{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T05:44:33Z","timestamp":1749620673772,"version":"3.40.2"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T00:00:00Z","timestamp":1712534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T00:00:00Z","timestamp":1712534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"IITP","award":["2021-0-00087"],"award-info":[{"award-number":["2021-0-00087"]}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","award":["4199990214394"],"award-info":[{"award-number":["4199990214394"]}],"id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-18878-6","type":"journal-article","created":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T04:01:35Z","timestamp":1712548895000},"page":"5565-5582","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Human-oriented video retargeting via object detection and patch decision"],"prefix":"10.1007","volume":"84","author":[{"given":"Dong-Hwi","family":"Kim","sequence":"first","affiliation":[]},{"given":"Sujin","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Jaehyun","family":"Bae","sequence":"additional","affiliation":[]},{"given":"Sukee","family":"Cho","sequence":"additional","affiliation":[]},{"given":"Byungjun","family":"Bae","sequence":"additional","affiliation":[]},{"given":"Jieun","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7282-7686","authenticated-orcid":false,"given":"Sang-hyo","family":"Park","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,8]]},"reference":[{"key":"18878_CR1","unstructured":"Jocher G, Stoken A, Chaurasia A, Borovec J, Kwon Y, Michael K et al (2021) Ultralytics\/yolov5: v6. 0-YOLOv5n'Nano'models. In: Roboflow integration, TensorFlow export, OpenCV DNN support. Zenodo"},{"key":"18878_CR2","doi-asserted-by":"crossref","unstructured":"Avidan S, Shamir A (2007) Seam carving for content-aware image resizing. ACM Trans Graph 26(3):10","DOI":"10.1145\/1276377.1276390"},{"key":"18878_CR3","doi-asserted-by":"crossref","unstructured":"Bansal A, Ma S, Ramanan D, Sheikh Y (2018) Recycle-GAN: Unsupervised video retargeting. In: Proceedings of the European conference on computer vision (ECCV), pp 119\u2013135","DOI":"10.1007\/978-3-030-01228-1_8"},{"issue":"1","key":"18878_CR4","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TCSVT.2006.885717","volume":"17","author":"WH Cheng","year":"2006","unstructured":"Cheng WH, Wang CW, Wu JL (2006) Video adaptation for small display based on content recomposition. IEEE Trans Circuits Syst Video Technol 17(1):43\u201358","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"18878_CR5","doi-asserted-by":"crossref","unstructured":"Cho D, Park J, Oh TH, Tai YW, So Kweon I (2017) Weakly-and self-supervised learning for content-aware deep image retargeting. In: Proceedings of the IEEE international conference on computer vision, pp 4558\u20134567","DOI":"10.1109\/ICCV.2017.488"},{"key":"18878_CR6","doi-asserted-by":"crossref","unstructured":"Cho D, Jung Y, Rameau F, Kim D, Woo S, Kweon IS (2019) Video Retargeting: trade-off between content preservation and spatio-temporal consistency. In: Proceedings of the 27th ACM international conference on multimedia, pp 882\u2013889","DOI":"10.1145\/3343031.3350895"},{"issue":"4","key":"18878_CR7","first-page":"75","volume":"39","author":"M Chu","year":"2020","unstructured":"Chu M, Xie Y, Mayer J et al (2020) Learning temporal coherence via self-supervision for gan-based video generation. ACM Trans Graphics (TOG) 39(4):75\u201381","journal-title":"ACM Trans Graphics (TOG)"},{"issue":"2","key":"18878_CR8","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","volume":"38","author":"C Dong","year":"2015","unstructured":"Dong C, Loy CC, He K et al (2015) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295\u2013307","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"8","key":"18878_CR9","doi-asserted-by":"crossref","first-page":"1016","DOI":"10.1175\/1520-0450(1979)018<1016:LFIOAT>2.0.CO;2","volume":"18","author":"CE Duchon","year":"1979","unstructured":"Duchon CE (1979) Lanczos filtering in one and two dimensions. J Appl Meteorol Climatol 18(8):1016\u20131022","journal-title":"J Appl Meteorol Climatol"},{"key":"18878_CR10","doi-asserted-by":"crossref","unstructured":"Imani H, Islam MB, Wong LK (2023) Saliency-aware stereoscopic video retargeting. In: Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition, pp 1230\u20131239","DOI":"10.1109\/CVPRW59228.2023.00130"},{"key":"18878_CR11","doi-asserted-by":"crossref","unstructured":"Jin JG, Bae J, Baek HG, Park SH (2023) Object-ratio-preserving video retargeting framework based on segmentation and inpainting. