{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:38Z","timestamp":1750309538789,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["62106204"],"award-info":[{"award-number":["62106204"]}]},{"name":"the Frontier Cross Innovation Team Project of Southwest Jiaotong University","award":["YH1500112432297"],"award-info":[{"award-number":["YH1500112432297"]}]},{"name":"the Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education"},{"name":"the Natural Science Foundation of XinjiangUygur Autonomous","award":["2024D01A14"],"award-info":[{"award-number":["2024D01A14"]}]},{"name":"the Natural Science Foundation of Sichuan","award":["2025YFHZ0124"],"award-info":[{"award-number":["2025YFHZ0124"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,22]]},"DOI":"10.1145\/3696410.3714609","type":"proceedings-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T22:52:18Z","timestamp":1745362338000},"page":"625-636","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Damage Analysis via Bidirectional Multi-Task Cascaded Multimodal Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0488-8900","authenticated-orcid":false,"given":"Tao","family":"Liang","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China and Bytedance Inc., Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3201-9117","authenticated-orcid":false,"given":"Siying","family":"Wu","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3317-2103","authenticated-orcid":false,"given":"Junfeng","family":"Fang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5133-0320","authenticated-orcid":false,"given":"Guowu","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China and Kash Institute of Electronics And Information Industry, Kashi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5612-7818","authenticated-orcid":false,"given":"Wenya","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1640-0992","authenticated-orcid":false,"given":"Fengmao","family":"Lv","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"volume-title":"Multimodal Categorization of Crisis Events in Social Media","author":"Abavisani Mahdi","key":"e_1_3_2_1_1_1","unstructured":"Mahdi Abavisani, Liwei Wu, Shengli Hu, Joel R. Tetreault, and Alejandro Jaimes. 2020. Multimodal Categorization of Crisis Events in Social Media. In CVPR. Computer Vision Foundation \/ IEEE, 14667--14677."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Mansi Agarwal Maitree Leekha Ramit Sawhney and Rajiv Ratn Shah. 2020. Crisis-DIAS: Towards Multimodal Damage Analysis - Deployment Challenges and Assessment. In AAAI. 346--353.","DOI":"10.1609\/aaai.v34i01.5369"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5982-9"},{"volume-title":"CrisisMMD: Multimodal Twitter Datasets from Natural Disasters","author":"Alam Firoj","key":"e_1_3_2_1_4_1","unstructured":"Firoj Alam, Ferda Ofli, and Muhammad Imran. 2018. CrisisMMD: Multimodal Twitter Datasets from Natural Disasters. In ICWSM. AAAI Press, 465--473."},{"volume-title":"CrisisDPS: Crisis Data Processing Services","author":"Alam Firoj","key":"e_1_3_2_1_5_1","unstructured":"Firoj Alam, Ferda Ofli, and Muhammad Imran. 2019. CrisisDPS: Crisis Data Processing Services. In ISCRAM. ISCRAM Association."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Mohammad Arif Ul Alam. 2022. College Student Retention Risk Analysis from Educational Database Using Multi-Task Multi-Modal Neural Fusion. In AAAI. 12689--12697.","DOI":"10.1609\/aaai.v36i11.21545"},{"key":"e_1_3_2_1_7_1","volume-title":"Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities. CoRR abs\/2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities. CoRR abs\/2308.12966 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Mohammad Basit Bashir Alam Zubaida Fatima and Salman Shaikh. 2023. Natural Disaster Tweets Classification Using Multimodal Data. In EMNLP. 7584--7594.","DOI":"10.18653\/v1\/2023.emnlp-main.471"},{"key":"e_1_3_2_1_9_1","volume-title":"Yu","author":"Cao Yuwei","year":"2024","unstructured":"Yuwei Cao, Hao Peng, Zhengtao Yu, and Philip S. Yu. 2024. Hierarchical and Incremental Structural Entropy Minimization for Unsupervised Social Event Detection. In AAAI. AAAI Press, 8255--8264."},{"key":"e_1_3_2_1_10_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171--4186.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171--4186."},{"key":"e_1_3_2_1_11_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR."},{"key":"e_1_3_2_1_12_1","unstructured":"Junfeng Fang Zac Bi Ruipeng Wang Houcheng Jiang Yuan Gao Kun Wang An Zhang Jie Shi Xiang Wang and Tat-Seng Chua. 2024. Towards Neuron Attributions in Multi-Modal Large Language Models. In NeurIPS."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.13949"},{"key":"e_1_3_2_1_14_1","unstructured":"Ruidan He Wee Sun Lee Hwee Tou Ng and Daniel Dahlmeier. [n. d.]