{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:55:57Z","timestamp":1781585757845,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Nanyang Associate Professorship and the National Research Foundation Fellowship","award":["NRF- NRFF13-2021-000"],"award-info":[{"award-number":["NRF- NRFF13-2021-000"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612526","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"5504-5513","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Training Multimedia Event Extraction With Generated Images and Captions"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3534-9547","authenticated-orcid":false,"given":"Zilin","family":"Du","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4819-2489","authenticated-orcid":false,"given":"Yunxin","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1034-9508","authenticated-orcid":false,"given":"Xu","family":"Guo","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7897-3035","authenticated-orcid":false,"given":"Yidan","family":"Sun","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6230-2376","authenticated-orcid":false,"given":"Boyang","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Shakhmatov Arseniy Razzhigaev Anton Nikolich Aleksandr Arkhipkin Vladimir Pavlov Igor Kuznetsov Andrey and Dimitrov Denis. 2023. Kandinsky 2.1. https:\/\/github.com\/ai-forever\/Kandinsky-2."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.8"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547943"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01904"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01904"},{"key":"e_1_3_2_2_6_1","volume-title":"Radu Tudor Ionescu, and Mubarak Shah","author":"Croitoru Florinel-Alin","year":"2023","unstructured":"Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, and Mubarak Shah. 2023. Diffusion models in vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_2_7_1","volume-title":"Lrec","volume":"2","author":"Doddington George R","year":"2004","unstructured":"George R Doddington, Alexis Mitchell, Mark A Przybocki, Lance A Ramshaw, Stephanie M Strassel, and Ralph M Weischedel. 2004. The automatic content extraction (ace) program-tasks, data, and evaluation.. In Lrec, Vol. 2. Lisbon, 837--840."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.52"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01273"},{"key":"e_1_3_2_2_10_1","volume-title":"Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning. In International Conference on Learning Representations.","author":"Gao Jiahui","year":"2023","unstructured":"Jiahui Gao, Renjie Pi, LIN Yong, Hang Xu, Jiacheng Ye, Zhiyong Wu, Weizhong Zhang, Xiaodan Liang, Zhenguo Li, and Lingpeng Kong. 2023. Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_11_1","volume-title":"Automatic labeling of semantic roles. Computational linguistics","author":"Gildea Daniel","year":"2002","unstructured":"Daniel Gildea and Daniel Jurafsky. 2002. Automatic labeling of semantic roles. Computational linguistics, Vol. 28, 3 (2002), 245--288."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.181"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1076"},{"key":"e_1_3_2_2_14_1","volume-title":"International conference on learning representations.","author":"Higgins Irina","year":"2016","unstructured":"Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. 2016. beta-vae: Learning basic visual concepts with a constrained variational framework. In International conference on learning representations."},{"key":"e_1_3_2_2_15_1","volume-title":"The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751","author":"Holtzman Ari","year":"2019","unstructured":"Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2019. The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751 (2019)."},{"key":"e_1_3_2_2_16_1","volume-title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor. arXiv preprint arXiv:2212.09689","author":"Honovich Or","year":"2022","unstructured":"Or Honovich, Thomas Scialom, Omer Levy, and Timo Schick. 2022. Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor. arXiv preprint arXiv:2212.09689 (2022)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.138"},{"key":"e_1_3_2_2_18_1","volume-title":"International Conference on Machine Learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International Conference on Machine Learning. PMLR, 4904--4916."},{"key":"e_1_3_2_2_19_1","volume-title":"Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217","author":"Kang Bingyi","year":"2019","unstructured":"Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo, Jiashi Feng, and Yannis Kalantidis. 2019. Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217 (2019)."},{"key":"e_1_3_2_2_20_1","unstructured":"Paul R Kingsbury and Martha Palmer. 2002. From TreeBank to PropBank.. In LREC. 1989--1993."},{"key":"e_1_3_2_2_21_1","volume-title":"The Illustrated Image Captioning using transformers. ankur3107.github.io","author":"Kumar Ankur","year":"2022","unstructured":"Ankur Kumar. 