{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T12:29:47Z","timestamp":1771244987448,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569496","type":"print"},{"value":"9789819569502","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-6950-2_11","type":"book-chapter","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:59:02Z","timestamp":1771243142000},"page":"147-161","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Taming Image-Based Vision-Language Pre-training Model with\u00a0Bootstrapped Auxiliary Tasks for\u00a0Video Captioning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7045-3919","authenticated-orcid":false,"given":"Ziyu","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-4871","authenticated-orcid":false,"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"key":"11_CR1","unstructured":"Banerjee, S., Lavie, A.: 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, pp. 65\u201372 (2005)"},{"key":"11_CR2","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 190\u2013200 (2011)"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"11_CR4","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1109\/TIP.2021.3120867","volume":"31","author":"L Gao","year":"2021","unstructured":"Gao, L., Lei, Y., Zeng, P., Song, J., Wang, M., Shen, H.T.: Hierarchical representation network with auxiliary tasks for video captioning and video question answering. IEEE Trans. Image Process. 31, 202\u2013215 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Han, T., Xu, Y., Yu, J., Yu, Z., Zhao, S.: Action-driven semantic representation and aggregation for video captioning. IEEE Trans. Circ. Syst. Video Technol. (2024)","DOI":"10.1109\/TCSVT.2024.3502736"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Hanna-Asaad, A., Aspandi, D., Zaharia, T.: Multi-modal interpretable automatic video captioning. arXiv preprint arXiv:2411.06872 (2024)","DOI":"10.1109\/CBMI66578.2025.11339325"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"He, X., et al.: Vlab: enhancing video language pre-training by feature adapting and blending. IEEE Trans. Multimedia (2024)","DOI":"10.1109\/TMM.2024.3521729"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Kainulainen, J., Guo, Z., Laaksonen, J.: Diffusion-based multimodal video captioning. In: Proceedings of the Asian Conference on Computer Vision, pp. 2820\u20132837 (2024)","DOI":"10.1007\/978-981-96-0908-6_9"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Kim, B., Hwang, D., Cho, S., Jang, Y., Lee, H., Lee, M.: Show think and tell: thought-augmented fine-tuning of large language models for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1808\u20131817 (2024)","DOI":"10.1109\/CVPRW63382.2024.00187"},{"issue":"2","key":"11_CR10","doi-asserted-by":"publisher","first-page":"1049","DOI":"10.1109\/TPAMI.2023.3327677","volume":"46","author":"G Li","year":"2023","unstructured":"Li, G., et al.: Learning hierarchical modular networks for video captioning. IEEE Trans. Pattern Anal. Mach. Intell. 46(2), 1049\u20131064 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR11","doi-asserted-by":"publisher","first-page":"4389","DOI":"10.1109\/TMM.2023.3322329","volume":"26","author":"Y Liang","year":"2023","unstructured":"Liang, Y., Zhu, L., Wang, X., Yang, Y.: Icocap: improving video captioning by compounding images. IEEE Trans. Multimedia 26, 4389\u20134400 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"11_CR12","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out: Proceedings of the ACL-04 Workshop, pp. 74\u201381 (2004)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Lin, K., et al.: Swinbert: end-to-end transformers with sparse attention for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17949\u201317958 (2022)","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Liu, H., Wan, X.: Qavidcap: enhancing video captioning through question answering techniques. In: Proceedings of the 2024 International Conference on Multimedia Retrieval, pp. 155\u2013164 (2024)","DOI":"10.1145\/3652583.3658061"},{"key":"11_CR15","unstructured":"Luo, H., et al.: Univl: a unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Luo, H., Cai, X., Shark, L.K.: Frame-by-frame multi-object tracking-guided video captioning. IEEE Trans. Circ. Syst. Video Technol. (2025)","DOI":"10.1109\/TCSVT.2025.3541965"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Seo, P.H., Nagrani, A., Arnab, A., Schmid, C.: End-to-end generative pretraining for multimodal video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17959\u201317968 (2022)","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Sung, Y.L., Cho, J., Bansal, M.: VL-adapter: parameter-efficient transfer learning for vision-and-language tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5227\u20135237 (2022)","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Tang, M., Wang, Z., Liu, Z., Rao, F., Li, D., Li, X.: Clip4caption: clip for video caption. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 4858\u20134862 (2021)","DOI":"10.1145\/3474085.3479207"},{"key":"11_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107702","volume":"111","author":"Y Tu","year":"2021","unstructured":"Tu, Y., Zhou, C., Guo, J., Gao, S., Yu, Z.: Enhancing the alignment between target words and corresponding frames for video captioning. Pattern Recogn. 111, 107702 (2021)","journal-title":"Pattern Recogn."},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015, pp. 1494\u20131504 (2015)","DOI":"10.3115\/v1\/N15-1173"},{"key":"11_CR24","unstructured":"Wang, J., et al.: Git: a generative image-to-text transformer for vision and language. Trans. Mach. Learn. Res."},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y.F., Wang, W.Y.: Vatex: a large-scale, high-quality multilingual dataset for video-and-language research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4581\u20134591 (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"11_CR26","unstructured":"Xu, H., et al.: mplug-2: a modularized multi-modal foundation model across text, image and video. In: International Conference on Machine Learning, pp. 38728\u201338748 (2023)"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Ye, Q., et al.: Hitea: hierarchical temporal-aware video-language pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15405\u201315416 (2023)","DOI":"10.1109\/ICCV51070.2023.01413"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Yogish, D., Manjunath, T., Hegadi, R.S.: Review on natural language processing trends and techniques using NLTK. In: International Conference on Recent Trends in Image Processing and Pattern Recognition, pp. 589\u2013606 (2018)","DOI":"10.1007\/978-981-13-9187-3_53"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Object relational graph with teacher-recommended learning for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13278\u201313288 (2020)","DOI":"10.1109\/CVPR42600.2020.01329"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6950-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:59:08Z","timestamp":1771243148000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6950-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569496","9789819569502"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6950-2_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"17 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}