{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:56:30Z","timestamp":1781538990235,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100019491","name":"National Natural Science Foundation of China - State Grid Corporation Joint Fund for Smart Grid","doi-asserted-by":"publisher","award":["Grant No. 62372060"],"award-info":[{"award-number":["Grant No. 62372060"]}],"id":[{"id":"10.13039\/501100019491","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BUPT Innovation and Entrepreneurship Support Program","award":["2025-YC-T013"],"award-info":[{"award-number":["2025-YC-T013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810702","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1317-1326","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DenseSpeech: Dense Multi-Segment Temporal Grounding in Public Speaking Videos"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1059-7037","authenticated-orcid":false,"given":"Jiachen","family":"Tan","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8182-6346","authenticated-orcid":false,"given":"Tingting","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2148-8473","authenticated-orcid":false,"given":"Tao","family":"Zhou","sequence":"additional","affiliation":[{"name":"China Unicom Software Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3206-0651","authenticated-orcid":false,"given":"Guangyao","family":"Su","sequence":"additional","affiliation":[{"name":"China Unicom Software Research Institute, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7082-3356","authenticated-orcid":false,"given":"Jianwei","family":"Fang","sequence":"additional","affiliation":[{"name":"China Unicom Software Research Institute, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7112-126X","authenticated-orcid":false,"given":"Bin","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0407-2381","authenticated-orcid":false,"given":"Chunping","family":"Zheng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16175"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612504"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32214"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Jianfeng Dong Xiaoman Peng Daizong Liu Xiaoye Qu Xun Yang Cuizhu Bao and Meng Wang. 2024. Temporal sentence grounding with relevance feedback in videos. Advances in Neural Information Processing Systems 37 (2024) 43107\u201343132.","DOI":"10.52202\/079017-1365"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Jianxiang Dong and Zhaozheng Yin. 2025. Graph-based Dense Event Grounding with relative positional encoding. Comput. Vis. Image Underst. 251 (2025) 104257.","DOI":"10.1016\/j.cviu.2024.104257"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01735"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00250"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.360"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02241"},{"key":"e_1_3_3_1_19_2","volume-title":"The art of public speaking","author":"Lucas Stephen","year":"2004","unstructured":"Stephen Lucas and Paul Stob. 2004. The art of public speaking. McGraw-Hill New York."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"e_1_3_3_1_21_2","unstructured":"Sherwyn Morreale. 1990. \" The Competent Speaker\": Development of a Communication-Competency Based Speech Evaluation Form and Manual. (1990)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Sherwyn Morreale Lawrence Hugenberg and David Worley. 2006. The basic communication course at US colleges and universities in the 21st century: Study VII. Communication Education 55 4 (2006) 415\u2013437.","DOI":"10.1080\/03634520600879162"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00191"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Michaela Regneri Marcus Rohrbach Dominikus Wetzel Stefan Thater Bernt Schiele and Manfred Pinkal. 2013. Grounding action descriptions in videos. Transactions of the Association for Computational Linguistics 1 (2013) 25\u201336.","DOI":"10.1162\/tacl_a_00207"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Fengyuan Shi Weilin Huang and Limin Wang. 2024. End-to-end dense video grounding via parallel regression. Computer Vision and Image Understanding 242 (2024) 103980.","DOI":"10.1016\/j.cviu.2024.103980"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01819"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Stephanie Thomson and Mary\u00a0L Rucker. 2002. The development of a specialized public speaking competency scale: Test of reliability. Communication Research Reports 19 1 (2002) 18\u201328.","DOI":"10.1080\/08824090209384828"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/216"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.69"},{"key":"e_1_3_3_1_32_2","unstructured":"Hao Zhang Aixin Sun Wei Jing and Joey\u00a0Tianyi Zhou. 2020. Span-based localizing network for natural language video localization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2004.13931 (2020)."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33185"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:28:37Z","timestamp":1781537317000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810702"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":32,"alternative-id":["10.1145\/3805622.3810702","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810702","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}