{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:51:55Z","timestamp":1777654315143,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Pioneer and Leading Goose R&D Program of Zhejiang Province","award":["2024C01023, 2023C01046, 2022C01068, 2024C01107, 2023C01030"],"award-info":[{"award-number":["2024C01023, 2023C01046, 2022C01068, 2024C01107, 2023C01030"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322211, 62336008, U21B2024, 61931008, 62071415"],"award-info":[{"award-number":["62322211, 62336008, U21B2024, 61931008, 62071415"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Laboratory of Intelligent Processing Technology for Digital Music (Zhejiang Conservatory of Music), Ministry of Culture and Tourism","award":["2023DMKLB004"],"award-info":[{"award-number":["2023DMKLB004"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1406604, 2023YFB4502800, 2023YFB4502803"],"award-info":[{"award-number":["2020YFB1406604, 2023YFB4502800, 2023YFB4502803"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LDT23F01011F01, LDT23F01015F01, LDT23F01014F01, LD24F020007"],"award-info":[{"award-number":["LDT23F01011F01, LDT23F01015F01, LDT23F01014F01, LD24F020007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681155","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"8306-8315","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Domain Shared and Specific Prompt Learning for Incremental Monocular Depth Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1697-3066","authenticated-orcid":false,"given":"Zhiwen","family":"Yang","sequence":"first","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1943-8219","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0790-9279","authenticated-orcid":false,"given":"Jiehua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4169-1595","authenticated-orcid":false,"given":"Tingyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8874-241X","authenticated-orcid":false,"given":"Yaoqi","family":"Sun","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University & Lishui Institute of Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1204-0512","authenticated-orcid":false,"given":"Chenggang","family":"Yan","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4009--4018","author":"Bhat Shariq Farooq","year":"2021","unstructured":"Shariq Farooq Bhat, Ibraheem Alhashim, and Peter Wonka. 2021. Adabins: Depth estimation using adaptive bins. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4009--4018."},{"key":"e_1_3_2_1_2_1","volume-title":"Coresets via bilevel optimization for continual learning and streaming. Advances in neural information processing systems","author":"Borsos Zal\u00e1n","year":"2020","unstructured":"Zal\u00e1n Borsos, Mojmir Mutny, and Andreas Krause. 2020. Coresets via bilevel optimization for continual learning and streaming. Advances in neural information processing systems, Vol. 33 (2020), 14879--14890."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00380"},{"key":"e_1_3_2_1_4_1","volume-title":"Virtual kitti 2. arXiv preprint arXiv:2001.10773","author":"Cabon Yohann","year":"2020","unstructured":"Yohann Cabon, Naila Murray, and Martin Humenberger. 2020. Virtual kitti 2. arXiv preprint arXiv:2001.10773 (2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"Philip HS Torr, and Marc'Aurelio Ranzato","author":"Chaudhry Arslan","year":"2019","unstructured":"Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet K Dokania, Philip HS Torr, and Marc'Aurelio Ranzato. 2019. On tiny episodic memories in continual learning. arXiv preprint arXiv:1902.10486 (2019)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00823"},{"key":"e_1_3_2_1_7_1","first-page":"1111","article-title":"Review of omnimedia content quality evaluation [J]","volume":"38","author":"Chenggang Y","year":"2022","unstructured":"Y Chenggang, S Yaoqi, Z Hao, Z Chenwei, Z Zunjie, Z Bolun, and Z Xiaofei. 2022. Review of omnimedia content quality evaluation [J]. J. Signal Process., Vol. 38, 6 (2022), 1111--1143.","journal-title":"J. Signal Process."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"e_1_3_2_1_12_1","volume-title":"Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation. arXiv preprint arXiv:2303.05050","author":"Hu Junjie","year":"2023","unstructured":"Junjie Hu, Chenyou Fan, Liguang Zhou, Qing Gao, Honghai Liu, and Tin Lun Lam. 2023. Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation. arXiv preprint arXiv:2303.05050 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Revisiting single image depth estimation: Toward higher resolution maps with accurate object boundaries. In 2019 IEEE winter conference on applications of computer vision (WACV)","author":"Hu Junjie","unstructured":"Junjie Hu, Mete Ozay, Yan Zhang, and Takayuki Okatani. 