{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T04:19:45Z","timestamp":1778559585870,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62220106008, U20B2063, 62102070"],"award-info":[{"award-number":["62220106008, U20B2063, 62102070"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["2023NSFSC1392"],"award-info":[{"award-number":["2023NSFSC1392"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681593","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"2776-2785","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["MM-Forecast: A Multimodal Approach to Temporal Event Forecasting with Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1355-6256","authenticated-orcid":false,"given":"Haoxuan","family":"Li","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9919-3678","authenticated-orcid":false,"given":"Zhengmao","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3038-5389","authenticated-orcid":false,"given":"Yunshan","family":"Ma","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9714-8738","authenticated-orcid":false,"given":"Yi","family":"Bin","sequence":"additional","affiliation":[{"name":"Tongji University & National University of Singapore, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. In NeurIPS."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Daniel M Benjamin Fred Morstatter Ali E Abbas Andres Abeliuk Pavel Atanasov Stephen Bennett Andreas Beger Saurabh Birari David V Budescu Michele Catasta et al. 2023. Hybrid forecasting of geopolitical events. AI Magazine (2023).","DOI":"10.1002\/aaai.12085"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612427"},{"key":"e_1_3_2_1_4_1","volume-title":"A Comprehensive Evaluation of Large Language Models on Temporal Event Forecasting. arXiv preprint arXiv:2407.11638","author":"Chang He","year":"2024","unstructured":"He Chang, Chenchen Ye, Zhulin Tao, Jie Wu, Zhengmao Yang, Yunshan Ma, Xianglin Huang, and Tat-Seng Chua. 2024. A Comprehensive Evaluation of Large Language Models on Temporal Event Forecasting. arXiv preprint arXiv:2407.11638 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Xing","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03--30-vicuna\/"},{"key":"e_1_3_2_1_6_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, Vol. 24, 240 (2023), 1--113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_7_1","unstructured":"Songgaojun Deng Maarten de Rijke and Yue Ning. 2024. Advances in Human Event Modeling: From Graph Neural Networks to Language Models. (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Convolutional 2D Knowledge Graph Embeddings","author":"Dettmers Tim","year":"1811","unstructured":"Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, and Sebastian Riedel. 2018. Convolutional 2D Knowledge Graph Embeddings. In AAAI. AAAI Press, 1811--1818."},{"key":"e_1_3_2_1_9_1","volume-title":"QLoRA: Efficient Finetuning of Quantized LLMs. CoRR","author":"Dettmers Tim","year":"2023","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. QLoRA: Efficient Finetuning of Quantized LLMs. CoRR, Vol. abs\/2305.14314 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651232"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_12_1","volume-title":"Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118 (2021)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583295"},{"key":"e_1_3_2_1_14_1","volume-title":"ACL\/IJCNLP (1)","author":"Jin Woojeong","unstructured":"Woojeong Jin, Rahul Khanna, Suji Kim, Dong-Ho Lee, Fred Morstatter, Aram Galstyan, and Xiang Ren. 2021. ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data. In ACL\/IJCNLP (1). Association for Computational Linguistics, 4636--4650."},{"key":"e_1_3_2_1_15_1","volume-title":"EMNLP (1)","author":"Jin Woojeong","unstructured":"Woojeong Jin, Meng Qu, Xisen Jin, and Xiang Ren. 2020. Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs. In EMNLP (1). Association for Computational Linguistics, 6669--6683."