. An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis. In ACL. 504--515."},{"key":"e_1_3_2_1_15_1","unstructured":"Ahmed Hendawy Jan Peters and Carlo D'Eramo. 2024. Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts. In ICLR. OpenReview.net."},{"key":"e_1_3_2_1_16_1","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In ICLR. OpenReview.net."},{"key":"e_1_3_2_1_17_1","unstructured":"Xincheng Ju Dong Zhang Rong Xiao Junhui Li Shoushan Li Min Zhang and Guodong Zhou. 2021. Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection. In EMNLP. 4395--4405."},{"key":"e_1_3_2_1_18_1","volume-title":"Marina Meila and Tong Zhang (Eds.)","volume":"139","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. In ICML, Marina Meila and Tong Zhang (Eds.), Vol. 139. 5583--5594."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Xin Li Lidong Bing Wai Lam and Bei Shi. 2018. Transformation Networks for Target-Oriented Sentiment Classification. In ACL. 946--956.","DOI":"10.18653\/v1\/P18-1087"},{"volume-title":"Localizing and Quantifying Damage in Social Media Images","author":"Li Xukun","key":"e_1_3_2_1_20_1","unstructured":"Xukun Li, Doina Caragea, Huaiyu Zhang, and Muhammad Imran. 2018. Localizing and Quantifying Damage in Social Media Images. In IEEE\/ACM. 194--201."},{"key":"e_1_3_2_1_21_1","first-page":"1","article-title":"Focusing Attention across Multiple Images for Multimodal Event Detection","volume":"74","author":"Li Yangyang","year":"2021","unstructured":"Yangyang Li, Jun Li, Hao Jin, and Liang Peng. 2021. Focusing Attention across Multiple Images for Multimodal Event Detection. In ACM MM. 74:1--74:6.","journal-title":"ACM MM."},{"volume-title":"Attention is not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion","author":"Liang Tao","key":"e_1_3_2_1_22_1","unstructured":"Tao Liang, Guosheng Lin, Lei Feng, Yan Zhang, and Fengmao Lv. 2021. Attention is not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion. In ICCV. IEEE, 8128--8136."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Tao Liang Guosheng Lin Mingyang Wan Tianrui Li Guojun Ma and Fengmao Lv. 2022. Expanding Large Pre-trained Unimodal Models with Multimodal Information Injection for Image-Text Multimodal Classification. In CVPR. 15471--15480.","DOI":"10.1109\/CVPR52688.2022.01505"},{"key":"e_1_3_2_1_24_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692 (2019)."},{"key":"e_1_3_2_1_25_1","volume-title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","author":"Liu Ze","year":"2021","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In ICCV. IEEE, 9992--10002."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Dehong Ma Sujian Li and Houfeng Wang. 2018. Joint Learning for Targeted Sentiment Analysis. In EMNLP Ellen Riloff David Chiang Julia Hockenmaier and Junichi Tsujii (Eds.). 4737--4742.","DOI":"10.18653\/v1\/D18-1504"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Krishanu Maity Prince Jha Sriparna Saha and Pushpak Bhattacharyya. 2022. A Multitask Framework for Sentiment Emotion and Sarcasm aware Cyberbullying Detection from Multi-modal Code-Mixed Memes. In SIGIR. 1739--1749.","DOI":"10.1145\/3477495.3531925"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Bishwas Mandal Sarthak Khanal and Doina Caragea. 2024. Contrastive Learning for Multimodal Classification of Crisis related Tweets. In WWW. ACM 4555--4564.","DOI":"10.1145\/3589334.3648143"},{"volume-title":"A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis","author":"Mao Yue","key":"e_1_3_2_1_29_1","unstructured":"Yue Mao, Yi Shen, Chao Yu, and Longjun Cai. 2021. A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis. In AAAI. AAAI Press, 13543--13551."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2024.102654"},{"key":"e_1_3_2_1_31_1","volume-title":"Nowak","author":"Mukherjee Subhojyoti","year":"2023","unstructured":"Subhojyoti Mukherjee, Qiaomin Xie, Josiah Hanna, and Robert D. Nowak. 2023. Multi-task Representation Learning for Pure Exploration in Bilinear Bandits. In NeurIPS."},{"key":"e_1_3_2_1_32_1","volume-title":"Fakeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detection","author":"Nakamura Kai","year":"2020","unstructured":"Kai Nakamura, Sharon Levy, and William Yang Wang. 2020. Fakeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detection. In LREC. European Language Resources Association, 6149--6157."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Ganesh Nalluru Rahul Pandey and Hemant Purohit. 2019. Relevancy Classification of Multimodal Social Media Streams for Emergency Services. In SMARTCOMP. 121--125.","DOI":"10.1109\/SMARTCOMP.2019.00040"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3648141"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Marco Aurelio Deoldoto Paulino Yandre M. G. Costa and Val\u00e9ria Delisandra Feltrim. 