{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T07:38:48Z","timestamp":1765438728837,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Youth Innovation Promotion Association of Chinese Academy of Sciences under Grant","award":["2020108"],"award-info":[{"award-number":["2020108"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61931008, 61671196, 62071415, 62001146, 61701149, 61801157, 61971268, 61901145, 61901150, 619721 23, 61771457, 61732007"],"award-info":[{"award-number":["61931008, 61671196, 62071415, 62001146, 61701149, 61801157, 61971268, 61901145, 61901150, 619721 23, 61771457, 61732007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Province Natural Science Foundation of China","award":["LR17F030006, Q19F010030"],"award-info":[{"award-number":["LR17F030006, Q19F010030"]}]},{"name":"National Key Research and Development Program of China under Grant","award":["2020YFB1406604"],"award-info":[{"award-number":["2020YFB1406604"]}]},{"name":"111 Project","award":["No. D17019"],"award-info":[{"award-number":["No. D17019"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475386","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T11:31:01Z","timestamp":1634556661000},"page":"2252-2261","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Heuristic Depth Estimation with Progressive Depth Reconstruction and Confidence-Aware Loss"],"prefix":"10.1145","author":[{"given":"Jiehua","family":"Zhang","sequence":"first","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}]},{"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Chenggang","family":"Yan","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}]},{"given":"Yaoqi","family":"Sun","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}]},{"given":"Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Kunming University of Science and Technology, Kunming, China"}]},{"given":"Jiyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}]},{"given":"Zhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Moreal Pte. Ltd, Geylang, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00273"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157178"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3367032.3367132"},{"key":"e_1_3_2_1_4_1","volume-title":"Laplacian Pyramid Neural Network for Dense Continuous-Value Regression for Complex Scenes","author":"Chen Xuejin","year":"2020","unstructured":"Xuejin Chen , Xiaotian Chen , Yiteng Zhang , Xueyang Fu , and Zheng-Jun Zha . 2020. Laplacian Pyramid Neural Network for Dense Continuous-Value Regression for Complex Scenes . IEEE Transactions on Neural Networks and Learning Systems ( 2020 ). Xuejin Chen, Xiaotian Chen, Yiteng Zhang, Xueyang Fu, and Zheng-Jun Zha. 2020. Laplacian Pyramid Neural Network for Dense Continuous-Value Regression for Complex Scenes. IEEE Transactions on Neural Networks and Learning Systems (2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation. arXiv preprint arXiv:2104.00877","author":"Chen Xiaotian","year":"2021","unstructured":"Xiaotian Chen , Yuwang Wang , Xuejin Chen , and Wenjun Zeng . 2021. S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation. arXiv preprint arXiv:2104.00877 ( 2021 ). Xiaotian Chen, Yuwang Wang, Xuejin Chen, and Wenjun Zeng. 2021. S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation. arXiv preprint arXiv:2104.00877 (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_11"},{"key":"e_1_3_2_1_7_1","unstructured":"Xinjing Cheng Peng Wang Chenye Guan and Ruigang Yang. 2020. Cspn  Xinjing Cheng Peng Wang Chenye Guan and Ruigang Yang. 2020. Cspn"},{"volume":"34","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","key":"e_1_3_2_1_8_1","unstructured":": Learning context and resource aware convolutional spatial propagation networks for depth completion . In Proceedings of the AAAI Conference on Artificial Intelligence , Vol. 34 . 10615--10622. : Learning context and resource aware convolutional spatial propagation networks for depth completion. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 10615--10622."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_7"},{"key":"e_1_3_2_1_10_1","volume-title":"Learning depth with convolutional spatial propagation network","author":"Cheng Xinjing","year":"2019","unstructured":"Xinjing Cheng , Peng Wang , and Ruigang Yang . 2019. Learning depth with convolutional spatial propagation network . IEEE transactions on pattern analysis and machine intelligence ( 2019 ). Xinjing Cheng, Peng Wang, and Ruigang Yang. 2019. Learning depth with convolutional spatial propagation network. IEEE transactions on pattern analysis and machine intelligence (2019)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063423"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00227"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969091"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01203"},{"key":"e_1_3_2_1_16_1","volume-title":"Confidence Propagation through CNNs for Guided Sparse Depth Regression","author":"Eldesokey Abdelrahman","year":"2019","unstructured":"Abdelrahman Eldesokey , Michael Felsberg , and Fahad Khan . 2019. Confidence Propagation through CNNs for Guided Sparse Depth Regression . IEEE Transactions on Pattern Analysis and Machine Intelligence , Vol. PP ( 07 2019 ), 1--1. https:\/\/doi.org\/10.1109\/TPAMI.2019.2929170 10.1109\/TPAMI.2019.2929170 Abdelrahman Eldesokey, Michael Felsberg, and Fahad Khan. 2019. Confidence Propagation through CNNs for Guided Sparse Depth Regression. IEEE Transactions on Pattern Analysis and Machine Intelligence , Vol. PP (07 2019), 1--1. https:\/\/doi.org\/10.1109\/TPAMI.2019.2929170"},{"key":"e_1_3_2_1_17_1","volume-title":"Propagating confidences through cnns for sparse data regression. arXiv preprint arXiv:1805.11913","author":"Eldesokey Abdelrahman","year":"2018","unstructured":"Abdelrahman Eldesokey , Michael Felsberg , and Fahad Shahbaz Khan . 