{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:31:37Z","timestamp":1763202697699,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031189067"},{"type":"electronic","value":"9783031189074"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-18907-4_29","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"368-381","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter"],"prefix":"10.1007","author":[{"given":"Bang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"29_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"29_CR2","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for MT evaluation with improved correlation with human judgments. In: ACL Workshop, pp. 65\u201372 (2005)"},{"key":"29_CR3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R.: Multitask learning. Mach. Learn. 28, 41\u201375 (1997)","journal-title":"Mach. Learn."},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Chen, S., Jiang, Y.G.: Motion guided region message passing for video captioning. In: ICCV, pp. 1543\u20131552 (2021)","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Chen, S., Chen, J., Jin, Q., Hauptmann, A.: Video captioning with guidance of multimodal latent topics. In: ACMMM, pp. 1838\u20131846 (2017)","DOI":"10.1145\/3123266.3123420"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Desai, K., Johnson, J.: Virtex: learning visual representations from textual annotations. In: CVPR, pp. 11162\u201311173 (2021)","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Zhu, X., Yao, P., Lu, S., Lu, H.: Normalized and geometry-aware self-attention network for image captioning. In: CVPR, pp. 10327\u201310336 (2020)","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and imagenet? In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Girshick, R., Doll\u00e1r, P.: Rethinking imagenet pre-training. In: ICCV, pp. 4918\u20134927 (2019)","DOI":"10.1109\/ICCV.2019.00502"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: ICASSP, pp. 131\u2013135. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"29_CR12","first-page":"4013","volume":"29","author":"Y Huang","year":"2020","unstructured":"Huang, Y., Chen, J., Ouyang, W., Wan, W., Xue, Y.: Image captioning with end-to-end attribute detection and subsequent attributes prediction. TIP 29, 4013\u20134026 (2020)","journal-title":"TIP"},{"key":"29_CR13","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: ICML, vol. 139, pp. 5583\u20135594 (2021)"},{"key":"29_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Li, L., Gong, B.: End-to-end video captioning with multitask reinforcement learning. In: WACV, pp. 339\u2013348. IEEE (2019)","DOI":"10.1109\/WACV.2019.00042"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, Y.C., Cheng, Y., Gan, Z., Yu, L., Liu, J.: Hero: hierarchical encoder for video+ language omni-representation pre-training. In: EMNLP, pp. 2046\u20132065 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"29_CR17","doi-asserted-by":"publisher","first-page":"31751","DOI":"10.1109\/ACCESS.2022.3160451","volume":"10","author":"S Li","year":"2022","unstructured":"Li, S., Yang, B., Zou, Y.: Adaptive curriculum learning for video captioning. IEEE Access 10, 31751\u201331759 (2022)","journal-title":"IEEE Access"},{"key":"29_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"29_CR19","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: ACL Workshop, pp. 74\u201381 (2004)"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Lin, K., Gan, Z., Wang, L.: Augmented partial mutual learning with frame masking for video captioning. In: AAAI, vol. 35, pp. 2047\u20132055 (2021)","DOI":"10.1609\/aaai.v35i3.16301"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Liu, F., Ren, X., Wu, X., Yang, B., Ge, S., Sun, X.: O2na: an object-oriented non-autoregressive approach for controllable video captioning. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 281\u2013292 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.24"},{"issue":"1","key":"29_CR22","first-page":"1","volume":"16","author":"F Liu","year":"2021","unstructured":"Liu, F., et al.: Dimbert: learning vision-language grounded representations with disentangled multimodal-attention. ACM Trans. Knowl. Disc. Data (TKDD) 16(1), 1\u201319 (2021)","journal-title":"ACM Trans. Knowl. Disc. Data (TKDD)"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Luo, H., et al.: Clip4clip: An empirical study of clip for end to end video clip retrieval. arXiv preprint arXiv:2104.08860 (2021)","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"29_CR24","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Pan, B., et al.: Spatio-temporal graph for video captioning with knowledge distillation. In: CVPR, pp. 10870\u201310879 (2020)","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Pasunuru, R., Bansal, M.: Multi-task video captioning with video and entailment generation. In: ACL, pp. 1273\u20131283 (2017)","DOI":"10.18653\/v1\/D17-1103"},{"key":"29_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, vol. 139, pp. 8748\u20138763 (2021)"},{"key":"29_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/978-3-030-58598-3_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"MB Sariyildiz","year":"2020","unstructured":"Sariyildiz, M.B., Perez, J., Larlus, D.: Learning visual representations with\u00a0caption annotations. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 153\u2013170. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_10"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"29_CR31","unstructured":"Shen, S., et al.: How much can clip benefit vision-and-language tasks? In: International Conference on Learning Representations (2021)"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: Videobert: a joint model for video and language representation learning. In: ICCV, pp. 7464\u20137473 (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"29_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: CVPR, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence-video to text. In: ICCV, pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"29_CR36","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: NAACL (2015)","DOI":"10.3115\/v1\/N15-1173"},{"key":"29_CR37","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: ICCV, pp. 4581\u20134591 (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"29_CR38","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: CVPR (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Yang, B., Zou, Y.: Visual oriented encoder: integrating multimodal and multi-scale contexts for video captioning. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 188\u2013195. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412315"},{"key":"29_CR40","doi-asserted-by":"crossref","unstructured":"Yang, B., Zou, Y., Liu, F., Zhang, C.: Non-autoregressive coarse-to-fine video captioning. In: AAAI, vol. 35, pp. 3119\u20133127 (2021)","DOI":"10.1609\/aaai.v35i4.16421"},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Yu, Y., Ko, H., Choi, J., Kim, G.: End-to-end concept word detection for video captioning, retrieval, and question answering. In: CVPR, pp. 3165\u20133173 (2017)","DOI":"10.1109\/CVPR.2017.347"},{"key":"29_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Open-book video captioning with retrieve-copy-generate network. In: CVPR, pp. 9837\u20139846 (2021)","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Object relational graph with teacher-recommended learning for video captioning. In: CVPR, pp. 13278\u201313288 (2020)","DOI":"10.1109\/CVPR42600.2020.01329"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18907-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:09:26Z","timestamp":1666825766000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18907-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189067","9783031189074"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18907-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"233","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.03","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.35","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}