang-etal-2021-graghvqa,
    title = "{G}ragh{VQA}: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering",
    author = "Liang, Weixin  and
      Jiang, Yanhao  and
      Liu, Zixuan",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.12/",
    doi = "10.18653/v1/2021.maiworkshop-1.12",
    pages = "79--86"
}
@inproceedings{lee-etal-2021-learning,
    title = "Learning to Select Question-Relevant Relations for Visual Question Answering",
    author = "Lee, Jaewoong  and
      Lee, Heejoon  and
      Lee, Hwanhee  and
      Jung, Kyomin",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2021.maiworkshop-1.13/",
    doi = "10.18653/v1/2021.maiworkshop-1.13",
    pages = "87--96"
}