{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T23:54:25Z","timestamp":1743119665751,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030930455"},{"type":"electronic","value":"9783030930462"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-93046-2_39","type":"book-chapter","created":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T05:30:01Z","timestamp":1641015001000},"page":"456-468","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Dual Attention Feature Fusion Network for Monocular Depth Estimation"],"prefix":"10.1007","author":[{"given":"Yifang","family":"Xu","sequence":"first","affiliation":[]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[]},{"given":"Chenglei","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Sidan","family":"Du","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,1]]},"reference":[{"key":"39_CR1","unstructured":"Saxena, A., Chung, S.H., Ng, A.: Learning depth from single monocular images. In: NIPS (2005)"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Godard, C., Aodha, O.M., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR, pp. 6602\u20136611. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"39_CR3","doi-asserted-by":"publisher","unstructured":"Ranftl, R., Vineet, V., Chen, Q., Koltun, V.: Dense monocular depth estimation in complex dynamic scenes. In: CVPR, pp. 4058\u20134066. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.440","DOI":"10.1109\/CVPR.2016.440"},{"key":"39_CR4","doi-asserted-by":"publisher","unstructured":"Yang, J., Mao, W., Alvarez, J.M., Liu, M.: Cost volume pyramid based depth inference for multi-view stereo. In: CVPR, pp. 4876\u20134885. IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00493","DOI":"10.1109\/CVPR42600.2020.00493"},{"key":"39_CR5","unstructured":"Lee, J.H., Han, M., Ko, D.W., Suh, I.H.: From big to small: multi-scale local planar guidance for monocular depth estimation. CoRR abs\/1907.10326 (2019)"},{"key":"39_CR6","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: NIPS, pp. 2366\u20132374 (2014)"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: CVPR, pp. 2002\u20132011. IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"39_CR8","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the Kitti dataset. Int. J. Robot. Res. 32, 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"F\u00e1cil, J.M., Ummenhofer, B., Zhou, H., Montesano, L., Brox, T., Civera, J.: CAM-Convs: camera-aware multi-scale convolutions for single-view depth. In: CVPR, pp. 11826\u201311835. Computer Vision Foundation. IEEE (2019)","DOI":"10.1109\/CVPR.2019.01210"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, C.: Monocular depth estimation using relative depth maps. In: CVPR, pp. 9729\u20139738. Computer Vision Foundation\/IEEE (2019)","DOI":"10.1109\/CVPR.2019.00996"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.: Unsupervised learning of depth and ego-motion from video. In: CVPR, pp. 6612\u20136619 (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 2261\u20132269 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R.B., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR, pp. 5987\u20135995. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"39_CR15","unstructured":"Alhashim, I., Wonka, P.: High quality monocular depth estimation via transfer learning. CoRR abs\/1812.11941 (2018)"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Aich, S., Vianney, J.M.U., Islam, M.A., Kaur, M., Liu, B.: Bidirectional attention network for monocular depth estimation. CoRR abs\/2009.00743 (2020)","DOI":"10.1109\/ICRA48506.2021.9560885"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Chen, T., et al.: Improving monocular depth estimation by leveraging structural awareness and complementary datasets (2020)","DOI":"10.1007\/978-3-030-58568-6_6"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Ummenhofer, B., et al.: Demon: depth and motion network for learning monocular stereo. In: CVPR, pp. 5622\u20135631. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.596"},{"key":"39_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"39_CR20","doi-asserted-by":"publisher","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Make3D: learning 3D scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 824\u2013840 (2009). https:\/\/doi.org\/10.1109\/TPAMI.2008.132","DOI":"10.1109\/TPAMI.2008.132"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: 3DV, pp. 239\u2013248. IEEE Computer Society (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"39_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/978-3-030-20870-7_41","volume-title":"Computer Vision \u2013 ACCV 2018","author":"R Li","year":"2019","unstructured":"Li, R., Xian, K., Shen, C., Cao, Z., Lu, H., Hang, L.: Deep attention-based classification network for robust depth prediction. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11364, pp. 663\u2013678. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20870-7_41"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: ICCV, pp. 2650\u20132658. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Ramamonjisoa, M., Du, Y., Lepetit, V.: Predicting sharp and accurate occlusion boundaries in monocular depth estimation using displacement fields. In: CVPR, pp. 14636\u201314645. IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.01466"},{"key":"39_CR25","doi-asserted-by":"crossref","unstructured":"Xu, D., Ricci, E., Ouyang, W., Wang, X., Sebe, N.: Multi-scale continuous CRFS as sequential deep networks for monocular depth estimation. In: CVPR, pp. 161\u2013169. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.25"},{"key":"39_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-46484-8_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Garg","year":"2016","unstructured":"Garg, R., B.G., V.K., Carneiro, G., Reid, I.: Unsupervised CNN for single view depth estimation: geometry to the rescue. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 740\u2013756. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_45"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints. In: CVPR, pp. 5667\u20135675. IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00594"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, P., Wang, Y., Xu, W., Nevatia, R.: LEGO: learning edge with geometry all at once by watching videos. In: CVPR, pp. 225\u2013234. IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00031"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Zheng, C., Cham, T., Cai, J.: T2Net: synthetic-to-realistic translation for solving single-image depth estimation tasks. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01234-2_47"},{"key":"39_CR30","doi-asserted-by":"publisher","first-page":"1640","DOI":"10.1109\/TIFS.2019.2946938","volume":"15","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Guo, G.: LS-CNN: characterizing local patches at multiple scales for face recognition. IEEE Trans. Inf. Forensics Secur. 15, 1640\u20131653 (2020)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"39_CR31","doi-asserted-by":"publisher","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132\u20137141. IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"3","key":"39_CR32","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"IJCV"},{"key":"39_CR33","doi-asserted-by":"crossref","unstructured":"Kong, S., Fowlkes, C.C.: Pixel-wise attentional gating for parsimonious pixel labeling. CoRR abs\/1805.01556 (2018)","DOI":"10.1109\/WACV.2019.00114"},{"key":"39_CR34","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) ICLR (2015)"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-93046-2_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,18]],"date-time":"2022-06-18T08:08:26Z","timestamp":1655539706000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-93046-2_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030930455","9783030930462"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-93046-2_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"1 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"307","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":"105","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":"34% - 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":"3.2","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":"5.3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}