2018. Propagating confidences through cnns for sparse data regression. arXiv preprint arXiv:1805.11913 ( 2018 ). Abdelrahman Eldesokey, Michael Felsberg, and Fahad Shahbaz Khan. 2018. Propagating confidences through cnns for sparse data regression. arXiv preprint arXiv:1805.11913 (2018)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2013.6728473"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354978"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.107"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00397"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_40"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491","author":"Kendall Alex","year":"2018","unstructured":"Alex Kendall , Yarin Gal , and Roberto Cipolla . 2018 . Multi-task learning using uncertainty to weigh losses for scene geometry and semantics . In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491 . Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.54"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_46"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413830"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539823"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413777"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01132"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460184"},{"key":"e_1_3_2_1_40_1","volume-title":"Object Scene Flow for Autonomous Vehicles. In Conference on Computer Vision and Pattern Recognition (CVPR) .","author":"Menze Moritz","year":"2015","unstructured":"Moritz Menze and Andreas Geiger . 2015 . Object Scene Flow for Autonomous Vehicles. In Conference on Computer Vision and Pattern Recognition (CVPR) . Moritz Menze and Andreas Geiger. 2015. Object Scene Flow for Autonomous Vehicles. In Conference on Computer Vision and Pattern Recognition (CVPR) ."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1090\/conm\/443\/08555"},{"key":"e_1_3_2_1_42_1","volume-title":"Beyond Image to Depth: Improving Depth Prediction using Echoes. arXiv preprint arXiv:2103.08468","author":"Parida Kranti Kumar","year":"2021","unstructured":"Kranti Kumar Parida , Siddharth Srivastava , and Gaurav Sharma . 2021. Beyond Image to Depth: Improving Depth Prediction using Echoes. arXiv preprint arXiv:2103.08468 ( 2021 ). Kranti Kumar Parida, Siddharth Srivastava, and Gaurav Sharma. 2021. Beyond Image to Depth: Improving Depth Prediction using Echoes. arXiv preprint arXiv:2103.08468 (2021)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_8"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00343"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"e_1_3_2_1_49_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_50_1","volume-title":"CLIFFNet for Monocular Depth Estimation with Hierarchical Embedding Loss. In European Conference on Computer Vision. Springer, 316--331","author":"Wang Lijun","year":"2020","unstructured":"Lijun Wang , Jianming Zhang , Yifan Wang , Huchuan Lu , and Xiang Ruan . 2020 . CLIFFNet for Monocular Depth Estimation with Hierarchical Embedding Loss. In European Conference on Computer Vision. Springer, 316--331 . Lijun Wang, Jianming Zhang, Yifan Wang, Huchuan Lu, and Xiang Ruan. 2020. CLIFFNet for Monocular Depth Estimation with Hierarchical Embedding Loss. In European Conference on Computer Vision. Springer, 316--331."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794404"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794182"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00014"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00290"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2975798"},{"key":"e_1_3_2_1_57_1","volume-title":"2021 a. Task-adaptive attention for image captioning","author":"Yan Chenggang","year":"2021","unstructured":"Chenggang Yan , Yiming Hao , Liang Li , Jian Yin , Anan Liu , Zhendong Mao , Zhenyu Chen , and Xingyu Gao . 2021 a. Task-adaptive attention for image captioning . IEEE Transactions on Circuits and Systems for Video Technology ( 2021 ). Chenggang Yan, Yiming Hao, Liang Li, Jian Yin, Anan Liu, Zhendong Mao, Zhenyu Chen, and Xingyu Gao. 2021 a. Task-adaptive attention for image captioning. IEEE Transactions on Circuits and Systems for Video Technology (2021)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404374"},{"key":"e_1_3_2_1_59_1","volume-title":"2021 b. Age-Invariant Face Recognition By Multi-Feature Fusion and Decomposition with Self-Attention. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)","author":"Yan Chenggang","year":"2021","unstructured":"Chenggang Yan , Lixuan Meng , Liang Li , Jiehua Zhang , Jian Yin , Jiyong Zhang , Zhan Wang , Yaoqi Sun , and Bolun Zheng . 2021 b. Age-Invariant Face Recognition By Multi-Feature Fusion and Decomposition with Self-Attention. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) ( 2021 ). Chenggang Yan, Lixuan Meng, Liang Li, Jiehua Zhang, Jian Yin, Jiyong Zhang, Zhan Wang, Yaoqi Sun, and Bolun Zheng. 2021 b. Age-Invariant Face Recognition By Multi-Feature Fusion and Decomposition with Self-Attention. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) (2021)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00136"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107578"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.015"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_15"},{"key":"e_1_3_2_1_65_1","volume-title":"The berhu penalty and the grouped effect. arXiv preprint arXiv:1207.6868","author":"Zwald Laurent","year":"2012","unstructured":"Laurent Zwald and Sophie Lambert-Lacroix . 2012. The berhu penalty and the grouped effect. arXiv preprint arXiv:1207.6868 ( 2012 ). Laurent Zwald and Sophie Lambert-Lacroix. 2012. The berhu penalty and the grouped effect. arXiv preprint arXiv:1207.6868 (2012)."}],"event":{"name":"MM '21: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Virtual Event China","acronym":"MM '21"},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475386","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:32Z","timestamp":1750193312000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475386"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":65,"alternative-id":["10.1145\/3474085.3475386","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475386","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}