{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:22:25Z","timestamp":1771953745415,"version":"3.50.1"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031262838","type":"print"},{"value":"9783031262845","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26284-5_34","type":"book-chapter","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T08:02:59Z","timestamp":1677052979000},"page":"560-576","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-modal Segment Assemblage Network for\u00a0Ad Video Editing with\u00a0Importance-Coherence Reward"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2796-1787","authenticated-orcid":false,"given":"Yunlong","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9934-7917","authenticated-orcid":false,"given":"Siting","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinglin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1701-9141","authenticated-orcid":false,"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,23]]},"reference":[{"key":"34_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Brown, A., Zisserman, A.: Condensed movies: story based retrieval with contextual embeddings. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69541-5_28"},{"key":"34_CR3","unstructured":"Bello, I., Pham, H., Le, Q.V., Norouzi, M., Bengio, S.: Neural combinatorial optimization with reinforcement learning. arXiv preprint arXiv:1611.09940 (2016)"},{"key":"34_CR4","unstructured":"Cai, D., Zhang, Y., Huang, Y., Lam, W., Dolan, B.: Narrative incoherence detection. arXiv preprint arXiv:2012.11157 (2020)"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"34_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1007\/978-3-319-93031-2_12","volume-title":"Integration of Constraint Programming, Artificial Intelligence, and Operations Research","author":"M Deudon","year":"2018","unstructured":"Deudon, M., Cournut, P., Lacoste, A., Adulyasak, Y., Rousseau, L.-M.: Learning heuristics for the TSP by policy gradient. In: van Hoeve, W.-J. (ed.) CPAIOR 2018. LNCS, vol. 10848, pp. 170\u2013181. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-93031-2_12"},{"key":"34_CR7","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":"34_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/978-3-030-21074-8_4","volume-title":"Computer Vision \u2013 ACCV 2018 Workshops","author":"J Fajtl","year":"2019","unstructured":"Fajtl, J., Sokeh, H.S., Argyriou, V., Monekosso, D., Remagnino, P.: Summarizing videos with attention. In: Carneiro, G., You, S. (eds.) ACCV 2018. LNCS, vol. 11367, pp. 39\u201354. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-21074-8_4"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Feng, L., Li, Z., Kuang, Z., Zhang, W.: Extractive video summarizer with memory augmented neural networks. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 976\u2013983 (2018)","DOI":"10.1145\/3240508.3240651"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Fu, T.J., Tai, S.H., Chen, H.T.: Attentive and adversarial learning for video summarization. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1579\u20131587. IEEE (2019)","DOI":"10.1109\/WACV.2019.00173"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Ghauri, J.A., Hakimov, S., Ewerth, R.: Supervised video summarization via multiple feature sets with parallel attention. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136s. IEEE (2021)","DOI":"10.1109\/ICME51207.2021.9428318"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Gong, Y., et al.: Exact-K recommendation via maximal clique optimization. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 617\u2013626 (2019)","DOI":"10.1145\/3292500.3330832"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Guo, D., Zeng, Z.: Multi-modal representation learning for video advertisement content structuring. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 4770\u20134774 (2021)","DOI":"10.1145\/3474085.3479218"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 131\u2013135. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"34_CR15","unstructured":"Huang, Q., Xiong, Y., Xiong, Y., Zhang, Y., Lin, D.: From trailers to storylines: an efficient way to learn from movies. arXiv preprint arXiv:1806.05341 (2018)"},{"issue":"6","key":"34_CR16","doi-asserted-by":"publisher","first-page":"1709","DOI":"10.1109\/TCSVT.2019.2904996","volume":"30","author":"Z Ji","year":"2019","unstructured":"Ji, Z., Xiong, K., Pang, Y., Li, X.: Video summarization with attention-based encoder-decoder networks. IEEE Trans. Circuits Syst. Video Technol. 30(6), 1709\u20131717 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Kikuchi, Y., Neubig, G., Sasano, R., Takamura, H., Okumura, M.: Controlling output length in neural encoder-decoders. arXiv preprint arXiv:1609.09552 (2016)","DOI":"10.18653\/v1\/D16-1140"},{"key":"34_CR18","unstructured":"Kool, W., Van Hoof, H., Welling, M.: Attention, learn to solve routing problems! arXiv preprint arXiv:1803.08475 (2018)"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Koutras, P., Maragos, P.: SUSiNet: see, understand and summarize it. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00109"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Lin, Q., Pang, N., Hong, Z.: Automated multi-modal video editing for ads video. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 4823\u20134827 (2021)","DOI":"10.1145\/3474085.3479205"},{"key":"34_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/978-3-030-11018-5_19","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"R Lin","year":"2019","unstructured":"Lin, R., Xiao, J., Fan, J.: NeXtVLAD: an efficient neural network to aggregate frame-level features for large-scale video classification. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11132, pp. 206\u2013218. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11018-5_19"},{"key":"34_CR22","unstructured":"Liu, M., Zhang, W., Orabona, F., Yang, T.: Adam: a stochastic method with adaptive variance reduction. arXiv preprint arXiv:2011.11985 (2020)"},{"key":"34_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-030-69541-5_30","volume-title":"Computer Vision \u2013 ACCV 2020","author":"Y-T Liu","year":"2021","unstructured":"Liu, Y.-T., Li, Y.-J., Wang, Y.-C.F.: Transforming multi-concept attention into video summarization. In: Ishikawa, H., Liu, C.-L., Pajdla, T., Shi, J. (eds.) ACCV 2020. LNCS, vol. 12626, pp. 498\u2013513. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-69541-5_30"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"34_CR25","unstructured":"Merler, M., et al.: The excitement of sports: automatic highlights using audio\/visual cues. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2520\u20132523 (2018)"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Merler, M., et al.: Automatic curation of golf highlights using multimodal excitement features. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 57\u201365. IEEE (2017)","DOI":"10.1109\/CVPRW.2017.14"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Messaoud, S., et al.: DeepQAMVS: query-aware hierarchical pointer networks for multi-video summarization. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1389\u20131399 (2021)","DOI":"10.1145\/3404835.3462959"},{"key":"34_CR28","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"34_CR29","unstructured":"Nazari, M., Oroojlooy, A., Snyder, L.V., Tak\u00e1c, M.: Deep reinforcement learning for solving the vehicle routing problem. arXiv preprint arXiv:1802.04240 (2018)"},{"issue":"8","key":"34_CR30","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"34_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/978-3-030-58589-1_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Rochan","year":"2020","unstructured":"Rochan, M., Krishna Reddy, M.K., Ye, L., Wang, Y.: Adaptive video highlight detection by learning from user history. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 261\u2013278. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_16"},{"key":"34_CR32","unstructured":"Vinyals, O., Bengio, S., Kudlur, M.: Order matters: sequence to sequence for sets. arXiv preprint arXiv:1511.06391 (2015)"},{"key":"34_CR33","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Wang, J., Wang, W., Wang, Z., Wang, L., Feng, D., Tan, T.: Stacked memory network for video summarization. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 836\u2013844 (2019)","DOI":"10.1145\/3343031.3350992"},{"issue":"3","key":"34_CR35","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Xiong, B., Kalantidis, Y., Ghadiyaram, D., Grauman, K.: Less is more: learning highlight detection from video duration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1258\u20131267 (2019)","DOI":"10.1109\/CVPR.2019.00135"},{"key":"34_CR37","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Huang, Q., Guo, L., Zhou, H., Zhou, B., Lin, D.: A graph-based framework to bridge movies and synopses. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4592\u20134601 (2019)","DOI":"10.1109\/ICCV.2019.00469"},{"key":"34_CR38","doi-asserted-by":"crossref","unstructured":"Yang, H., Wang, B., Lin, S., Wipf, D., Guo, M., Guo, B.: Unsupervised extraction of video highlights via robust recurrent auto-encoders. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4633\u20134641 (2015)","DOI":"10.1109\/ICCV.2015.526"},{"key":"34_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-030-01237-3_24","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K Zhang","year":"2018","unstructured":"Zhang, K., Grauman, K., Sha, F.: Retrospective encoders for video summarization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 391\u2013408. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_24"},{"key":"34_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, K., Qiao, Y., Xiang, T.: Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12255"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26284-5_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T21:33:46Z","timestamp":1728941626000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26284-5_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031262838","9783031262845"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26284-5_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"23 February 2023","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":"Macao","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"277","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}