{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T15:49:04Z","timestamp":1768232944033,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557394","type":"print"},{"value":"9789819557400","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5740-0_35","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:24:33Z","timestamp":1768220673000},"page":"508-521","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mask Time as\u00a0Language: Advancing Temporal Sentence Grounding in\u00a0Video via\u00a0Large Model Transfer"],"prefix":"10.1007","author":[{"given":"Lei","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzhu","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujiao","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijie","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"35_CR1","doi-asserted-by":"publisher","unstructured":"Chen, L., et al.: Rethinking the bottom-up framework for query-based video localization. Proc. AAAI Conf. Artif. Intell. 34(07), 10551\u201310558 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6627","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: UNITER: universal image-text representation learning. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"35_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"35_CR4","doi-asserted-by":"publisher","unstructured":"Ji, W., et al.: Are binary annotations sufficient? Video moment retrieval via hierarchical uncertainty-based active learning. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23013\u201323022 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02204","DOI":"10.1109\/CVPR52729.2023.02204"},{"issue":"3","key":"35_CR5","doi-asserted-by":"publisher","first-page":"1902","DOI":"10.1609\/aaai.v35i3.16285","volume":"35","author":"K Li","year":"2021","unstructured":"Li, K., Guo, D., Wang, M.: Proposal-free video grounding with contextual pyramid network. Proc. AAAI Conf. Artif. Intell. 35(3), 1902\u20131910 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i3.16285","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, S., Wu, Y., Chen, C.W., Shan, Y., Qie, X.: UMT: unified multi-modal transformers for joint video moment retrieval and highlight detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3042\u20133051 (2022)","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"35_CR7","doi-asserted-by":"publisher","unstructured":"Lu, C., Chen, L., Tan, C., Li, X., Xiao, J.: DEBUG: a dense bottom-up grounding approach for natural language video localization. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5144\u20135153. Association for Computational Linguistics, Hong Kong, China (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1518","DOI":"10.18653\/v1\/D19-1518"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Nan, G., et al.: Interventional video grounding with dual contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2765\u20132775 (2021)","DOI":"10.1109\/CVPR46437.2021.00279"},{"issue":"9","key":"35_CR9","doi-asserted-by":"publisher","first-page":"2434","DOI":"10.1109\/TMM.2019.2957854","volume":"22","author":"K Ning","year":"2020","unstructured":"Ning, K., Cai, M., Xie, D., Wu, F.: An attentive sequence to sequence translator for localizing video clips by natural language. IEEE Trans. Multimedia 22(9), 2434\u20132443 (2020). https:\/\/doi.org\/10.1109\/TMM.2019.2957854","journal-title":"IEEE Trans. Multimedia"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Shen, X., et al.: Semantics-enriched cross-modal alignment for complex-query video moment retrieval. In: Proceedings of the 31st ACM International Conference on Multimedia, MM \u201923, pp. 4109\u20134118. Association for Computing Machinery (2023)","DOI":"10.1145\/3581783.3613772"},{"key":"35_CR11","doi-asserted-by":"publisher","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7463\u20137472 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00756","DOI":"10.1109\/ICCV.2019.00756"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: 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 (2023)","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, L., Wu, T., Li, T., Wu, G.: Negative sample matters: a renaissance of metric learning for temporal grounding. In: AAAI, pp. 2613\u20132623. AAAI Press (2022)","DOI":"10.1609\/aaai.v36i3.20163"},{"issue":"07","key":"35_CR14","doi-asserted-by":"publisher","first-page":"12386","DOI":"10.1609\/aaai.v34i07.6924","volume":"34","author":"J Wu","year":"2020","unstructured":"Wu, J., Li, G., Liu, S., Lin, L.: Tree-structured policy based progressive reinforcement learning for temporally language grounding in video. Proc. AAAI Conf. Artif. Intell. 34(07), 12386\u201312393 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6924","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"35_CR15","doi-asserted-by":"publisher","unstructured":"Xiao, S., Chen, L., Shao, J., Zhuang, Y., Xiao, J.: Natural language video localization with learnable moment proposals. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Online and Punta Cana, Dominican Republic, pp. 4008\u20134017. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.327","DOI":"10.18653\/v1\/2021.emnlp-main.327"},{"key":"35_CR16","doi-asserted-by":"publisher","first-page":"5178","DOI":"10.1109\/TIP.2022.3191841","volume":"31","author":"Z Xu","year":"2022","unstructured":"Xu, Z., Chen, D., Wei, K., Deng, C., Xue, H.: HISA: hierarchically semantic associating for video temporal grounding. IEEE Trans. Image Process. 31, 5178\u20135188 (2022). https:\/\/doi.org\/10.1109\/TIP.2022.3191841","journal-title":"IEEE Trans. Image Process."},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Yang, A., et al.: Vid2Seq: large-scale pretraining of a visual language model for dense video captioning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"35_CR18","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). https:\/\/doi.org\/10.1109\/TIP.2022.3140611","journal-title":"IEEE Trans. Image Process."},{"issue":"5","key":"35_CR19","doi-asserted-by":"publisher","first-page":"2725","DOI":"10.1109\/TPAMI.2020.3038993","volume":"44","author":"Y Yuan","year":"2022","unstructured":"Yuan, Y., Ma, L., Wang, J., Liu, W., Zhu, W.: Semantic conditioned dynamic modulation for temporal sentence grounding in videos. IEEE Trans. Pattern Anal. Mach. Intell. 44(5), 2725\u20132741 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2020.3038993","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR20","doi-asserted-by":"publisher","unstructured":"Zeng, R., Xu, H., Huang, W., Chen, P., Tan, M., Gan, C.: Dense regression network for video grounding. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10284\u201310293 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01030","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"35_CR21","doi-asserted-by":"publisher","unstructured":"Zhang, H., Sun, A., Jing, W., Zhou, J.T.: Temporal sentence grounding in videos: a survey and future directions. IEEE Trans. Pattern Anal. Mach. Intell., 1\u201320 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3258628","DOI":"10.1109\/TPAMI.2023.3258628"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, S., Peng, H., Fu, J., Luo, J.: Learning 2D temporal adjacent networks for moment localization with natural language. In: The IEEE Conference on Computer Vision and Pattern Recognition (AAAI) (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"35_CR23","doi-asserted-by":"publisher","unstructured":"Zhu, L., Yang, Y.: ActBERT: learning global-local video-text representations. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8743\u20138752 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00877","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"35_CR24","unstructured":"Zhuang, L., Wayne, L., Ya, S., Jun, Z.: A robustly optimized BERT pre-training approach with post-training. In: Proceedings of the 20th Chinese National Conference on Computational Linguistics, pp. 1218\u20131227. Chinese Information Processing Society (2021)"}],"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\/978-981-95-5740-0_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:24:44Z","timestamp":1768220684000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5740-0_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557394","9789819557400"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5740-0_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 January 2026","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":"Shanghai","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}