{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T17:06:52Z","timestamp":1743095212986,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819756117"},{"type":"electronic","value":"9789819756124"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5612-4_34","type":"book-chapter","created":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T13:03:51Z","timestamp":1722344631000},"page":"396-407","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ST-CLIP: Spatio-Temporal Enhanced CLIP Towards Dense Video Captioning"],"prefix":"10.1007","author":[{"given":"Huimin","family":"Chen","sequence":"first","affiliation":[]},{"given":"Pengfei","family":"Duan","sequence":"additional","affiliation":[]},{"given":"Mingru","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Jingyi","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Shengwu","family":"Xiong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,31]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., et al.: Dense-captioning events in videos. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 706\u2013715. IEEE (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"34_CR2","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Rao, Y., Zhao, W., Chen, G., et al.: DenseCLIP: language-guided dense prediction with context-aware prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18082\u201318091 (2022)","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"34_CR4","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., Ji, L., Zhong, M., et al.: CLIP4Clip: an empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Yang, A., Nagrani, A., Seo, P.H., et al.: Vid2Seq: large-scale pretraining of a visual language model for dense video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10714\u201310726 (2023)","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"34_CR6","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference of Learning Representation. ICLR, Vienna (2021)"},{"key":"34_CR7","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: International Conference on Machine Learning, Vienna (2021)"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhang, R., Lu, Z., et al.: End-to-end dense video captioning with parallel decoding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6847\u20136857 (2021)","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"34_CR9","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30, pp. 6000\u20136010 (2017)"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., et al.: ViViT: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"34_CR11","doi-asserted-by":"publisher","unstructured":"Ni, B., Peng, H., Chen, M., et al.: Expanding language-image pretrained models for general video recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13664, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19772-7_1","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.: Towards automatic learning of procedures from web instructional videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Huang, G., Pang, B., Zhu, Z., et al.: Multimodal pretraining for dense video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 4117\u20134126. CVPRW, Seattle (2020)","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"34_CR14","unstructured":"Yang, A., Nagrani, A., Laptev, I., et al.: VidChapters-7M: video chapters at scale. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"issue":"1","key":"34_CR15","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"34_CR16","unstructured":"Zhu, W., Pang, B., Thapliyal, A.V., et al.: End-to-end dense video captioning as sequence generation. In: Proceedings of the 29th International Conference on Computational Linguistics. Korea, pp. 5651\u20135665 (2022)"},{"key":"34_CR17","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 (2005)"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"34_CR19","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1007\/978-3-030-58539-6_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Fujita","year":"2020","unstructured":"Fujita, S., Hirao, T., Kamigaito, H., Okumura, M., Nagata, M.: Soda: story oriented dense video captioning evaluation framework. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision \u2013 ECCV 2020. LNCS, vol. 12351, pp. 517\u2013531. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_31"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., et al.: HowTo100M: learning a text-video embedding by watching hundred million narrated video clips. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2630\u20132640 (2019)","DOI":"10.1109\/ICCV.2019.00272"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5612-4_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T02:47:49Z","timestamp":1732502869000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5612-4_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756117","9789819756124"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5612-4_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"31 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}