{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:16:04Z","timestamp":1783106164266,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533459","type":"print"},{"value":"9789819533466","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"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\/978-981-95-3346-6_11","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:50:15Z","timestamp":1763790615000},"page":"141-154","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["End-to-End VideoQA with\u00a0Frame Scoring Mechanisms and\u00a0Adaptive Sampling"],"prefix":"10.1007","author":[{"given":"Jianxin","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueqian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"issue":"5","key":"11_CR1","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.ipl.2005.11.003","volume":"97","author":"PS Efraimidis","year":"2006","unstructured":"Efraimidis, P.S., Spirakis, P.G.: Weighted random sampling with a reservoir. Inf. Process. Lett. 97(5), 181\u2013185 (2006)","journal-title":"Inf. Process. Lett."},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Gao, D., Zhou, L., Ji, L., Zhu, L., Yang, Y., Shou, M.Z.: Mist: multi-modal iterative spatial-temporal transformer for long-form video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14773\u201314783 (2023)","DOI":"10.1109\/CVPR52729.2023.01419"},{"issue":"2","key":"11_CR3","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1109\/TCSVT.2019.2890899","volume":"30","author":"C Huang","year":"2019","unstructured":"Huang, C., Wang, H.: A novel key-frames selection framework for comprehensive video summarization. IEEE Trans. Circuits Syst. Video Technol. 30(2), 577\u2013589 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Kim, H., Tang, Z., Bansal, M.: Dense-caption matching and frame-selection gating for temporal localization in VideoQA. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4812\u20134822 (2020)","DOI":"10.18653\/v1\/2020.acl-main.435"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Kim, S., Jeong, S., Kim, E., Kang, I., Kwak, N.: Self-supervised pre-training and contrastive representation learning for multiple-choice video QA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 13171\u201313179 (2021)","DOI":"10.1609\/aaai.v35i14.17556"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Ko, D., Lee, J., Kang, W.Y., Roh, B., Kim, H.: Large language models are temporal and causal reasoners for video question answering. In: The 2023 Conference on Empirical Methods in Natural Language Processing (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.261"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Lei, J., et al.: Less is more: ClipBERT for video-and-language learning via sparse sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering. arXiv preprint arXiv:1809.01696 (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"11_CR9","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":"11_CR10","doi-asserted-by":"crossref","unstructured":"Pan, J., et al.: Retrieving-to-answer: zero-shot video question answering with frozen large language models. arXiv preprint arXiv:2306.11732 (2023)","DOI":"10.1109\/ICCVW60793.2023.00035"},{"key":"11_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/978-3-030-68790-8_27","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"D Patel","year":"2021","unstructured":"Patel, D., Parikh, R., Shastri, Y.: Recent advances in video question answering: a review of datasets and methods. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12662, pp. 339\u2013356. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68790-8_27"},{"key":"11_CR12","unstructured":"Singh, A., Meetei, L.S., Singh, S.M., Singh, T.D., Bandyopadhyay, S.: An efficient keyframes selection based framework for video captioning. In: Proceedings of the 18th International Conference on Natural Language Processing (ICON), pp. 240\u2013250 (2021)"},{"key":"11_CR13","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.neucom.2018.11.038","volume":"331","author":"H Tang","year":"2019","unstructured":"Tang, H., Liu, H., Xiao, W., Sebe, N.: Fast and robust dynamic hand gesture recognition via key frames extraction and feature fusion. Neurocomputing 331, 424\u2013433 (2019)","journal-title":"Neurocomputing"},{"key":"11_CR14","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Wang, J., et\u00a0al.: All in one: exploring unified video-language pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6598\u20136608 (2023)","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"11_CR16","unstructured":"Wang, Y., et\u00a0al.: InternVideo: general video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191 (2022)"},{"key":"11_CR17","unstructured":"Wang, Y., Wang, Y., Wu, P., Liang, J., Zhao, D., Zheng, Z.: LSTP: language-guided spatial-temporal prompt learning for long-form video-text understanding. arXiv preprint arXiv:2402.16050 (2024)"},{"key":"11_CR18","unstructured":"Wu, B., Yu, S., Chen, Z., Tenenbaum, J.B., Gan, C.: Star: a benchmark for situated reasoning in real-world videos. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Xiao, J., Shang, X., Yao, A., Chua, T.S.: Next-QA: next phase of question-answering to explaining temporal actions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9777\u20139786 (2021)","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Xie, S.M., Ermon, S.: Reparameterizable subset sampling via continuous relaxations. arXiv preprint arXiv:1901.10517 (2019)","DOI":"10.24963\/ijcai.2019\/544"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Xu, D., et al.: Video question answering via gradually refined attention over appearance and motion. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1645\u20131653 (2017)","DOI":"10.1145\/3123266.3123427"},{"issue":"23","key":"11_CR22","doi-asserted-by":"publisher","first-page":"6941","DOI":"10.3390\/s20236941","volume":"20","author":"X Yan","year":"2020","unstructured":"Yan, X., Gilani, S.Z., Feng, M., Zhang, L., Qin, H., Mian, A.: Self-supervised learning to detect key frames in videos. Sensors 20(23), 6941 (2020)","journal-title":"Sensors"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: Just ask: learning to answer questions from millions of narrated videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1686\u20131697 (2021)","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Yang, Z., Garcia, N., Chu, C., Otani, M., Nakashima, Y., Takemura, H.: Bert representations for video question answering. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1556\u20131565 (2020)","DOI":"10.1109\/WACV45572.2020.9093596"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Ye, Q., et al.: HITEA: hierarchical temporal-aware video-language pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15405\u201315416 (2023)","DOI":"10.1109\/ICCV51070.2023.01413"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Yu, S., Cho, J., Yadav, P., Bansal, M.: Self-chained image-language model for video localization and question answering. arXiv preprint arXiv:2305.06988 (2023)","DOI":"10.52202\/075280-3354"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-llama: an instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Xiao, J., Ji, W., Li, Y., Deng, W., Chua, T.S.: Video question answering: datasets, algorithms and challenges. In: The 2022 Conference on Empirical Methods in Natural Language Processing (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.432"}],"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\/978-981-95-3346-6_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:24:01Z","timestamp":1783103041000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3346-6_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9789819533459","9789819533466"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3346-6_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"23 November 2025","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":"Urumqi","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":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}