{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:23:42Z","timestamp":1750220622172,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Electronics and Telecommunications Research Institute(ETRI) grant funded by the Korean government","award":["20ZH1200, The research of the basic media contents technologies"],"award-info":[{"award-number":["20ZH1200, The research of the basic media contents technologies"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3414396","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:26:53Z","timestamp":1602505613000},"page":"4506-4508","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Scene-segmented Video Information Annotation System V2.0"],"prefix":"10.1145","author":[{"given":"Alex","family":"Lee","sequence":"first","affiliation":[{"name":"ETRI, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang-Uk","family":"Kwak","sequence":"additional","affiliation":[{"name":"ETRI, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeong-Woo","family":"Son","sequence":"additional","affiliation":[{"name":"ETRI, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gyeong-June","family":"Hahm","sequence":"additional","affiliation":[{"name":"ETRI, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min-Ho","family":"Han","sequence":"additional","affiliation":[{"name":"ETRI, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sun-Joong","family":"Kim","sequence":"additional","affiliation":[{"name":"ETRI, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24670-1_36"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"M. Aydinlilar and A. Yazici. 2013. Semi-Automatic Semantic Video Annotation Tool. In Computer and Information Sciences III. 303--310.  M. Aydinlilar and A. Yazici. 2013. Semi-Automatic Semantic Video Annotation Tool. In Computer and Information Sciences III. 303--310.","DOI":"10.1007\/978-1-4471-4594-3_31"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2644872"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s001380100064"},{"volume-title":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval. 470--474","author":"Collyda C.","key":"e_1_3_2_2_5_1"},{"key":"e_1_3_2_2_6_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. CoRR Vol. abs\/1512.03385 (2015). http:\/\/arxiv.org\/abs\/1512.03385  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. CoRR Vol. abs\/1512.03385 (2015). http:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3241400"},{"volume-title":"Key Frame Extraction Based on Sub-Shot Segmentation and Entropy Computing. In 2009 Chinese Conference on Pattern Recognition. 1--5.","author":"Pan L.","key":"e_1_3_2_2_8_1"},{"volume-title":"Adversarial Inference for Multi-Sentence Video Description. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) .","year":"2019","author":"Park Jae Sung","key":"e_1_3_2_2_9_1"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.23919\/ICACT.2017.7890152"},{"key":"e_1_3_2_2_11_1","unstructured":"Joseph Redmon and Ali Farhadi. 2018. YOLOv3: An Incremental Improvement. arXiv (2018).  Joseph Redmon and Ali Farhadi. 2018. YOLOv3: An Incremental Improvement. arXiv (2018)."},{"key":"e_1_3_2_2_12_1","unstructured":"Anna Rohrbach Atousa Torabi Marcus Rohrbach Niket Tandon Christopher J. Pal Hugo Larochelle Aaron C. Courville and Bernt Schiele. 2016. Movie Description. CoRR Vol. abs\/1605.03705 (2016). arxiv: 1605.03705 http:\/\/arxiv.org\/abs\/1605.03705  Anna Rohrbach Atousa Torabi Marcus Rohrbach Niket Tandon Christopher J. Pal Hugo Larochelle Aaron C. Courville and Bernt Schiele. 2016. Movie Description. CoRR Vol. abs\/1605.03705 (2016). arxiv: 1605.03705 http:\/\/arxiv.org\/abs\/1605.03705"},{"volume-title":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval. 187--195","author":"Rotman D.","key":"e_1_3_2_2_13_1"},{"key":"e_1_3_2_2_14_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR Vol. abs\/1409.1556 (2014). http:\/\/arxiv.org\/abs\/1409.1556  Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR Vol. abs\/1409.1556 (2014). http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3084139"},{"volume-title":"Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. 4278--4284","author":"Szegedy C.","key":"e_1_3_2_2_16_1"},{"volume-title":"Proceedings of the 2015 IEEE International Conference on Computer Vision. 4489--4497","author":"Tran D.","key":"e_1_3_2_2_17_1"},{"volume-title":"CBAM: Convolutional Block Attention Module. CoRR","year":"2018","author":"Woo Sanghyun","key":"e_1_3_2_2_18_1"},{"key":"e_1_3_2_2_19_1","unstructured":"L. Zelnik-Manor and P. Perona. 2004. Self-Tuning Spectral Clustering. In Advances in Neural Information Processing Systems 17. 1601--1608.  L. Zelnik-Manor and P. Perona. 2004. Self-Tuning Spectral Clustering. In Advances in Neural Information Processing Systems 17. 1601--1608."}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Seattle WA USA","acronym":"MM '20"},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3414396","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3414396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:24Z","timestamp":1750197684000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3414396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":19,"alternative-id":["10.1145\/3394171.3414396","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3414396","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}