{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:41:56Z","timestamp":1765503716169,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761576","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:18:04Z","timestamp":1762561084000},"page":"5634-5641","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["When Words Can't Capture It All: Towards Video-Based User Complaint Text Generation with Multimodal Video Complaint Dataset"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6608-0400","authenticated-orcid":false,"given":"Sarmistha","family":"Das","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3572-2454","authenticated-orcid":false,"given":"R E Zera Marveen","family":"Lyngkhoi","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5392-9187","authenticated-orcid":false,"given":"Kirtan","family":"Jain","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0343-568X","authenticated-orcid":false,"given":"Vinayak","family":"Goyal","sequence":"additional","affiliation":[{"name":"Indian Institute Of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5458-9381","authenticated-orcid":false,"given":"Sriparna","family":"Saha","sequence":"additional","affiliation":[{"name":"Indian Institute Of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2843-3110","authenticated-orcid":false,"given":"Manish","family":"Gupta","sequence":"additional","affiliation":[{"name":"Microsoft India, Hyderabad, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joitmc.2024.100222"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5121\/ijcsit.2021.13302"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65-72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65-72."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0076540"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00699"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-33380-4_5"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3338357"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3338357"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681595"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0062427"},{"key":"e_1_3_2_1_11_1","unstructured":"Institute for Telecommunication Sciences. 2024. Video Quality Research Data. https:\/\/its.ntia.gov\/research\/qoe\/video-quality-research\/data Accessed: 2024-11-01."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","article-title":"A DECISION SUPPORT MODEL TO IMPROVE COMPLAINT HANDLING IN E-COMMERCE TO ENHANCE CUSTOMER TRUST","volume":"102","author":"YEHIA HELMY, MERNA","year":"2024","unstructured":"YEHIA HELMY, MERNA ASHRAF, and LAILA ABDELHAMID. 2024. A DECISION SUPPORT MODEL TO IMPROVE COMPLAINT HANDLING IN E-COMMERCE TO ENHANCE CUSTOMER TRUST. Journal of Theoretical and Applied Information Technology, Vol. 102, 11 (2024).","journal-title":"Journal of Theoretical and Applied Information Technology"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Yanrong Huang Zhiyi He Han Lv and Jian Min. 2024. Research on Mining Negative Online Reviews on E-commerce Platforms Based on Social Network Analysis and LDA Model. In Intelligent Management of Data and Information in Decision Making: Proceedings of the 16th FLINS Conference on Computational Intelligence in Decision and Control & the 19th ISKE Conference on Intelligence Systems and Knowledge Engineering (FLINS-ISKE 2024). World Scientific 177-185.","DOI":"10.1142\/9789811294631_0023"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v8i1.14550"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613776"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.2016299"},{"key":"e_1_3_2_1_18_1","volume-title":"Modeling the severity of complaints in social media. arXiv preprint arXiv:2103.12428","author":"Jin Mali","year":"2021","unstructured":"Mali Jin and Nikolaos Aletras. 2021. Modeling the severity of complaints in social media. arXiv preprint arXiv:2103.12428 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_20_1","unstructured":"Junnan Li Dongxu Li Silvio Savarese and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In ICML."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4512"},{"key":"e_1_3_2_1_22_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74-81. https:\/\/aclanthology.org\/W04-1013"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220427"},{"key":"e_1_3_2_1_24_1","volume-title":"Cma-clip: Cross-modality attention clip for image-text classification. arXiv preprint arXiv:2112.03562","author":"Liu Huidong","year":"2021","unstructured":"Huidong Liu, Shaoyuan Xu, Jinmiao Fu, Yang Liu, Ning Xie, Chien-Chih Wang, Bryan Wang, and Yi Sun. 2021. Cma-clip: Cross-modality attention clip for image-text classification. arXiv preprint arXiv:2112.03562 (2021)."},{"key":"e_1_3_2_1_25_1","volume-title":"Meld: A multimodal multi-party dataset for emotion recognition in conversations. arXiv preprint arXiv:1810.02508","author":"Poria Soujanya","year":"2018","unstructured":"Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Gautam Naik, Erik Cambria, and Rada Mihalcea. 2018. Meld: A multimodal multi-party dataset for emotion recognition in conversations. arXiv preprint arXiv:1810.02508 (2018)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1495"},{"key":"e_1_3_2_1_27_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_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.ecnlp-1.2"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.456"},{"key":"e_1_3_2_1_30_1","volume-title":"Ziya Ata Yazici, and Hazim Kemal Ekenel","author":"Sesver Duygu","year":"2022","unstructured":"Duygu Sesver, \u00c7a?ri Emre Yildiz, Zehra G\u00fcnindi, Faeze Habibi, Ziya Ata Yazici, and Hazim Kemal Ekenel. 2022. VIDI: A Video Dataset of Incidents. In 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP). IEEE, 1-5."},{"key":"e_1_3_2_1_31_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21476"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28238-6_9"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99736-6_29"},{"key":"e_1_3_2_1_35_1","volume-title":"https:\/\/goo.gle\/Gemma3Report","author":"Team Gemma","year":"2025","unstructured":"Gemma Team. 2025. Gemma 3. (2025). https:\/\/goo.gle\/Gemma3Report"},{"key":"e_1_3_2_1_36_1","volume-title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191","author":"Wang Peng","year":"2024","unstructured":"Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"Revista Argentina de Cl\u00ednica Psicol\u00f3gica","volume":"30","author":"Wassan Sobia","year":"2021","unstructured":"Sobia Wassan, Xi Chen, Tian Shen, Muhammad Waqar, and NZ Jhanjhi. 2021. Amazon product sentiment analysis using machine learning techniques. Revista Argentina de Cl\u00ednica Psicol\u00f3gica, Vol. 30, 1 (2021), 695."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"e_1_3_2_1_39_1","volume-title":"Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675","author":"Zhang Tianyi","year":"2019","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1053"},{"key":"e_1_3_2_1_41_1","unstructured":"Bin Zhu Bin Lin Munan Ning Yang Yan Jiaxi Cui HongFa Wang Yatian Pang Wenhao Jiang Junwu Zhang Zongwei Li et al. 2023. LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment. arXiv preprint arXiv:2310.01852 (2023)."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:39:09Z","timestamp":1765503549000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761576"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":41,"alternative-id":["10.1145\/3746252.3761576","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761576","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}