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 497\u2013503","DOI":"10.1109\/WACVW58289.2023.00055"},{"key":"18878_CR12","doi-asserted-by":"crossref","unstructured":"Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4401\u20134410","DOI":"10.1109\/CVPR.2019.00453"},{"issue":"6","key":"18878_CR13","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.1109\/TASSP.1981.1163711","volume":"29","author":"R Keys","year":"1981","unstructured":"Keys R (1981) Cubic convolution interpolation for digital image processing. IEEE Trans Acoust Speech Signal Process 29(6):1153\u20131160","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"3","key":"18878_CR14","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1145\/3231598","volume":"14","author":"J Kiess","year":"2018","unstructured":"Kiess J, Kopf S, Guthier B et al (2018) A survey on content-aware image and video retargeting. ACM Trans Multimed Comput Commun App 14(3):28. https:\/\/doi.org\/10.1145\/3231598","journal-title":"ACM Trans Multimed Comput Commun App"},{"key":"18878_CR15","doi-asserted-by":"crossref","unstructured":"Ledig C, Theis L, Husz\u00e1r F, Caballero J, Cunningham A, Acosta A et al (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4681\u20134690","DOI":"10.1109\/CVPR.2017.19"},{"issue":"2","key":"18878_CR16","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1109\/TBC.2018.2816783","volume":"64","author":"X Min","year":"2018","unstructured":"Min X, Zhai G, Gu K et al (2018) Blind image quality estimation via distortion aggravation. IEEE Trans Broadcast 64(2):508\u2013517","journal-title":"IEEE Trans Broadcast"},{"key":"18878_CR17","doi-asserted-by":"crossref","unstructured":"Mittal A, Moorthy AK, Bovik AC (2011) Blind\/referenceless image spatial quality evaluator. In: 2011 conference record of the forty fifth asilomar conference on signals, systems and computers (ASILOMAR). IEEE, pp 723\u2013727","DOI":"10.1109\/ACSSC.2011.6190099"},{"key":"18878_CR18","doi-asserted-by":"crossref","unstructured":"Ni H, Liu Y, Huang SX, Xue Y (2023) Cross-identity video motion retargeting with joint transformation and synthesis. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 412\u2013422","DOI":"10.1109\/WACV56688.2023.00049"},{"key":"18878_CR19","unstructured":"Pont-Tuset J, Perazzi F, Caelles S, Arbel\u00e1ez P, Sorkine-Hornung A, Van Gool L (2017) The 2017 Davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675"},{"key":"18878_CR20","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"issue":"3","key":"18878_CR21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1360612.1360615","volume":"27","author":"M Rubinstein","year":"2008","unstructured":"Rubinstein M, Shamir A, Avidan S (2008) Improved seam carving for video retargeting. ACM Transactions Graphics (TOG) 27(3):1\u20139","journal-title":"ACM Transactions Graphics (TOG)"},{"key":"18878_CR22","doi-asserted-by":"crossref","unstructured":"Shocher A, Bagon S, Isola P, Irani M (2019) Ingan: Capturing and retargeting the \u201cDNA\u201d of a natural image. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4492\u20134501","DOI":"10.1109\/ICCV.2019.00459"},{"issue":"1","key":"18878_CR23","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1016\/B978-012077790-7\/50030-8","volume":"1","author":"P Th\u2019evenaz","year":"2000","unstructured":"Th\u2019evenaz P, Blu T, Unser M (2000) Image interpolation and resampling. Handbook Med Imaging, Process Anal 1(1):393\u2013420","journal-title":"Handbook Med Imaging, Process Anal"},{"issue":"146","key":"18878_CR24","first-page":"10","volume":"2006","author":"S Tomar","year":"2006","unstructured":"Tomar S (2006) Converting video formats with ffmpeg. Linux Journal 2006(146):10","journal-title":"Linux Journal"},{"key":"18878_CR25","doi-asserted-by":"crossref","unstructured":"Venkatanath N, Praneeth D, Bh MC, Channappayya SS, Medasani SS (2015) Blind image quality evaluation using perception based features. In: 2015 twenty first national conference on communications (NCC). IEEE, pp 1\u20136","DOI":"10.1109\/NCC.2015.7084843"},{"key":"18878_CR26","doi-asserted-by":"crossref","unstructured":"Wang YS, Lin HC, Sorkine O, Lee TY (2010) Motion-based video retargeting with optimized crop-and-warp. In: ACM SIGGRAPH 2010 papers, pp 1\u20139","DOI":"10.1145\/1833349.1778827"},{"key":"18878_CR27","doi-asserted-by":"crossref","unstructured":"Wang YS, Hsiao JH, Sorkine O, Lee TY (2011) Scalable and coherent video resizing with per-frame optimization. ACM Trans Graph (TOG) 30(4):1\u20138","DOI":"10.1145\/2010324.1964983"},{"key":"18878_CR28","doi-asserted-by":"crossref","unstructured":"Wang Z, Simoncelli EP, Bovik AC (2003) Multiscale structural similarity for image quality assessment. In: The thrity-seventh Asilomar conference on signals, systems & computers, vol 2. IEEE, pp 1398\u20131402","DOI":"10.1109\/ACSSC.2003.1292216"},{"issue":"4","key":"18878_CR29","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR et al (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600\u2013612","journal-title":"IEEE Trans Image Process"},{"key":"18878_CR30","doi-asserted-by":"publisher","unstructured":"Xu X, Liu S, Li Z (2021) Tencent video dataset (tvd): A video dataset for learning-based visual data compression and analysis. https:\/\/doi.org\/10.48550\/ARXIV. 2105.05961, URL https:\/\/arxiv.org\/abs\/2105.05961","DOI":"10.48550\/ARXIV"},{"key":"18878_CR31","doi-asserted-by":"crossref","unstructured":"Yang Z, Zhu W, Wu W, Qian C, Zhou Q, Zhou B, Loy CC (2020) Transmomo: Invariance-driven unsupervised video motion retargeting. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5306\u20135315","DOI":"10.1109\/CVPR42600.2020.00535"},{"key":"18878_CR32","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros AA, Shechtman E, Wang O (2018) The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 586\u2013595","DOI":"10.1109\/CVPR.2018.00068"},{"key":"18878_CR33","doi-asserted-by":"crossref","unstructured":"Granot N, Feinstein B, Shocher A, Bagon S, Irani M (2022) Drop the GAN: In defense of patches nearest neighbors as single image generative models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13460\u201313469","DOI":"10.1109\/CVPR52688.2022.01310"},{"issue":"12","key":"18878_CR34","doi-asserted-by":"crossref","first-page":"4695","DOI":"10.1109\/TIP.2012.2214050","volume":"21","author":"A Mittal","year":"2012","unstructured":"Mittal A, Moorthy AK, Bovik AC (2012) No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 21(12):4695\u20134708","journal-title":"IEEE Trans Image Process"},{"issue":"3","key":"18878_CR35","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","volume":"20","author":"A Mittal","year":"2012","unstructured":"Mittal A, Soundararajan R, Bovik AC (2012) Making a \u201ccompletely blind\u201d image quality analyzer. IEEE Signal Process Lett 20(3):209\u2013212","journal-title":"IEEE Signal Process Lett"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18878-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-18878-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18878-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T00:20:54Z","timestamp":1742689254000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-18878-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,8]]},"references-count":35,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["18878"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-18878-6","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2024,4,8]]},"assertion":[{"value":"4 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there are no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}}]}}