2022. Evaluating multimodal strategies for multi-label movie genre classification. In IWSSIP. 1--4.","DOI":"10.1109\/IWSSIP55020.2022.9854451"},{"key":"e_1_3_2_1_36_1","volume-title":"A Novel Energy Based Model Mechanism for Multi-Modal Aspect-Based Sentiment Analysis","author":"Peng Tianshuo","year":"1886","unstructured":"Tianshuo Peng, Zuchao Li, Ping Wang, Lefei Zhang, and Hai Zhao. 2024. A Novel Energy Based Model Mechanism for Multi-Modal Aspect-Based Sentiment Analysis. In AAAI. AAAI Press, 18869--18878."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Georgios Petkos Symeon Papadopoulos and Yiannis Kompatsiaris. 2012. Social event detection using multimodal clustering and integrating supervisory signals. In ICMR. 23.","DOI":"10.1145\/2324796.2324825"},{"key":"e_1_3_2_1_38_1","unstructured":"Raj Pranesh. 2022. Exploring Multimodal Features and Fusion Strategies for Analyzing Disaster Tweets. In COLING. 62--68."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Zitai Qiu Congbo Ma Jia Wu and Jian Yang. 2024. An Efficient Automatic Meta-Path Selection for Social Event Detection via Hyperbolic Space. In WWW. ACM 2519--2529.","DOI":"10.1145\/3589334.3645526"},{"key":"e_1_3_2_1_40_1","volume-title":"ICML","volume":"139","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In ICML, Vol. 139. PMLR, 8748--8763."},{"key":"e_1_3_2_1_41_1","volume-title":"Deep Multitask Learning with Progressive Parameter Sharing","author":"Shi Haosen","year":"1986","unstructured":"Haosen Shi, Shen Ren, Tianwei Zhang, and Sinno Jialin Pan. 2023. Deep Multitask Learning with Progressive Parameter Sharing. In ICCV. IEEE, 19867--19878."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Madichetty Sreenivasulu and M. Sridevi. 2019. Detecting Informative Tweets during Disaster using Deep Neural Networks. In COMSNETS. 709--713.","DOI":"10.1109\/COMSNETS.2019.8711095"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Kevin Stowe Michael J. Paul Martha Palmer Leysia Palen and Ken Anderson. 2016. Identifying and Categorizing Disaster-Related Tweets. In EMNLP. 1--6.","DOI":"10.18653\/v1\/W16-6201"},{"key":"e_1_3_2_1_44_1","unstructured":"Weijie Su Xizhou Zhu Yue Cao Bin Li Lewei Lu Furu Wei and Jifeng Dai. 2020. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. In ICLR. OpenReview.net."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102260"},{"key":"e_1_3_2_1_46_1","volume-title":"Luu Anh Tuan, and Siu Cheung Hui","author":"Tay Yi","year":"2018","unstructured":"Yi Tay, Luu Anh Tuan, and Siu Cheung Hui. 2018. Learning to Attend via Word-Aspect Associative Fusion for Aspect-Based Sentiment Analysis. In AAAI. 5956--5963."},{"key":"e_1_3_2_1_47_1","volume-title":"CogVLM: Visual Expert for Pretrained Language Models. CoRR abs\/2311.03079","author":"Wang Weihan","year":"2023","unstructured":"Weihan Wang, Qingsong Lv, Wenmeng Yu, Wenyi Hong, Ji Qi, Yan Wang, Junhui Ji, Zhuoyi Yang, Lei Zhao, Xixuan Song, Jiazheng Xu, Bin Xu, Juanzi Li, Yuxiao Dong, Ming Ding, and Jie Tang. 2023. CogVLM: Visual Expert for Pretrained Language Models. CoRR abs\/2311.03079 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.102977"},{"key":"e_1_3_2_1_49_1","volume-title":"Le","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang, Zihang Dai, Yiming Yang, Jaime G. Carbonell, Ruslan Salakhutdinov, and Quoc V. Le. 2019. XLNet: Generalized Autoregressive Pretraining for Language Understanding. In NeurIPS. 5754--5764."},{"volume-title":"Learning Multi-Task Sparse Representation Based on Fisher Information","author":"Zhang Yayu","key":"e_1_3_2_1_50_1","unstructured":"Yayu Zhang, Yuhua Qian, Guoshuai Ma, Keyin Zheng, Guoqing Liu, and Qingfu Zhang. 2024. Learning Multi-Task Sparse Representation Based on Fisher Information. In AAAI. AAAI Press, 16899--16907."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Ru Zhou Wenya Guo Xumeng Liu Shenglong Yu Ying Zhang and Xiaojie Yuan. 2023. AoM: Detecting Aspect-oriented Information for Multimodal Aspect-Based Sentiment Analysis. In ACL. 8184--8196.","DOI":"10.18653\/v1\/2023.findings-acl.519"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi10100636"}],"event":{"name":"WWW '25: The ACM Web Conference 2025","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Sydney NSW Australia","acronym":"WWW '25"},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714609","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:34Z","timestamp":1750295914000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":53,"alternative-id":["10.1145\/3696410.3714609","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714609","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}