2022. The Illustrated Image Captioning using transformers. ankur3107.github.io (2022). https:\/\/ankur3107.github.io\/blogs\/the-illustrated-image-captioning-using-transformers\/"},{"key":"e_1_3_2_2_22_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Li Bowen","year":"2019","unstructured":"Bowen Li, Xiaojuan Qi, Thomas Lukasiewicz, and Philip Torr. 2019. Controllable text-to-image generation. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_23_1","volume-title":"2023 b. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023 b. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_2_24_1","volume-title":"International Conference on Machine Learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022b. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. PMLR, 12888--12900."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01593"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.230"},{"key":"e_1_3_2_2_27_1","unstructured":"Qian Li Jianxin Li Jiawei Sheng Shiyao Cui Jia Wu Yiming Hei Hao Peng Shu Guo Lihong Wang Amin Beheshti et al. 2022a. A Survey on Deep Learning Event Extraction: Approaches and Applications. IEEE Transactions on Neural Networks and Learning Systems (2022)."},{"key":"e_1_3_2_2_28_1","volume-title":"2023 a. LMEye: An Interactive Perception Network for Large Language Models. arXiv preprint arXiv:2305.03701","author":"Li Yunxin","year":"2023","unstructured":"Yunxin Li, Baotian Hu, Xinyu Chen, Lin Ma, and Min Zhang. 2023 a. LMEye: An Interactive Perception Network for Large Language Models. arXiv preprint arXiv:2305.03701 (2023)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548132"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1156"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.457"},{"key":"e_1_3_2_2_32_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.326"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.466"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.57"},{"key":"e_1_3_2_2_36_1","volume-title":"Generating training data with language models: Towards zero-shot language understanding. arXiv preprint arXiv:2202.04538","author":"Meng Yu","year":"2022","unstructured":"Yu Meng, Jiaxin Huang, Yu Zhang, and Jiawei Han. 2022a. Generating training data with language models: Towards zero-shot language understanding. arXiv preprint arXiv:2202.04538 (2022)."},{"key":"e_1_3_2_2_37_1","volume-title":"Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning. arXiv preprint arXiv:2211.03044","author":"Meng Yu","year":"2022","unstructured":"Yu Meng, Martin Michalski, Jiaxin Huang, Yu Zhang, Tarek Abdelzaher, and Jiawei Han. 2022b. Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning. arXiv preprint arXiv:2211.03044 (2022)."},{"key":"e_1_3_2_2_38_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning. PMLR, 16784--16804","author":"Nichol Alexander Quinn","year":"2022","unstructured":"Alexander Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob Mcgrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning. PMLR, 16784--16804."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_19"},{"key":"e_1_3_2_2_40_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_41_1","volume-title":"International Conference on Machine Learning. PMLR, 8821--8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821--8831."},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of the 2020 conference on empirical methods in natural language processing (emnlp). 5357--5367","author":"Ramponi Alan","unstructured":"Alan Ramponi, Rob van der Goot, Rosario Lombardo, and Barbara Plank. 2020. Biomedical event extraction as sequence labeling. In Proceedings of the 2020 conference on empirical methods in natural language processing (emnlp). 5357--5367."},{"key":"e_1_3_2_2_43_1","volume-title":"International conference on machine learning. PMLR, 1060--1069","author":"Reed Scott","year":"2016","unstructured":"Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, and Honglak Lee. 2016. Generative adversarial text to image synthesis. In International conference on machine learning. PMLR, 1060--1069."},{"key":"e_1_3_2_2_44_1","volume-title":"Sixth Workshop on Very Large Corpora.","author":"Riloff Ellen","year":"1998","unstructured":"Ellen Riloff and Mark Schmelzenbach. 1998. An empirical approach to conceptual case frame acquisition. In Sixth Workshop on Very Large Corpora."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.196"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00554"},{"key":"e_1_3_2_2_48_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36479--36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6437"},{"key":"e_1_3_2_2_50_1","unstructured":"Ultralytics. 2023. YOLOv8. https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"e_1_3_2_2_51_1","volume-title":"NVAE: A deep hierarchical variational autoencoder. Advances in neural information processing systems","author":"Vahdat Arash","year":"2020","unstructured":"Arash Vahdat and Jan Kautz. 2020. NVAE: A deep hierarchical variational autoencoder. Advances in neural information processing systems, Vol. 33 (2020), 19667--19679."