{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T06:21:24Z","timestamp":1743056484921,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":15,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819609079"},{"type":"electronic","value":"9789819609086"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-981-96-0908-6_25","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:25:32Z","timestamp":1733513132000},"page":"439-453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text Query to\u00a0Web Image to\u00a0Video: A Comprehensive Ad-Hoc Video Search"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4319-1265","authenticated-orcid":false,"given":"Nhat-Minh","family":"Nguyen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9556-484X","authenticated-orcid":false,"given":"Tien-Dung","family":"Mai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0356-5501","authenticated-orcid":false,"given":"Duy-Dinh","family":"Le","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"25_CR1","unstructured":"Fan, L., Krishnan, D., Isola, P., Katabi, D., Tian, Y.: Improving clip training with language rewrites. NeurIPS 36 (2024)"},{"key":"25_CR2","unstructured":"Galanopoulos, D., Mezaris, V.: Iti-certh participation in avs task of trecvid 2023. In: NIST (ed.) TRECVID 2023, International Workshop on Video Retrieval Evaluation (2023)"},{"key":"25_CR3","unstructured":"He, J., Li, R., Guo, J., Zhang, H., Li, M., Wu, Z., Wang, Z., Du, B., Liang, C.: Whu-nercms at trecvid 2023: Ad-hoc vedio search (avs) and deep video understanding (dvu) tasks. In: NIST (ed.) TRECVID 2023, International Workshop on Video Retrieval Evaluation (2023)"},{"key":"25_CR4","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML. pp. 19730\u201319742. PMLR (2023)"},{"key":"25_CR5","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML. pp. 12888\u201312900. PMLR (2022)"},{"key":"25_CR6","unstructured":"Li, X., Hu, F., Zhao, R., Wang, Z., Liu, J., Liu, J., Lan, B., Kou, W., Fu, Y., Kang, Z.: Renmin university of china and tencent at trecvid 2023: Harnessing pre-trained models for ad-hoc video search. In: NIST (ed.) TRECVID 2023, International Workshop on Video Retrieval Evaluation (2023)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Mu, N., Kirillov, A., Wagner, D., Xie, S.: Slip: Self-supervision meets language-image pre-training. In: ECCV. pp. 529\u2013544. Springer (2022)","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"25_CR8","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML. pp. 8748\u20138763. PMLR (2021)"},{"key":"25_CR9","unstructured":"Rossetto, L., Schoeffmann, K., Bernstein, A.: Insights on the v3c2 dataset. arXiv preprint arXiv:2105.01475 (2021)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Rossetto, L., Schuldt, H., Awad, G., Butt, A.A.: V3c \u2013 a research video collection. In: MultiMedia Modeling. pp. 349\u2013360 (2019)","DOI":"10.1007\/978-3-030-05710-7_29"},{"key":"25_CR11","unstructured":"Thuyen, T.D., Khiem, L., Thua, N., Tien, D., TruongAn, P., Tien-Dung, M., Duy-Dinh, L., Satoh, S.: Nii uit participation in avs and dvu tracks of trecvid 2023. In: NIST (ed.) TRECVID 2023, International Workshop on Video Retrieval Evaluation (2023)"},{"key":"25_CR12","unstructured":"Ueki, K., Suzuki, Y., Takushima, H., Okamoto, H., Tanoue, H., Hori, T.: Waseda meisei softbank at trecvid 2022. In: Proceedings of the TRECVid 2022 Workshop. pp.\u00a01\u20135 (2022)"},{"key":"25_CR13","unstructured":"Ueki, K., Suzuki, Y., Takushima, H., Sato, H., Takada, T., Okamoto, H., Tanoue, H., Hori, T., Kumar, A.M.: Waseda meisei softbank at trecvid 2023. In: Proceedings of the TRECVid 2023 Workshop (2023)"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Wang, W., Bao, H., Dong, L., Bjorck, J., Peng, Z., Liu, Q., Aggarwal, K., Mohammed, O.K., Singhal, S., Som, S., Wei, F.: Image as a foreign language: Beit pretraining for vision and vision-language tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 19175\u201319186 (June 2023)","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"25_CR15","unstructured":"Wu, J., Ma, Z., Zhong, S.H., Ngo, C.W.: Vireo @ trecvid 2023 ad-hoc video search. In: NIST (ed.) TRECVID 2023, International Workshop on Video Retrieval Evaluation (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0908-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:15:50Z","timestamp":1733516150000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0908-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819609079","9789819609086"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0908-6_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}