{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:57:51Z","timestamp":1785488271668,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1145\/3774521.3774590","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T07:34:24Z","timestamp":1785483264000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Can Unsupervised Segmentation Reduce Annotation Costs for Video Semantic Segmentation?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8606-3348","authenticated-orcid":false,"given":"Samik","family":"Some","sequence":"first","affiliation":[{"name":"IIT Kanpur, Kanpur, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5262-9722","authenticated-orcid":false,"given":"Vinay","family":"Namboodiri","sequence":"additional","affiliation":[{"name":"University of Bath, Bath, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_5"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_40"},{"key":"e_1_3_3_2_4_2","volume-title":"ICLR 2015","author":"Chen Liang-Chieh","year":"2015","unstructured":"Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan\u00a0L. Yuille. 2015. Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs. In ICLR 2015. USA."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Liang-Chieh Chen George Papandreou Iasonas Kokkinos Kevin Murphy and Alan\u00a0L. Yuille. 2018. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets Atrous Convolution and Fully Connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40 4 (2018) 834\u2013848.","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_3_3_2_6_2","first-page":"17864","volume-title":"NeurIPS 2021","author":"Cheng Bowen","year":"2021","unstructured":"Bowen Cheng, Alexander\u00a0G. Schwing, and Alexander Kirillov. 2021. Per-Pixel Classification is Not All You Need for Semantic Segmentation. In NeurIPS 2021. virtual, 17864\u201317875."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00592"},{"key":"e_1_3_3_2_9_2","volume-title":"ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR 2021. OpenReview.net, Virtual Event."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.477"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01178"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Yanming Guo Yu Liu Theodoros Georgiou and Michael\u00a0S. Lew. 2018. A review of semantic segmentation using deep neural networks. Int. J. Multim. Inf. Retr. 7 2 (2018) 87\u201393.","DOI":"10.1007\/s13735-017-0141-z"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Shijie Hao Yuan Zhou and Yanrong Guo. 2020. A Brief Survey on Semantic Segmentation with Deep Learning. Neurocomputing 406 (2020) 302\u2013321.","DOI":"10.1016\/j.neucom.2019.11.118"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00884"},{"key":"e_1_3_3_2_16_2","first-page":"65","volume-title":"BMVC 2018","author":"Hung Wei-Chih","year":"2018","unstructured":"Wei-Chih Hung, Yi-Hsuan Tsai, Yan-Ting Liou, Yen-Yu Lin, and Ming-Hsuan Yang. 2018. Adversarial Learning for Semi-supervised Semantic Segmentation. In BMVC 2018. BMVA Press, UK, 65."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00083"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00907"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428381"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00628"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.114"},{"key":"e_1_3_3_2_24_2","series-title":"Lecture Notes in Computer Science","first-page":"352","volume-title":"ECCV 2020","author":"Liu Yifan","year":"2020","unstructured":"Yifan Liu, Chunhua Shen, Changqian Yu, and Jingdong Wang. 2020. Efficient Semantic Video Segmentation with Per-Frame Inference. In ECCV 2020(Lecture Notes in Computer Science, Vol.\u00a012355), Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.). Springer, UK, 352\u2013368."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_46"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Sudhanshu Mittal Maxim Tatarchenko and Thomas Brox. 2021. Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency. IEEE Trans. Pattern Anal. Mach. Intell. 43 4 (2021) 1369\u20131379.","DOI":"10.1109\/TPAMI.2019.2960224"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00713"},{"key":"e_1_3_3_2_29_2","series-title":"Proceedings of Machine Learning Research","first-page":"8748","volume-title":"ICML 2021","volume":"139","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In ICML 2021(Proceedings of Machine Learning Research, Vol.\u00a0139). PMLR, Virtual Event, 8748\u20138763."},{"key":"e_1_3_3_2_30_2","volume-title":"ICLR 2025","author":"Ravi Nikhila","year":"2025","unstructured":"Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman R\u00e4dle, Chlo\u00e9 Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan\u00a0Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross\u00a0B. Girshick, Piotr Doll\u00e1r, and Christoph Feichtenhofer. 2025. SAM 2: Segment Anything in Images and Videos. In ICLR 2025. OpenReview.net, Singapore."},{"key":"e_1_3_3_2_31_2","volume-title":"ICLR 2015","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In ICLR 2015. USA."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.606"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00313"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00190"},{"key":"e_1_3_3_2_36_2","first-page":"5998","volume-title":"NeurIPS 2017","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS 2017. USA, 5998\u20136008."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506731"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00421"},{"key":"e_1_3_3_2_39_2","first-page":"12077","volume-title":"NeurIPS 2021","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jos\u00e9\u00a0M. \u00c1lvarez, and Ping Luo. 2021. SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. In NeurIPS 2021. virtual, 12077\u201312090."},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00906"},{"key":"e_1_3_3_2_46_2","unstructured":"Yi Zhu Zhongyue Zhang Chongruo Wu Zhi Zhang Tong He Hang Zhang R. Manmatha Mu Li and Alexander\u00a0J. Smola. 2020. Improving Semantic Segmentation via Self-Training. CoRR abs\/2004.14960 (2020). arXiv:https:\/\/arXiv.org\/abs\/2004.14960https:\/\/arxiv.org\/abs\/2004.14960"},{"key":"e_1_3_3_2_47_2","volume-title":"ICLR 2021","author":"Zou Yuliang","year":"2021","unstructured":"Yuliang Zou, Zizhao Zhang, Han Zhang, Chun-Liang Li, Xiao Bian, Jia-Bin Huang, and Tomas Pfister. 2021. PseudoSeg: Designing Pseudo Labels for Semantic Segmentation. In ICLR 2021. OpenReview.net, Virtual Event."}],"event":{"name":"ICVGIP 2025: Indian Conference on Computer Vision, Graphics, and Image Processing","location":"Mandi Himachal Pradesh India","acronym":"ICVGIP 2025"},"container-title":["Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774521.3774590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:03:43Z","timestamp":1785485023000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774521.3774590"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":46,"alternative-id":["10.1145\/3774521.3774590","10.1145\/3774521"],"URL":"https:\/\/doi.org\/10.1145\/3774521.3774590","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}