},{"key":"e_1_3_2_2_52_1","volume-title":"ACE 2005 multilingual training corpus. Linguistic Data Consortium","volume":"57","author":"Walker Christopher","year":"2006","unstructured":"Christopher Walker, Stephanie Strassel, Julie Medero, and Kazuaki Maeda. 2006. ACE 2005 multilingual training corpus. Linguistic Data Consortium, Philadelphia, Vol. 57 (2006), 45."},{"key":"e_1_3_2_2_53_1","volume-title":"Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100","author":"Wang Jianfeng","year":"2022","unstructured":"Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu, Linjie Li, Kevin Lin, Zhe Gan, Zicheng Liu, Ce Liu, and Lijuan Wang. 2022b. Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)."},{"key":"e_1_3_2_2_54_1","volume-title":"International Conference on Machine Learning. PMLR, 23318--23340","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022c. Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In International Conference on Machine Learning. PMLR, 23318--23340."},{"key":"e_1_3_2_2_55_1","volume-title":"ReelFramer: Co-creating News Reels on Social Media with Generative AI. arXiv preprint arXiv:2304.09653","author":"Wang Sitong","year":"2023","unstructured":"Sitong Wang, Samia Menon, Tao Long, Keren Henderson, Dingzeyu Li, Kevin Crowston, Mark Hansen, Jeffrey V Nickerson, and Lydia B Chilton. 2023. ReelFramer: Co-creating News Reels on Social Media with Generative AI. arXiv preprint arXiv:2304.09653 (2023)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_2_57_1","volume-title":"Self-Instruct: Aligning Language Model with Self Generated Instructions. arXiv preprint arXiv:2212.10560","author":"Wang Yizhong","year":"2022","unstructured":"Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2022a. Self-Instruct: Aligning Language Model with Self Generated Instructions. arXiv preprint arXiv:2212.10560 (2022)."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.491"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.360"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20167"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.6"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.341"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10524"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.274"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.3115\/1119250.1119257"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.78"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.671"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.597"},{"key":"e_1_3_2_2_69_1","volume-title":"Zerogen: Efficient zero-shot learning via dataset generation. arXiv preprint arXiv:2202.07922","author":"Ye Jiacheng","year":"2022","unstructured":"Jiacheng Ye, Jiahui Gao, Qintong Li, Hang Xu, Jiangtao Feng, Zhiyong Wu, Tao Yu, and Lingpeng Kong. 2022. Zerogen: Efficient zero-shot learning via dataset generation. arXiv preprint arXiv:2202.07922 (2022)."},{"key":"e_1_3_2_2_70_1","volume-title":"Han Zhang, Ruoming Pang, James Qin, Alexander Ku, Yuanzhong Xu, Jason Baldridge, and Yonghui Wu.","author":"Yu Jiahui","year":"2021","unstructured":"Jiahui Yu, Xin Li, Jing Yu Koh, Han Zhang, Ruoming Pang, James Qin, Alexander Ku, Yuanzhong Xu, Jason Baldridge, and Yonghui Wu. 2021. Vector-quantized image modeling with improved VQGAN. arXiv preprint arXiv:2110.04627 (2021)."},{"key":"e_1_3_2_2_71_1","volume-title":"Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, et al.","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Yuanzhong Xu, Jing Yu Koh, Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, et al. 2022. Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 (2022)."},{"key":"e_1_3_2_2_72_1","volume-title":"Text-to-image Diffusion Model in Generative AI: A Survey. arXiv preprint arXiv:2303.07909","author":"Zhang Chenshuang","year":"2023","unstructured":"Chenshuang Zhang, Chaoning Zhang, Mengchun Zhang, and In So Kweon. 2023. Text-to-image Diffusion Model in Generative AI: A Survey. arXiv preprint arXiv:2303.07909 (2023)."},{"key":"e_1_3_2_2_73_1","volume-title":"Event extraction with generative adversarial imitation learning. arXiv preprint arXiv:1804.07881","author":"Zhang Tongtao","year":"2018","unstructured":"Tongtao Zhang and Heng Ji. 2018. Event extraction with generative adversarial imitation learning. arXiv preprint arXiv:1804.07881 (2018)."},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123294"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17720"},{"key":"e_1_3_2_2_76_1","volume-title":"Miguel Eckstein, and William Yang Wang.","author":"Zhu Wanrong","year":"2022","unstructured":"Wanrong Zhu, An Yan, Yujie Lu, Wenda Xu, Xin Eric Wang, Miguel Eckstein, and William Yang Wang. 2022. Visualize Before You Write: Imagination-Guided Open-Ended Text Generation. arXiv preprint arXiv:2210.03765 (2022)."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612526","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:55:41Z","timestamp":1755820541000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612526"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":76,"alternative-id":["10.1145\/3581783.3612526","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612526","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}