{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:52:24Z","timestamp":1777567944115,"version":"3.51.4"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726514","type":"print"},{"value":"9783031726521","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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\/978-3-031-72652-1_6","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:29:02Z","timestamp":1730190542000},"page":"92-107","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["TimeCraft:\u00a0Navigate Weakly-Supervised Temporal Grounded Video Question Answering via\u00a0Bi-directional Reasoning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9174-1696","authenticated-orcid":false,"given":"Huabin","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8307-7107","authenticated-orcid":false,"given":"Weiyao","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Buch, S., Eyzaguirre, C., Gaidon, A., Wu, J., Fei-Fei, L., Niebles, J.C.: Revisiting the \u201cvideo\u201d in video-language understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2917\u20132927 (2022)","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"6_CR2","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"6_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"6_CR4","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Fu, T.J., et al.: An empirical study of end-to-end video-language transformers with masked visual modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22898\u201322909 (2023)","DOI":"10.1109\/CVPR52729.2023.02193"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Gao, D., Wang, R., Bai, Z., Chen, X.: Env-QA: a video question answering benchmark for comprehensive understanding of dynamic environments. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1675\u20131685 (2021)","DOI":"10.1109\/ICCV48922.2021.00170"},{"key":"6_CR7","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"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Gao, M., Davis, L.S., Socher, R., Xiong, C.: WSLLN: weakly supervised natural language localization networks. arXiv preprint arXiv:1909.00239 (2019)","DOI":"10.18653\/v1\/D19-1157"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Grunde-McLaughlin, M., Krishna, R., Agrawala, M.: AGQA: a benchmark for compositional spatio-temporal reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11287\u201311297 (2021)","DOI":"10.1109\/CVPR46437.2021.01113"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Huang, J., Liu, Y., Gong, S., Jin, H.: Cross-sentence temporal and semantic relations in video activity localisation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7199\u20137208 (2021)","DOI":"10.1109\/ICCV48922.2021.00711"},{"key":"6_CR11","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.1007\/s11263-019-01189-x","volume":"127","author":"Y Jang","year":"2019","unstructured":"Jang, Y., Song, Y., Kim, C.D., Yu, Y., Kim, Y., Kim, G.: Video question answering with spatio-temporal reasoning. Int. J. Comput. Vis. 127, 1385\u20131412 (2019)","journal-title":"Int. J. Comput. Vis."},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, J., Chen, Z., Lin, H., Zhao, X., Gao, Y.: Divide and conquer: question-guided spatio-temporal contextual attention for video question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11101\u201311108 (2020)","DOI":"10.1609\/aaai.v34i07.6766"},{"issue":"2s","key":"6_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3321505","volume":"15","author":"W Jin","year":"2019","unstructured":"Jin, W., Zhao, Z., Li, Y., Li, J., Xiao, J., Zhuang, Y.: Video question answering via knowledge-based progressive spatial-temporal attention network. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 15(2s), 1\u201322 (2019)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl. (TOMM)"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Berg, T.L., Bansal, M.: TVQA+: spatio-temporal grounding for video question answering. arXiv preprint arXiv:1904.11574 (2019)","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"6_CR15","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":"6_CR16","doi-asserted-by":"crossref","unstructured":"Lin, Z., Zhao, Z., Zhang, Z., Wang, Q., Liu, H.: Weakly-supervised video moment retrieval via semantic completion network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11539\u201311546 (2020)","DOI":"10.1609\/aaai.v34i07.6820"},{"key":"6_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-030-58604-1_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Ma","year":"2020","unstructured":"Ma, M., Yoon, S., Kim, J., Lee, Y., Kang, S., Yoo, C.D.: VLANet: video-language alignment network for weakly-supervised video moment retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XXVIII 16. LNCS, vol. 12373, pp. 156\u2013171. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_10"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Mithun, N.C., Paul, S., Roy-Chowdhury, A.K.: Weakly supervised video moment retrieval from text queries. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11592\u201311601 (2019)","DOI":"10.1109\/CVPR.2019.01186"},{"key":"6_CR19","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"6_CR20","unstructured":"Song, Y., Wang, J., Ma, L., Yu, Z., Yu, J.: Weakly-supervised multi-level attentional reconstruction network for grounding textual queries in videos. arXiv preprint arXiv:2003.07048 (2020)"},{"key":"6_CR21","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"6_CR22","unstructured":"InternLM Team: InternLM: a multilingual language model with progressively enhanced capabilities (2023). https:\/\/github.com\/InternLM\/InternLM"},{"key":"6_CR23","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"6_CR24","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":"6_CR25","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":"6_CR26","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":"6_CR27","doi-asserted-by":"crossref","unstructured":"Xiao, J., Yao, A., Li, Y., Chua, T.S.: Can i trust your answer? Visually grounded video question answering. arXiv preprint arXiv:2309.01327 (2023)","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"6_CR28","doi-asserted-by":"publisher","unstructured":"Xiao, J., Zhou, P., Chua, TS., Yan, S.: Video graph transformer for video question answering. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13696, pp. 39\u201358. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_3","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"6_CR29","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: Zero-shot video question answering via frozen bidirectional language models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 124\u2013141 (2022)"},{"key":"6_CR30","unstructured":"Yu, S., Cho, J., Yadav, P., Bansal, M.: Self-chained image-language model for video localization and question answering. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Zheng, M., Huang, Y., Chen, Q., Liu, Y.: Weakly supervised video moment localization with contrastive negative sample mining. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 3517\u20133525 (2022)","DOI":"10.1609\/aaai.v36i3.20263"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72652-1_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:31:39Z","timestamp":1730190699000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72652-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031726514","9783031726521"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72652-1_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}