{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T08:30:29Z","timestamp":1765269029929,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","funder":[{"name":"Beijing Natural Science Foundation","award":["4244086"],"award-info":[{"award-number":["4244086"]}]},{"DOI":"10.13039\/501100006374","name":"Science Foundation of China University of Petroleum, Beijing","doi-asserted-by":"publisher","award":["2462023YJRC029"],"award-info":[{"award-number":["2462023YJRC029"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402526"],"award-info":[{"award-number":["62402526"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733347","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:29:43Z","timestamp":1750876183000},"page":"61-70","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["From Skeleton to Flesh: Aggregated Relational Transformer Towards Controllable Video Captioning with Two-Step Decoding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7491-5201","authenticated-orcid":false,"given":"Qianwen","family":"Cao","sequence":"first","affiliation":[{"name":"China University of Petroleum (Beijing), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0320-7520","authenticated-orcid":false,"given":"Heyan","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1948-5154","authenticated-orcid":false,"given":"Boran","family":"Wang","sequence":"additional","affiliation":[{"name":"Bytedance, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"e_1_3_2_1_2_1","volume-title":"Video captioning using transformer-based GAN. Multimedia Tools and Applications","author":"Babavalian Mohammad Reza","year":"2024","unstructured":"Mohammad Reza Babavalian and Kourosh Kiani. 2024. Video captioning using transformer-based GAN. Multimedia Tools and Applications (2024), 1--23."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL-2011)","author":"David","key":"e_1_3_2_1_4_1","unstructured":"David L. Chen and William B. Dolan. 2011. Collecting Highly Parallel Data for Paraphrase Evaluation. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL-2011). Portland, OR."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01657"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106813"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01816"},{"key":"e_1_3_2_1_12_1","volume-title":"Action-Driven Semantic Representation and Aggregation for Video Captioning","author":"Han Tingting","year":"2024","unstructured":"Tingting Han, Yaochen Xu, Jun Yu, Zhou Yu, and Sicheng Zhao. 2024. Action-Driven Semantic Representation and Aggregation for Video Captioning. IEEE Transactions on Circuits and Systems for Video Technology (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00544"},{"key":"e_1_3_2_1_15_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109134"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3648370"},{"key":"e_1_3_2_1_19_1","volume-title":"Scene Graph Parser. https:\/\/github.com\/vacancy\/SceneGraphParser","author":"Jiayuan Mao","year":"2018","unstructured":"Mao Jiayuan and Kasai Seito. 2018. Scene Graph Parser. https:\/\/github.com\/vacancy\/SceneGraphParser (2018)."},{"key":"e_1_3_2_1_20_1","first-page":"48955","article-title":"Miradata: A large-scale video dataset with long durations and structured captions","volume":"37","author":"Ju Xuan","year":"2025","unstructured":"Xuan Ju, Yiming Gao, Zhaoyang Zhang, Ziyang Yuan, Xintao Wang, Ailing Zeng, Yu Xiong, Qiang Xu, and Ying Shan. 2025. Miradata: A large-scale video dataset with long durations and structured captions. Advances in Neural Information Processing Systems, Vol. 37 (2025), 48955--48970.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00607-024-01334-6"},{"key":"e_1_3_2_1_22_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3638558"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02652"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"e_1_3_2_1_28_1","volume-title":"Evcap: Element-aware video captioning","author":"Liu Sheng","year":"2024","unstructured":"Sheng Liu, Annan Li, Yuwei Zhao, Jiahao Wang, and Yunhong Wang. 2024a. Evcap: Element-aware video captioning. IEEE Transactions on Circuits and Systems for Video Technology (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28178"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3541965"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109202"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.109662"},{"key":"e_1_3_2_1_35_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_36_1","volume-title":"Support-set bottlenecks for video-text representation learning. arXiv preprint arXiv:2010.02824","author":"Patrick Mandela","year":"2020","unstructured":"Mandela Patrick, Po-Yao Huang, Yuki Asano, Florian Metze, Alexander Hauptmann, Joao Henriques, and Andrea Vedaldi. 2020. Support-set bottlenecks for video-text representation learning. arXiv preprint arXiv:2010.02824 (2020)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-52417-z"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00559"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00186"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663976.3664004"},{"key":"e_1_3_2_1_44_1","volume-title":"Sequence to sequence learning with neural networks. Advances in neural information processing systems","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_47_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","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, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3254162"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3365104"},{"key":"e_1_3_2_1_51_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"e_1_3_2_1_54_1","first-page":"121475","article-title":"Cogvlm: Visual expert for pretrained language models","volume":"37","author":"Wang Weihan","year":"2025","unstructured":"Weihan Wang, Qingsong Lv, Wenmeng Yu, Wenyi Hong, Ji Qi, Yan Wang, Junhui Ji, Zhuoyi Yang, Lei Zhao, Song XiXuan, et al. 2025. Cogvlm: Visual expert for pretrained language models. Advances in Neural Information Processing Systems, Vol. 37 (2025), 121475--121499.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"e_1_3_2_1_56_1","volume-title":"End-to-End Transformer Based Model for Image Captioning. arXiv preprint arXiv:2203.15350","author":"Wang Yiyu","year":"2022","unstructured":"Yiyu Wang, Jungang Xu, and Yingfei Sun. 2022. End-to-End Transformer Based Model for Image Captioning. arXiv preprint arXiv:2203.15350 (2022)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_60_1","first-page":"40924","article-title":"Exploring diverse in-context configurations for image captioning","volume":"36","author":"Yang Xu","year":"2023","unstructured":"Xu Yang, Yongliang Wu, Mingzhuo Yang, Haokun Chen, and Xin Geng. 2023. Exploring diverse in-context configurations for image captioning. Advances in Neural Information Processing Systems, Vol. 36 (2023), 40924--40943.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680724"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00793"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3528216"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02713"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"ICMR '25"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:14:00Z","timestamp":1755749640000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":69,"alternative-id":["10.1145\/3731715.3733347","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733347","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}