{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:21:23Z","timestamp":1742912483894,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723469"},{"type":"electronic","value":"9783031723476"}],"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\/978-3-031-72347-6_2","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:02:55Z","timestamp":1726491775000},"page":"19-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BVRCC: Bootstrapping Video Retrieval via\u00a0Cross-Matching Correction"],"prefix":"10.1007","author":[{"given":"Luozheng","family":"Qin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoyao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqiang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Anne\u00a0Hendricks, L., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5803\u20135812 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"2_CR2","unstructured":"Bai, J., Bai, S., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"2_CR3","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"2_CR4","unstructured":"Brown, T., Mann, B., et\u00a0al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020)"},{"key":"2_CR5","unstructured":"Chen, D., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 190\u2013200 (2011)"},{"key":"2_CR6","unstructured":"Chen, J., Zhu, D., et\u00a0al.: MiniGPT-V2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)"},{"key":"2_CR7","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"2_CR8","doi-asserted-by":"publisher","unstructured":"Chun, S., Kim, W., Park, S., Chang, M., Oh, S.J.: ECCV caption: correcting false negatives by collecting machine-and-human-verified image-caption associations for MS-COCO. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13668, pp. 1\u201319. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20074-8_1","DOI":"10.1007\/978-3-031-20074-8_1"},{"key":"2_CR9","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"2_CR10","unstructured":"Desai, K., Kaul, G., Aysola, Z., Johnson, J.: RedCaps: web-curated image-text data created by the people, for the people. arXiv preprint arXiv:2111.11431 (2021)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Du, Z., et al.: GLM: general language model pretraining with autoregressive blank infilling. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, vol.\u00a01, pp. 320\u2013335 (2022)","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Elliott, D., Frank, S., Sima\u2019an, K., Specia, L.: Multi30K: multilingual English-German image descriptions. arXiv preprint arXiv:1605.00459 (2016)","DOI":"10.18653\/v1\/W16-3210"},{"key":"2_CR13","unstructured":"Fu, C., Chen, P., et\u00a0al.: MME: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394 (2023)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Ge, Y., et al.: Bridging video-text retrieval with multiple choice questions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16167\u201316176 (2022)","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Gorti, S.K., et al.: X-Pool: cross-modal language-video attention for text-video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5006\u20135015 (2022)","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Escorcia, V., Ghanem, B., Niebles, J.C.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Huang, S., Cao, Z., et\u00a0al.: Contrastive learning with high-quality and low-quality augmented data for query-focused summarization. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 11536\u201311540. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10447820"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"2_CR19","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"2_CR20","doi-asserted-by":"publisher","unstructured":"Liu, Y., Xiong, P., Xu, L., Cao, S., Jin, Q.: TS2-Net: token shift and selection transformer for text-video retrieval. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13674, pp. 319\u2013335. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19781-9_19","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"2_CR21","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., 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":"2_CR22","unstructured":"OpenAI, Achiam, J., Adler, S., et\u00a0al.: GPT-4 technical report (2023)"},{"key":"2_CR23","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems, vol. 35, pp. 27730\u201327744 (2022)"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Parekh, Z., Baldridge, J., Cer, D., Waters, A., Yang, Y.: Crisscrossed captions: extended intramodal and intermodal semantic similarity judgments for MS-COCO. arXiv preprint arXiv:2004.15020 (2020)","DOI":"10.18653\/v1\/2021.eacl-main.249"},{"key":"2_CR25","unstructured":"Rashtchian, C., Young, P., Hodosh, M., Hockenmaier, J.: Collecting image annotations using Amazon\u2019s Mechanical Turk. In: Proceedings of the NAACL HLT Workshop on Creating Speech and Language Data with Amazon\u2019s Mechanical Turk, pp. 139\u2013147 (2010)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133212 (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Shaoyao\u00a0Huang, L.Q., et\u00a0al.: Diffusion language model with query-document relevance for query-focused summarization. In: Findings of the ACL Conference on Empirical Methods in Natural Language Processing, pp. 11020\u201311030 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.735"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"2_CR29","unstructured":"Wang, Q., Zhang, Y., Zheng, Y., Pan, P., Hua, X.S.: Disentangled representation learning for text-video retrieval. arXiv preprint arXiv:2203.07111 (2022)"},{"key":"2_CR30","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":"2_CR31","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, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"2_CR32","unstructured":"Yan, X., Ai, C., Cao, Z., et\u00a0al.: Revising image-text retrieval via multi-modal entailment. arXiv preprint arXiv:2208.10126 (2022)"},{"key":"2_CR33","unstructured":"Ye, Q., et\u00a0al.: mPLUG-Owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"2_CR34","unstructured":"Yin, S., et al.: A survey on multimodal large language models. arXiv preprint arXiv:2306.13549 (2023)"},{"key":"2_CR35","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguistics 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"2_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/978-3-030-01234-2_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Yu","year":"2018","unstructured":"Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 487\u2013503. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_29"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, S., Zhu, L., Wang, X., Yang, Y.: CenterCLIP: token clustering for efficient text-video retrieval. In: Proceedings of the international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 970\u2013981 (2022)","DOI":"10.1145\/3477495.3531950"},{"key":"2_CR38","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72347-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:14:52Z","timestamp":1726492492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72347-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723469","9783031723476"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72347-6_2","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":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}