{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T15:51:09Z","timestamp":1763308269821,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794423"},{"type":"electronic","value":"9789819794430"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-9443-0_31","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:29:32Z","timestamp":1730392172000},"page":"353-364","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MQuA: Multi-level Query-Video Augmentation for\u00a0Multilingual Video Corpus Retrieval"],"prefix":"10.1007","author":[{"given":"Guyang","family":"Yu","sequence":"first","affiliation":[]},{"given":"Xiaoyang","family":"Bi","sequence":"additional","affiliation":[]},{"given":"Jielong","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Tianbai","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Zhiqiang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Miankuan","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Li, B., Weng, Y., Sun, B., Li, S.: Learning to locate visual answer in video corpus using question. In: 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2023, pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096391"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Li, S., Li, B., Sun, B., Weng, Y.: Towards visual-prompt temporal answer grounding in instructional video. IEEE Trans. Pattern Anal. Mach. Intell. 1\u201318 (2024)","DOI":"10.1109\/TPAMI.2024.3411045"},{"key":"31_CR3","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1109\/TIP.2022.3140611","volume":"31","author":"X Yang","year":"2022","unstructured":"Yang, X., Wang, S., Dong, J., Dong, J., Wang, M., Chua, T.-S.: Video moment retrieval with cross-modal neural architecture search. IEEE Trans. Image Process. 31, 1204\u20131216 (2022)","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"31_CR4","doi-asserted-by":"publisher","first-page":"5412","DOI":"10.1109\/TNNLS.2020.2967597","volume":"31","author":"X Xu","year":"2020","unstructured":"Xu, X., Wang, T., Yang, Y., Zuo, L., Shen, F., Shen, H.T.: Cross-modal attention with semantic consistence for image-text matching. IEEE Trans. Neural Netw. Learn. Syst. 31(12), 5412\u20135425 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"31_CR5","unstructured":"Tang, J., Wang, Z., Gong, Z., Yu, J., Wang, S., Yin, J.: Multi-grained query-guided set prediction network for grounded multimodal named entity recognition. arXiv preprint arXiv:2407.21033 (2024)"},{"key":"31_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/978-3-030-58589-1_27","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Lei","year":"2020","unstructured":"Lei, J., Yu, L., Berg, T.L., Bansal, M.: TVR: a large-scale dataset for video-subtitle moment retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 447\u2013463. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_27"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Video corpus moment retrieval with contrastive learning. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 685\u2013695 (2021)","DOI":"10.1145\/3404835.3462874"},{"key":"31_CR8","unstructured":"Zhang, B., et al.: A hierarchical multi-modal encoder for moment localization in video corpus. arXiv preprint arXiv:2011.09046 (2020)"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Hou, Z., Ngo, C.-W., Chan, W.K.: Conquer: contextual query-aware ranking for video corpus moment retrieval. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3900\u20133908 (2021)","DOI":"10.1145\/3474085.3475281"},{"key":"31_CR10","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/978-3-031-44699-3_21","volume-title":"NLPCC 2023","author":"B Li","year":"2023","unstructured":"Li, B., et al.: Overview of the NLPCC 2023 shared task: Chinese medical instructional video question answering. In: Liu, F., Duan, N., Xu, Q., Hong, Y. (eds.) NLPCC 2023. LNCS, vol. 14304, pp. 233\u2013242. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-44699-3_21"},{"key":"31_CR11","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"31_CR12","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"31_CR13","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract OCR engine. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol.\u00a02, pp. 629\u2013633. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Rubin, O., Herzig, J., Berant, J.: Learning to retrieve prompts for in-context learning. arXiv preprint arXiv:2112.08633 (2021)","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chen, A., Hu, F., Li, X.: Learn to understand negation in video retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 434\u2013443 (2022)","DOI":"10.1145\/3503161.3547968"},{"key":"31_CR19","unstructured":"He, P., Gao, J., Chen, W.: Debertav3: improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. arXiv, Computation and Language (2021)"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"31_CR21","unstructured":"Chorowski, J.K., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Weng, Y., Li, B.: Visual answer localization with cross-modal mutual knowledge transfer. In: 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2023, pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095026"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Chapelle, O., Metlzer, D., Zhang, Y., Grinspan, P.: Expected reciprocal rank for graded relevance. In: Proceedings of the 18th ACM Conference on Information and Knowledge Management, pp. 621\u2013630 (2009)","DOI":"10.1145\/1645953.1646033"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: Zero: memory optimizations toward training trillion parameter models. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020. IEEE Press (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"31_CR25","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"31_CR27","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/978-3-031-44699-3_19","volume-title":"NLPCC 2023","author":"N Lei","year":"2023","unstructured":"Lei, N., et al.: A two-stage Chinese medical video retrieval framework with LLM. In: Liu, F., Duan, N., Xu, Q., Hong, Y. (eds.) NLPCC 2023. LNCS, vol. 14304, pp. 211\u2013220. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-44699-3_19"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-9443-0_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T16:09:01Z","timestamp":1732982941000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9443-0_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794423","9789819794430"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9443-0_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","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":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}