},{"key":"e_1_3_2_1_16_1","volume-title":"Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning","author":"Lee Dong-Ho","unstructured":"Dong-Ho Lee, Kian Ahrabian, Woojeong Jin, Fred Morstatter, and Jay Pujara. 2023. Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning. In EMNLP. Association for Computational Linguistics, 544--557."},{"key":"e_1_3_2_1_17_1","unstructured":"Patrick S. H. Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel Sebastian Riedel and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In NeurIPS."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781638283379"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612101"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3389694"},{"key":"e_1_3_2_1_21_1","volume-title":"CLIP-Event: Connecting Text and Images with Event Structures","author":"Li Manling","unstructured":"Manling Li, Ruochen Xu, Shuohang Wang, Luowei Zhou, Xudong Lin, Chenguang Zhu, Michael Zeng, Heng Ji, and Shih-Fu Chang. 2022. CLIP-Event: Connecting Text and Images with Event Structures. In CVPR. IEEE, 16399--16408."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Zixuan Li Xiaolong Jin Wei Li Saiping Guan Jiafeng Guo Huawei Shen Yuanzhuo Wang and Xueqi Cheng. 2021. Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning. In SIGIR. ACM 408--417.","DOI":"10.1145\/3404835.3462963"},{"key":"e_1_3_2_1_23_1","volume-title":"Foundation Models for Time Series Analysis: A Tutorial and Survey. arXiv preprint arXiv:2403.14735","author":"Liang Yuxuan","year":"2024","unstructured":"Yuxuan Liang, Haomin Wen, Yuqi Nie, Yushan Jiang, Ming Jin, Dongjin Song, Shirui Pan, and Qingsong Wen. 2024. Foundation Models for Time Series Analysis: A Tutorial and Survey. arXiv preprint arXiv:2403.14735 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"GenTKG: Generative Forecasting on Temporal Knowledge Graph. CoRR","author":"Liao Ruotong","year":"2023","unstructured":"Ruotong Liao, Xu Jia, Yunpu Ma, and Volker Tresp. 2023. GenTKG: Generative Forecasting on Temporal Knowledge Graph. CoRR, Vol. abs\/2310.07793 (2023)."},{"key":"e_1_3_2_1_25_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2024. Visual instruction tuning. In NeurIPS."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"Jerry Liu. 2022. LlamaIndex. https:\/\/doi.org\/10.5281\/zenodo.1234","DOI":"10.5281\/zenodo.1234"},{"key":"e_1_3_2_1_27_1","volume-title":"Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completion. CoRR","author":"Luo Ruilin","year":"2024","unstructured":"Ruilin Luo, Tianle Gu, Haoling Li, Junzhe Li, Zicheng Lin, Jiayi Li, and Yujiu Yang. 2024. Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completion. CoRR, Vol. abs\/2401.06072 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.27"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Yunshan Ma Chenchen Ye Zijian Wu Xiang Wang Yixin Cao and Tat-Seng Chua. 2023. Context-aware Event Forecasting via Graph Disentanglement. In KDD. ACM 1643--1652.","DOI":"10.1145\/3580305.3599285"},{"key":"e_1_3_2_1_30_1","volume-title":"Complex and Time-complete Temporal Event Forecasting. CoRR","author":"Ma Yunshan","year":"2023","unstructured":"Yunshan Ma, Chenchen Ye, Zijian Wu, Xiang Wang, Yixin Cao, Liang Pang, and Tat-Seng Chua. 2023. Structured, Complex and Time-complete Temporal Event Forecasting. CoRR, Vol. abs\/2312.01052 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.7910\/DVN"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Namyong Park Fuchen Liu Purvanshi Mehta Dana Cristofor Christos Faloutsos and Yuxiao Dong. 2022. EvoKG: Jointly Modeling Event Time and Network Structure for Reasoning over Temporal Knowledge Graphs. In WSDM. ACM 794--803.","DOI":"10.1145\/3488560.3498451"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_35_1","volume-title":"ESWC (Lecture Notes in Computer Science","author":"Schlichtkrull Michael Sejr","unstructured":"Michael Sejr Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. 2018. Modeling Relational Data with Graph Convolutional Networks. In ESWC (Lecture Notes in Computer Science, Vol. 10843). Springer, 593--607."