2019. Revisiting single image depth estimation: Toward higher resolution maps with accurate object boundaries. In 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, 1043--1051."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00821"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings, Part XXVI 16","author":"Huynh Lam","year":"2020","unstructured":"Lam Huynh, Phong Nguyen-Ha, Jiri Matas, Esa Rahtu, and Janne Heikkil\"a. 2020. Guiding monocular depth estimation using depth-attention volume. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXVI 16. Springer, 581--597."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_2"},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Machine Learning. PMLR, 10734--10750","author":"Kang Haeyong","year":"2022","unstructured":"Haeyong Kang, Rusty John Lloyd Mina, Sultan Rizky Hikmawan Madjid, Jaehong Yoon, Mark Hasegawa-Johnson, Sung Ju Hwang, and Chang D Yoo. 2022. Forget-free continual learning with winning subnetworks. In International Conference on Machine Learning. PMLR, 10734--10750."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_1_19_1","volume-title":"What learning systems do intelligent agents need? Complementary learning systems theory updated. Trends in cognitive sciences","author":"Kumaran Dharshan","year":"2016","unstructured":"Dharshan Kumaran, Demis Hassabis, and James L McClelland. 2016. What learning systems do intelligent agents need? Complementary learning systems theory updated. Trends in cognitive sciences, Vol. 20, 7 (2016), 512--534."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01641-5"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611807"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3158546"},{"key":"e_1_3_2_1_24_1","volume-title":"Learning without forgetting","author":"Li Zhizhong","year":"2017","unstructured":"Zhizhong Li and Derek Hoiem. 2017. Learning without forgetting. IEEE transactions on pattern analysis and machine intelligence, Vol. 40, 12 (2017), 2935--2947."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.173"},{"key":"e_1_3_2_1_26_1","first-page":"3003","article-title":"Entity-enhanced adaptive reconstruction network for weakly supervised referring expression grounding","volume":"45","author":"Liu Xuejing","year":"2022","unstructured":"Xuejing Liu, Liang Li, Shuhui Wang, Zheng-Jun Zha, Zechao Li, Qi Tian, and Qingming Huang. 2022. Entity-enhanced adaptive reconstruction network for weakly supervised referring expression grounding. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 3 (2022), 3003--3018.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_27_1","volume-title":"Gradient episodic memory for continual learning. Advances in neural information processing systems","author":"Lopez-Paz David","year":"2017","unstructured":"David Lopez-Paz and Marc'Aurelio Ranzato. 2017. Gradient episodic memory for continual learning. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00360"},{"key":"e_1_3_2_1_29_1","volume-title":"Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychological review","author":"McClelland James L","year":"1995","unstructured":"James L McClelland, Bruce L McNaughton, and Randall C O'Reilly. 1995. Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychological review, Vol. 102, 3 (1995), 419."},{"key":"e_1_3_2_1_30_1","volume-title":"Psychology of learning and motivation.","author":"McCloskey Michael","unstructured":"Michael McCloskey and Neal J Cohen. 1989. Catastrophic interference in connectionist networks: The sequential learning problem. In Psychology of learning and motivation. Vol. 24. Elsevier, 109--165."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"e_1_3_2_1_33_1","volume-title":"Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer","author":"Ranftl Ren\u00e9","year":"2020","unstructured":"Ren\u00e9 Ranftl, Katrin Lasinger, David Hafner, Konrad Schindler, and Vladlen Koltun. 2020. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 3 (2020), 1623--1637."},{"key":"e_1_3_2_1_34_1","volume-title":"Learning to learn without forgetting by maximizing transfer and minimizing interference. arXiv preprint arXiv:1810.11910","author":"Riemer Matthew","year":"2018","unstructured":"Matthew Riemer, Ignacio Cases, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, and Gerald Tesauro. 2018. Learning to learn without forgetting by maximizing transfer and minimizing interference. arXiv preprint arXiv:1810.11910 (2018)."},{"key":"e_1_3_2_1_35_1","volume-title":"Progressive neural networks. arXiv preprint arXiv:1606.04671","author":"Rusu Andrei A","year":"2016","unstructured":"Andrei A Rusu, Neil C Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, and Raia Hadsell. 2016. Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"e_1_3_2_1_37_1","volume-title":"International conference on machine learning. PMLR, 4548--4557","author":"Serra Joan","year":"2018","unstructured":"Joan Serra, Didac Suris, Marius Miron, and Alexandros Karatzoglou. 2018. Overcoming catastrophic forgetting with hard attention to the task. In International conference on machine learning. PMLR, 4548--4557."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 22nd ACM SIGSAC conference on computer and communications security. 1310--1321","author":"Shokri Reza","year":"2015","unstructured":"Reza Shokri and Vitaly Shmatikov. 2015. Privacy-preserving deep learning. In Proceedings of the 22nd ACM SIGSAC conference on computer and communications security. 1310--1321."},{"key":"e_1_3_2_1_39_1","volume-title":"Indoor segmentation and support inference from rgbd images. ECCV (5)","author":"Silberman Nathan","year":"2012","unstructured":"Nathan Silberman, Derek Hoiem, Pushmeet Kohli, and Rob Fergus. 2012. Indoor segmentation and support inference from rgbd images. ECCV (5), Vol. 7576 (2012), 746--760."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3106055"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3164834"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.284"},{"key":"e_1_3_2_1_43_1","volume-title":"Smart: Syntax-calibrated multi-aspect relation transformer for change captioning","author":"Tu Yunbin","year":"2024","unstructured":"Yunbin Tu, Liang Li, Li Su, Zheng-Jun Zha, and Qingming Huang. 2024. Smart: Syntax-calibrated multi-aspect relation transformer for change captioning. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00012"},{"key":"e_1_3_2_1_45_1","volume-title":"Transformers in self-supervised monocular depth estimation with unknown camera intrinsics. arXiv preprint arXiv:2202.03131","author":"Varma Arnav","year":"2022","unstructured":"Arnav Varma, Hemang Chawla, Bahram Zonooz, and Elahe Arani. 2022. Transformers in self-supervised monocular depth estimation with unknown camera intrinsics. arXiv preprint arXiv:2202.03131 (2022)."},{"key":"e_1_3_2_1_46_1","volume-title":"CoDEPS: Online continual learning for depth estimation and panoptic segmentation. arXiv preprint arXiv:2303.10147","author":"V\u00f6disch Niclas","year":"2023","unstructured":"Niclas V\u00f6disch, K\u00fcrsat Petek, Wolfram Burgard, and Abhinav Valada. 2023. CoDEPS: Online continual learning for depth estimation and panoptic segmentation. arXiv preprint arXiv:2303.10147 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning. arXiv preprint arXiv:2401.06548","author":"Wang Chenyang","year":"2024","unstructured":"Chenyang Wang, Junjun Jiang, Xingyu Hu, Xianming Liu, and Xiangyang Ji. 2024. Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning. arXiv preprint arXiv:2401.06548 (2024)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3226328"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611751"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00040"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00025"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2975798"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404374"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472810"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468872"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00099"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2021.00.455"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3209968"},{"key":"e_1_3_2_1_61_1","volume-title":"Online coreset selection for rehearsal-based continual learning. arXiv preprint arXiv:2106.01085","author":"Yoon Jaehong","year":"2021","unstructured":"Jaehong Yoon, Divyam Madaan, Eunho Yang, and Sung Ju Hwang. 2021. Online coreset selection for rehearsal-based continual learning. arXiv preprint arXiv:2106.01085 (2021)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00043"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3432099"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475386"},{"key":"e_1_3_2_1_65_1","unstructured":"Jiehua Zhang Liang Li Chenggang Yan Zhan Wang Changliang Xu Jiyong Zhang and Chuqiao Chen. [n. d.]. Learning Domain Invariant Features for Unsupervised Indoor Depth Estimation Adaptation. ACM Transactions on Multimedia Computing Communications and Applications ( [n. d.])."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.414"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3044181"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612042"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681155","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:02Z","timestamp":1750295882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681155"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":69,"alternative-id":["10.1145\/3664647.3681155","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681155","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}