{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:39:19Z","timestamp":1786120759978,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818170","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-modal Fusion Transformer for Integrating Retrieved Knowledge into Video Caption Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9122-8665","authenticated-orcid":false,"given":"Karina","family":"Abubakirova","sequence":"first","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5191-9023","authenticated-orcid":false,"given":"Waseem","family":"Ullah","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7678-6949","authenticated-orcid":false,"given":"Latif U.","family":"Khan","sequence":"additional","affiliation":[{"name":"Abu Dhabi University, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8972-8094","authenticated-orcid":false,"given":"Mohsen","family":"Guizani","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.892"},{"key":"e_1_3_2_1_3_1","volume-title":"Natural Language Processing, with Python: Analyzing Text, with the Natural Language Toolkit","author":"Bird Steven","unstructured":"Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural Language Processing, with Python: Analyzing Text, with the Natural Language Toolkit. O'Reilly Media, Inc."},{"key":"e_1_3_2_1_4_1","first-page":"1877","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, Vol. V33. Curran Associates, Inc., 1877-1901."},{"key":"e_1_3_2_1_5_1","first-page":"1","article-title":"Scaling Instruction-Finetuned Language Models","volume":"25","author":"Chung Hyung Won","year":"2024","unstructured":"Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Alex Castro-Ros, Marie Pellat, Kevin Robinson, Dasha Valter, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, Andrew Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V. Le, and Jason Wei. 2024. Scaling Instruction-Finetuned Language Models. Journal of Machine Learning Research, V25, 70 (2024), 1-53.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01816"},{"key":"e_1_3_2_1_8_1","volume-title":"Squeeze-and-Excitation Networks. In Proceedings of the IEEE Conference, on Computer Vision, and Pattern Recognition. 7132-7141","author":"Hu Jie","year":"2018","unstructured":"Jie Hu, Li Shen, and Gang Sun. 2018. Squeeze-and-Excitation Networks. In Proceedings of the IEEE Conference, on Computer Vision, and Pattern Recognition. 7132-7141."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23125565"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01723"},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Learning Representations.","author":"Jaegle Andrew","year":"2022","unstructured":"Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding, Skanda Koppula, Daniel Zoran, Andrew Brock, Evan Shelhamer, Olivier J Henaff, Matthew Botvinick, Andrew Zisserman, Oriol Vinyals, and Joao Carreira. 2022. Perceiver IO: A General Architecture, for Structured Inputs, & Outputs. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 38th International Conference, on Machine Learning. PMLR, 4651-4664","author":"Jaegle Andrew","year":"2021","unstructured":"Andrew Jaegle, Felix Gimeno, Andy Brock, Oriol Vinyals, Andrew Zisserman, and Joao Carreira. 2021. Perceiver: General Perception, with Iterative Attention. In Proceedings of the 38th International Conference, on Machine Learning. PMLR, 4651-4664."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01318"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"e_1_3_2_1_16_1","first-page":"9459","volume-title":"Tasks. In Advances in Neural Information Processing Systems","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick 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 Advances in Neural Information Processing Systems, Vol. V33. Curran Associates, Inc., 9459-9474."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 40th International Conference, on Machine Learning. PMLR","author":"Li Junnan","year":"2023","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 Proceedings of the 40th International Conference, on Machine Learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_18_1","volume-title":"William Yang Wang","author":"Li Linjie","year":"2021","unstructured":"Linjie Li, Jie Lei, Zhe Gan, Licheng Yu, Yen-Chun Chen, Rohit Pillai, Yu Cheng, Luowei Zhou, Xin Eric Wang, William Yang Wang, Tamara Lee Berg, Mohit Bansal, Jingjing Liu, Lijuan Wang, and Zicheng Liu. 2021. VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation. In Advances in Neural Information Processing Systems, Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11192999"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.503"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00693"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"e_1_3_2_1_24_1","first-page":"14200","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Nagrani Arsha","year":"2021","unstructured":"Arsha Nagrani, Shan Yang, Anurag Arnab, Aren Jansen, Cordelia Schmid, and Chen Sun. 2021. Attention Bottlenecks, for Multimodal Fusion. In Advances in Neural Information Processing Systems, Vol. V34. Curran Associates, Inc., 14200-14213."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00724"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"e_1_3_2_1_27_1","volume-title":"V1, 8","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language Models, Are Unsupervised Multitask Learners. OpenAI blog, V1, 8 (2019), 9."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_29_1","first-page":"12786","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Ryoo Michael","year":"2021","unstructured":"Michael Ryoo, relax AJ Piergiovanni, Anurag Arnab, Mostafa Dehghani, and Anelia Angelova. 2021. TokenLearner: Adaptive Space-Time Tokenization, for Videos. In Advances in Neural Information Processing Systems, Vol. V34. Curran Associates, Inc., 12786-12797."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.188"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"e_1_3_2_1_32_1","volume-title":"V30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All, You Need. V30 (2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION59988.2024.10706514"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01284"},{"key":"e_1_3_2_1_36_1","unstructured":"Ori Yoran Tomer Wolfson Ori Ram and Jonathan Berant. 2024. Making Retrieval-Augmented Language Models Robust to Irrelevant Context. (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:18:25Z","timestamp":1786065505000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":38,"alternative-id":["10.1145\/3770855.3818170","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818170","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}