},{"key":"e_1_3_2_1_36_1","volume-title":"End-to-End Structure-Aware Convolutional Networks for Knowledge Base Completion","author":"Shang Chao","unstructured":"Chao Shang, Yun Tang, Jing Huang, Jinbo Bi, Xiaodong He, and Bowen Zhou. 2019. End-to-End Structure-Aware Convolutional Networks for Knowledge Base Completion. In AAAI. AAAI Press, 3060--3067."},{"key":"e_1_3_2_1_37_1","volume-title":"Think-on-Graph: Deep and Responsible Reasoning of Large Language Model with Knowledge Graph. CoRR","author":"Sun Jiashuo","year":"2023","unstructured":"Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Heung-Yeung Shum, and Jian Guo. 2023. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model with Knowledge Graph. CoRR, Vol. abs\/2307.07697 (2023)."},{"key":"e_1_3_2_1_38_1","unstructured":"Zhiqing Sun Zhi-Hong Deng Jian-Yun Nie and Jian Tang. 2019. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. In ICLR (Poster). OpenReview.net."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_40_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Image Enhanced Event Detection in News Articles","author":"Tong Meihan","unstructured":"Meihan Tong, Shuai Wang, Yixin Cao, Bin Xu, Juanzi Li, Lei Hou, and Tat-Seng Chua. 2020. Image Enhanced Event Detection in News Articles. In AAAI. AAAI Press, 9040--9047."},{"key":"e_1_3_2_1_42_1","volume-title":"LLaMA: Open and Efficient Foundation Language Models. CoRR","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aur\u00e9lien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. CoRR, Vol. abs\/2302.13971 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"TRAM: Benchmarking Temporal Reasoning for Large Language Models.","author":"Wang Yuqing","year":"2023","unstructured":"Yuqing Wang and Yun Zhao. 2023. TRAM: Benchmarking Temporal Reasoning for Large Language Models. (2023). arxiv: 2310.00835"},{"key":"e_1_3_2_1_44_1","volume-title":"ACL (Findings)","author":"Xu Wenjie","unstructured":"Wenjie Xu, Ben Liu, Miao Peng, Xu Jia, and Min Peng. 2023. Pre-trained Language Model with Prompts for Temporal Knowledge Graph Completion. In ACL (Findings). Association for Computational Linguistics, 7790--7803."},{"key":"e_1_3_2_1_45_1","unstructured":"Bishan Yang Wen-tau Yih Xiaodong He Jianfeng Gao and Li Deng. 2015. Embedding Entities and Relations for Learning and Inference in Knowledge Bases. In ICLR (Poster)."},{"key":"e_1_3_2_1_46_1","volume-title":"Yanqiao Zhu, and Wei Wang.","author":"Ye Chenchen","year":"2024","unstructured":"Chenchen Ye, Ziniu Hu, Yihe Deng, Zijie Huang, Mingyu Derek Ma, Yanqiao Zhu, and Wei Wang. 2024. MIRAI: Evaluating LLM Agents for Event Forecasting. arXiv preprint arXiv:2407.01231 (2024)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Michael Zhang and Eunsol Choi. 2021. SituatedQA: Incorporating Extra-Linguistic Contexts into QA. In EMNLP.","DOI":"10.18653\/v1\/2021.emnlp-main.586"},{"key":"e_1_3_2_1_48_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_49_1","volume-title":"Long Context Understanding. arXiv preprint arXiv:2406.02472","author":"Zhang Zhihan","year":"2024","unstructured":"Zhihan Zhang, Yixin Cao, Chenchen Ye, Yunshan Ma, Lizi Liao, and Tat-Seng Chua. 2024. Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding. arXiv preprint arXiv:2406.02472 (2024)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3444689"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","unstructured":"Ben Zhou Daniel Khashabi Qiang Ning and Dan Roth. 2019. 'Going on a vacation' takes longer than 'Going for a walk': A Study of Temporal Commonsense Understanding. In EMNLP. 3363--3369. https:\/\/doi.org\/10.18653\/v1\/D19--1332","DOI":"10.18653\/v1"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681593","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681593"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":51,"alternative-id":["10.1145\/3664647.3681593","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681593","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}