{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T04:48:01Z","timestamp":1790398081151,"version":"4.1.0"},"reference-count":36,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2018,7,30]],"date-time":"2018-07-30T00:00:00Z","timestamp":1532908800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2018,8,31]]},"abstract":"<jats:p>\n                    Accurate representation of soft transitions between image regions is essential for high-quality image editing and compositing. Current techniques for generating such representations depend heavily on interaction by a skilled visual artist, as creating such accurate object selections is a tedious task. In this work, we introduce\n                    <jats:italic>semantic soft segments<\/jats:italic>\n                    , a set of layers that correspond to semantically meaningful regions in an image with accurate soft transitions between different objects. We approach this problem from a spectral segmentation angle and propose a graph structure that embeds texture and color features from the image as well as higher-level semantic information generated by a neural network. The soft segments are generated via eigendecomposition of the carefully constructed Laplacian matrix fully automatically. We demonstrate that otherwise complex image editing tasks can be done with little effort using semantic soft segments.\n                  <\/jats:p>","DOI":"10.1145\/3197517.3201275","type":"journal-article","created":{"date-parts":[[2018,7,31]],"date-time":"2018-07-31T11:56:23Z","timestamp":1533038183000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":90,"title":["Semantic soft segmentation"],"prefix":"10.1145","volume":"37","author":[{"given":"Ya\u011fiz","family":"Aksoy","sequence":"first","affiliation":[{"name":"MIT CSAIL and ETH Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tae-Hyun","family":"Oh","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sylvain","family":"Paris","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Pollefeys","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Switzerland and Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wojciech","family":"Matusik","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,7,30]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.32"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2907940"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3002176"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360639"},{"key":"e_1_2_2_6_1","doi-asserted-by":"crossref","unstructured":"R. Barrett M. Berry T. Chan J. Demmel J. Donato J. Dongarra V. Eijkhout R. Pozo C. Romine and H. van der Vorst. 1994. Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods. SIAM.  R. Barrett M. Berry T. Chan J. Demmel J. Donato J. Dongarra V. Eijkhout R. Pozo C. Romine and H. van der Vorst. 1994. Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods. SIAM.","DOI":"10.1137\/1.9781611971538"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.65"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.392"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995413"},{"key":"e_1_2_2_10_1","volume-title":"COCO-Stuff: Thing and Stuff Classes in Context. arXiv: 1612.03716 {cs.CV}","author":"Caesar Holger","year":"2016","unstructured":"Holger Caesar , Jasper Uijlings , and Vittorio Ferrari . 2016. COCO-Stuff: Thing and Stuff Classes in Context. arXiv: 1612.03716 {cs.CV} ( 2016 ). Holger Caesar, Jasper Uijlings, and Vittorio Ferrari. 2016. COCO-Stuff: Thing and Stuff Classes in Context. arXiv: 1612.03716 {cs.CV} (2016)."},{"key":"e_1_2_2_11_1","volume-title":"Atrous Convolution, and Fully Connected CRFs","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen , George Papandreou , Iasonas Kokkinos , Kevin Murphy , and Alan L Yuille . 2017. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets , Atrous Convolution, and Fully Connected CRFs . IEEE Trans. Pattern Anal. Mach. Intell . ( 2017 ). Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2017. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. (2017)."},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.18"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366151"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12822"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12295"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.823819"},{"key":"e_1_2_2_17_1","volume-title":"Sergio Guadarrama, and Kevin P. Murphy.","author":"Fathi Alireza","year":"2017","unstructured":"Alireza Fathi , Zbigniew Wojna , Vivek Rathod , Peng Wang , Hyun Oh Song , Sergio Guadarrama, and Kevin P. Murphy. 2017 . Semantic Instance Segmentation via Deep Metric Learning . arXiv: 1703.10277 {cs.CV} (2017). Alireza Fathi, Zbigniew Wojna, Vivek Rathod, Peng Wang, Hyun Oh Song, Sergio Guadarrama, and Kevin P. Murphy. 2017. Semantic Instance Segmentation via Deep Metric Learning. arXiv: 1703.10277 {cs.CV} (2017)."},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"e_1_2_2_19_1","volume-title":"Mask R-CNN. In Proc. ICCV.","author":"He Kaiming","year":"2017","unstructured":"Kaiming He , Georgia Gkioxari , Piotr Dollar , and Ross Girshick . 2017 . Mask R-CNN. In Proc. ICCV. Kaiming He, Georgia Gkioxari, Piotr Dollar, and Ross Girshick. 2017. Mask R-CNN. In Proc. ICCV."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.213"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1177"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.168"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2008.01264.x"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_2_2_26_1","volume-title":"So Kweon, and Sing Bing Kang. 2017. Personalized Cinemagraphs Using Semantic Understanding and Collaborative Learning. In Proc. ICCV.","author":"Oh Tae-Hyun","unstructured":"Tae-Hyun Oh , Kyungdon Joo , Neel Joshi , Baoyuan Wang , In So Kweon, and Sing Bing Kang. 2017. Personalized Cinemagraphs Using Semantic Understanding and Collaborative Learning. In Proc. ICCV. Tae-Hyun Oh, Kyungdon Joo, Neel Joshi, Baoyuan Wang, In So Kweon, and Sing Bing Kang. 2017. Personalized Cinemagraphs Using Semantic Understanding and Collaborative Learning. In Proc. ICCV."},{"key":"e_1_2_2_27_1","volume-title":"Proc. ICME.","author":"Qin S.","unstructured":"S. Qin , S. Kim , and R. Manduchi . 2017. Automatic skin and hair masking using fully convolutional networks . In Proc. ICME. S. Qin, S. Kim, and R. Manduchi. 2017. Automatic skin and hair masking using fully convolutional networks. In Proc. ICME."},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.123"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206503"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_6"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.206"},{"key":"e_1_2_2_32_1","volume-title":"Proc. NIPS.","author":"Sohn Kihyuk","year":"2016","unstructured":"Kihyuk Sohn . 2016 . Improved deep metric learning with multi-class N-pair loss objective . In Proc. NIPS. Kihyuk Sohn. 2016. Improved deep metric learning with multi-class N-pair loss objective. In Proc. NIPS."},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1168"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988229"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.41"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3197517.3201275","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3197517.3201275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:39:22Z","timestamp":1750196362000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3197517.3201275"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,30]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,8,31]]}},"alternative-id":["10.1145\/3197517.3201275"],"URL":"https:\/\/doi.org\/10.1145\/3197517.3201275","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7,30]]},"assertion":[{"value":"2018-07-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}