{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:28:52Z","timestamp":1778081332581,"version":"3.51.4"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729911","type":"print"},{"value":"9783031729928","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\/978-3-031-72992-8_12","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:29:02Z","timestamp":1730190542000},"page":"200-216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-sentence Grounding for\u00a0Long-Term Instructional Video"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9721-8668","authenticated-orcid":false,"given":"Zeqian","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0330-1688","authenticated-orcid":false,"given":"Qirui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1874-9664","authenticated-orcid":false,"given":"Tengda","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5390-9053","authenticated-orcid":false,"given":"Ya","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3196-2347","authenticated-orcid":false,"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8609-6826","authenticated-orcid":false,"given":"Weidi","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"12_CR1","unstructured":"Abu-El-Haija, S., et al.: YouTube-8M: a large-scale video classification benchmark. arXiv preprint arXiv:1609.08675 (2016)"},{"key":"12_CR2","unstructured":"Afouras, T., Mavroudi, E., Nagarajan, T., Wang, H., Torresani, L.: HT-step: aligning instructional articles with how-to videos. In: NeurIPS (2023)"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Bain, M., Huh, J., Han, T., Zisserman, A.: WhisperX: time-accurate speech transcription of long-form audio. In: Conference of the International Speech Communication Association (2023)","DOI":"10.21437\/Interspeech.2023-78"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"12_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1007\/978-3-319-10602-1_41","volume-title":"Computer Vision \u2013 ECCV 2014","author":"P Bojanowski","year":"2014","unstructured":"Bojanowski, P., et al.: Weakly supervised action labeling in videos under ordering constraints. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 628\u2013643. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_41"},{"key":"12_CR6","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Caba\u00a0Heilbron, F., Escorcia, V., Ghanem, B., Carlos\u00a0Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Kukliansky, D., Szpektor, I., Chen, X., Ding, N., Soricut, R.: All you may need for VQA are image captions. arXiv preprint arXiv:2205.01883 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.142"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Chen, B., et\u00a0al.: Multimodal clustering networks for self-supervised learning from unlabeled videos. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00791"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Weakly-supervised temporal article grounding. In: EMNLP (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.639"},{"key":"12_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1007\/978-3-540-88693-8_12","volume-title":"Computer Vision \u2013 ECCV 2008","author":"T Cour","year":"2008","unstructured":"Cour, T., Jordan, C., Miltsakaki, E., Taskar, B.: Movie\/script: alignment and parsing of video and text transcription. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5305, pp. 158\u2013171. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88693-8_12"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Di, S., Xie, W.: Rounded question-answering in long egocentric videos. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01229"},{"key":"12_CR13","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":"12_CR14","doi-asserted-by":"crossref","unstructured":"Dvornik, N., Hadji, I., Zhang, R., Derpanis, K.G., Wildes, R.P., Jepson, A.D.: StepFormer: self-supervised step discovery and localization in instructional videos. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01817"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: TALL: temporal activity localization via language query. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Ghadiyaram, D., Tran, D., Mahajan, D.: Large-scale weakly-supervised pre-training for video action recognition. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01232"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Han, T., Xie, W., Zisserman, A.: Temporal alignment networks for long-term video. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00292"},{"key":"12_CR18","unstructured":"Koupaee, M., Wang, W.Y.: WikiHow: a large scale text summarization dataset. arXiv preprint arXiv:1810.09305 (2018)"},{"key":"12_CR19","unstructured":"Lei, J., Berg, T.L., Bansal, M.: Detecting moments and highlights in videos via natural language queries. In: NeurIPS (2021)"},{"key":"12_CR20","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":"12_CR21","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"12_CR22","unstructured":"Lin, K.Q., et\u00a0al.: Egocentric video-language pretraining. In: NeurIPS (2022)"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Lin, X., Petroni, F., Bertasius, G., Rohrbach, M., Chang, S.F., Torresani, L.: Learning to recognize procedural activities with distant supervision. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, X., Nie, L., Tian, Q., Chen, B., Chua, T.S.: Cross-modal moment localization in videos. In: ACM MM (2018)","DOI":"10.1145\/3240508.3240549"},{"key":"12_CR25","unstructured":"Liu, Y., Yao, J., Zhang, Y., Wang, Y., Xie, W.: Zero-shot composed text-image retrieval. arXiv preprint arXiv:2306.07272 (2023)"},{"key":"12_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"12_CR27","unstructured":"Luo, H., et al.: UniVL: a unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Mavroudi, E., Afouras, T., Torresani, L.: Learning to ground instructional articles in videos through narrations. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01395"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: HowTo100M: learning a text-video embedding by watching hundred million narrated video clips. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"12_CR31","unstructured":"Neelakantan, A., et\u00a0al.: Text and code embeddings by contrastive pre-training. arXiv preprint arXiv:2201.10005 (2022)"},{"key":"12_CR32","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Pramod\u00a0Sankar, K., Jawahar, C., Zisserman, A.: Subtitle-free movie to script alignment. In: BMVC (2009)","DOI":"10.5244\/C.23.121"},{"key":"12_CR34","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"12_CR35","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: ICML (2023)"},{"key":"12_CR36","unstructured":"Radford, A., et\u00a0al.: Language models are unsupervised multitask learners. OpenAI blog (2019)"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Ramakrishnan, S.K., Al-Halah, Z., Grauman, K.: NaQ: leveraging narrations as queries to supervise episodic memory. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00647"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Shvetsova, N., Kukleva, A., Hong, X., Rupprecht, C., Schiele, B., Kuehne, H.: HowtoCaption: prompting LLMs to transform video annotations at scale. arXiv preprint arXiv:2310.04900 (2023)","DOI":"10.1007\/978-3-031-72992-8_1"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Sun, L., Xu, X., Wu, M., Xie, W.: A large-scale dataset for audio-language representation learning. arXiv preprint arXiv:2309.11500 (2023)","DOI":"10.1145\/3664647.3681472"},{"key":"12_CR40","unstructured":"Taori, R., et al.: Alpaca: a strong, replicable instruction-following model. Stanford Center for Research on Foundation Models (2023). https:\/\/crfmstanford.edu\/2023\/03\/13\/alpaca.html"},{"key":"12_CR41","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: VideoMAE V2: scaling video masked autoencoders with dual masking. arXiv preprint arXiv:2303.16727 (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"12_CR43","unstructured":"Wang, Y., et al.: InternVideo: general video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191 (2022)"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"12_CR45","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: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning (still) requires rethinking generalization. Commun. ACM (2021)","DOI":"10.1145\/3446776"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, D., Dai, X., Wang, X., Wang, Y.F., Davis, L.S.: MAN: moment alignment network for natural language moment retrieval via iterative graph adjustment. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00134"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Misra, I., Kr\u00e4henb\u00fchl, P., Girdhar, R.: Learning video representations from large language models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.: Towards automatic learning of procedures from web instructional videos. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Zhukov, D., Alayrac, J.B., Cinbis, R.G., Fouhey, D., Laptev, I., Sivic, J.: Cross-task weakly supervised learning from instructional videos. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00365"}],"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\/978-3-031-72992-8_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T12:04:40Z","timestamp":1732968280000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72992-8_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031729911","9783031729928"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72992-8_12","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"}}]}}