{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:41:07Z","timestamp":1743061267799,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984312"},{"type":"electronic","value":"9789819984329"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8432-9_20","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"246-258","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SwinFusion: Channel Query-Response Based Feature Fusion for\u00a0Monocular Depth Estimation"],"prefix":"10.1007","author":[{"given":"Pengfei","family":"Lai","sequence":"first","affiliation":[]},{"given":"Mengxiao","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Yifan","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Min","family":"Xie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, A., Arora, C.: Attention attention everywhere: monocular depth prediction with skip attention. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5861\u20135870 (2023)","DOI":"10.1109\/WACV56688.2023.00581"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Lu, Y., Lu, G.: Self-supervised depth estimation from spectral consistency and novel view synthesis. In: 2022 International Joint Conference on Neural Networks, pp. 1\u20138 (2022)","DOI":"10.1109\/IJCNN55064.2022.9891946"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Liu, D., Cui, Y., Yan, L., Mousas, C., Yang, B., Chen, Y.: DenserNet: weakly supervised visual localization using multi-scale feature aggregation. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 6101\u20136109 (2021)","DOI":"10.1609\/aaai.v35i7.16760"},{"key":"20_CR4","doi-asserted-by":"publisher","unstructured":"Yan, Z., Wang, K., Li, X., Zhang, Z., Li, J., Yang, J.: RigNet: repetitive image guided network for depth completion. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13687, pp. 214\u2013230. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_13","DOI":"10.1007\/978-3-031-19812-0_13"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Yan, Z., Wang, K., Li, X., Zhang, Z., Li, J., Yang, J.: DesNet: decomposed scale-consistent network for unsupervised depth completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3109\u20133117 (2023)","DOI":"10.1609\/aaai.v37i3.25415"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Liang, J., Tao, G., Liu, D., Zhang, X.: Adversarial training of self-supervised monocular depth estimation against physical-world attacks. arXiv preprint arXiv:2301.13487 (2023)","DOI":"10.1109\/TPAMI.2024.3412632"},{"key":"20_CR7","doi-asserted-by":"publisher","unstructured":"Cheng, Z., et al.: Physical attack on monocular depth estimation with optimal adversarial patches. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13698, pp. 514\u2013532. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_30","DOI":"10.1007\/978-3-031-19839-7_30"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Wang, K., et al.: Regularizing nighttime weirdness: efficient self-supervised monocular depth estimation in the dark. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16055\u201316064 (2021)","DOI":"10.1109\/ICCV48922.2021.01575"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"20_CR10","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: AdaBins: depth estimation using adaptive bins. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4009\u20134018 (2021)"},{"key":"20_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"20_CR12","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"issue":"11","key":"20_CR13","doi-asserted-by":"publisher","first-page":"4381","DOI":"10.1109\/TCSVT.2021.3049869","volume":"31","author":"M Song","year":"2021","unstructured":"Song, M., Lim, S., Kim, W.: Monocular depth estimation using Laplacian pyramid-based depth residuals. IEEE Trans. Circ. Syst. Video Technol. 31(11), 4381\u20134393 (2021)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Yuan, W., Gu, X., Dai, Z., Zhu, S., Tan, P.: Neural window fully-connected CRFs for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3916\u20133925 (2022)","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2002\u20132011 (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"20_CR16","unstructured":"Li, Z., Wang, X., Liu, X., Jiang, J.: BinsFormer: revisiting adaptive bins for monocular depth estimation. arXiv preprint arXiv:2204.00987 (2022)"},{"key":"20_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., Barnard, K.: Attentional feature fusion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3560\u20133569 (2021)","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"issue":"1","key":"20_CR20","doi-asserted-by":"publisher","first-page":"20","DOI":"10.3390\/rs11010020","volume":"11","author":"Y Wang","year":"2018","unstructured":"Wang, Y., Liang, B., Ding, M., Li, J.: Dense semantic labeling with atrous spatial pyramid pooling and decoder for high-resolution remote sensing imagery. Remote Sens. 11(1), 20 (2018)","journal-title":"Remote Sens."},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Wang, H., Cao, P., Wang, J., Zaiane, O.R.: UCTransNet: rethinking the skip connections in U-Net from a channel-wise perspective with transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2441\u20132449 (2022)","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, Z., Liu, X., Jiang, J.: DepthFormer: exploiting long-range correlation and local information for accurate monocular depth estimation. arXiv preprint arXiv:2203.14211 (2022)","DOI":"10.1007\/s11633-023-1458-0"},{"key":"20_CR24","doi-asserted-by":"publisher","unstructured":"Huynh, L., Nguyen-Ha, P., Matas, J., Rahtu, E., Heikkil\u00e4, J.: Guiding monocular depth estimation using depth-attention volume. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 581\u2013597. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_35","DOI":"10.1007\/978-3-030-58574-7_35"},{"key":"20_CR25","doi-asserted-by":"publisher","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: LocalBins: improving depth estimation by learning local distributions. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13661, pp. 480\u2013496. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_28","DOI":"10.1007\/978-3-031-19769-7_28"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Naderi, T., Sadovnik, A., Hayward, J., Qi, H.: Monocular depth estimation with adaptive geometric attention. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 944\u2013954 (2022)","DOI":"10.1109\/WACV51458.2022.00069"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8432-9_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T19:33:15Z","timestamp":1730921595000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8432-9_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984312","9789819984329"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8432-9_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}