{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T23:58:55Z","timestamp":1768435135611,"version":"3.49.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T00:00:00Z","timestamp":1670889600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T00:00:00Z","timestamp":1670889600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Fundamental Research Funds for the Central Universities","award":["PA2021KCPY0041"],"award-info":[{"award-number":["PA2021KCPY0041"]}]},{"name":"Innovation Project of New Energy Vehicle and Intelligent Connected Vehicle of Anhui Province"},{"name":"The University Synergy Innovation Program of Anhui Province","award":["GXXT-2020-076"],"award-info":[{"award-number":["GXXT-2020-076"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s00371-022-02734-5","type":"journal-article","created":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T07:02:55Z","timestamp":1670914975000},"page":"6367-6377","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Based on real and virtual datasets adaptive joint training in multi-modal networks with applications in monocular 3D target detection"],"prefix":"10.1007","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7318-1365","authenticated-orcid":false,"given":"Teng","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junning","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengchao","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,13]]},"reference":[{"key":"2734_CR1","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. Arxiv preprint (2018). arXiv:1804.02767"},{"key":"2734_CR2","doi-asserted-by":"publisher","first-page":"3171","DOI":"10.1109\/TCYB.2017.2761775","volume":"48","author":"J Han","year":"2017","unstructured":"Han, J., Chen, H., Liu, N., Yan, C., Li, X.: CNNs-based RGB-D saliency detection via cross-view transfer and multiview fusion. IEEE Trans. Cybern. 48, 3171\u20133183 (2017)","journal-title":"IEEE Trans. Cybern."},{"key":"2734_CR3","unstructured":"Hackett, J.K., Shah, M.: Multi-sensor fusion: A perspective. In: Proceedings of the IEEE International  Conference on Robotics and Automation, pp. 1324\u20131330 (1990)"},{"key":"2734_CR4","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.jvcir.2018.01.013","volume":"52","author":"G Zhang","year":"2018","unstructured":"Zhang, G., Liu, J., Liu, Y., Zhao, J., Tian, L., Chen, Y.Q.: Physical blob detector and multi-channel color shape descriptor for human detection. J. Vis. Commun. Image Represent. 52, 13\u201323 (2018)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"2734_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, G., Liu, J., Tian, L., Chen, Y.Q.: Reliably detecting humans with RGB-D camera with physical blob detector followed by learning-based filtering. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 2004\u20132008. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472028"},{"key":"2734_CR6","doi-asserted-by":"publisher","first-page":"1666","DOI":"10.1109\/LSP.2017.2731952","volume":"24","author":"G Zhang","year":"2017","unstructured":"Zhang, G., Liu, J., Li, H., Chen, Y.Q., Davis, L.S.: Joint human detection and head pose estimation via multistream networks for RGB-D videos. IEEE Signal Process. Lett. 24, 1666\u20131670 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"2734_CR7","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/s00371-018-1471-4","volume":"35","author":"X Zhou","year":"2019","unstructured":"Zhou, X., Wang, Y., Zhu, Q., Xiao, C., Lu, X.: SSG: Superpixel segmentation and grabcut-based salient object segmentation. Vis. Comput. 35, 385\u2013398 (2019)","journal-title":"Vis. Comput."},{"key":"2734_CR8","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1007\/s00371-018-1477-y","volume":"34","author":"J Zhao","year":"2018","unstructured":"Zhao, J., Mao, X., Zhang, J.: Learning deep facial expression features from image and optical flow sequences using 3D CNN. Vis. Comput. 34, 1461\u20131475 (2018)","journal-title":"Vis. Comput."},{"key":"2734_CR9","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1007\/s00371-018-1477-y","volume":"34","author":"J Zhao","year":"2018","unstructured":"Berlin, S.J., John, M.: Spiking neural network based on joint entropy of optical flow features for human action recognition. Vis. Comput. 38, 223\u2013237 (2022)","journal-title":"Vis. Comput."},{"key":"2734_CR10","doi-asserted-by":"publisher","unstructured":"He, D., He, X., Yuan, R., Li, Y., Shen, C.: Lightweight network-based multi-modal feature fusion for face anti-spoofing. Vis. Comput. (2022). https:\/\/doi.org\/10.1007\/s00371-022-02420-6","DOI":"10.1007\/s00371-022-02420-6"},{"key":"2734_CR11","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s00371-012-0741-9","volume":"29","author":"K Ahmadian","year":"2013","unstructured":"Ahmadian, K., Gavrilova, M.: A multi-modal approach for high-dimensional feature recognition. Vis. Comput. 29, 123\u2013130 (2013)","journal-title":"Vis. Comput."},{"key":"2734_CR12","doi-asserted-by":"publisher","first-page":"1871","DOI":"10.1007\/s00371-021-02246-8","volume":"38","author":"Y Ding","year":"2022","unstructured":"Ding, Y., Duan, Z., Li, S.: Source-free unsupervised multi-source domain adaptation via proxy task for person re-identification. Vis. Comput. 38, 1871\u20131882 (2022)","journal-title":"Vis. Comput."},{"key":"2734_CR13","doi-asserted-by":"crossref","unstructured":"Li, P., Chen, X., Shen, S.: Stereo R-CNN based 3d object detection for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7644\u20137652 (2019)","DOI":"10.1109\/CVPR.2019.00783"},{"key":"2734_CR14","doi-asserted-by":"crossref","unstructured":"Qin, Z., Wang, J., Lu, Y.: Monogrnet: A geometric reasoning network for monocular 3d object localization. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 8851\u20138858 (2019)","DOI":"10.1609\/aaai.v33i01.33018851"},{"key":"2734_CR15","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.1007\/s12555-019-1014-4","volume":"19","author":"J Park","year":"2021","unstructured":"Park, J., Jung, D.-J.: Deep convolutional neural network architectures for tonal frequency identification in a lofargram. Int. J. Control Autom. Syst. 19, 1103\u20131112 (2021)","journal-title":"Int. J. Control Autom. Syst."},{"key":"2734_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, Z., T\u00f3th, R.: Smoke: Single-stage monocular 3d object detection via keypoint estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 996\u2013997 (2020)","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"2734_CR17","doi-asserted-by":"publisher","unstructured":"Zhang, J., Su, Q., Tang, B., Wang, C., Li, Y.: DPSNet: Multitask learning using geometry reasoning for scene depth and semantics. IEEE Trans. Neural Netw. Learn. Syst. (2021). https:\/\/doi.org\/10.1109\/TNNLS.2021.3107362","DOI":"10.1109\/TNNLS.2021.3107362"},{"key":"2734_CR18","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.neucom.2020.03.076","volume":"403","author":"J Zhang","year":"2020","unstructured":"Zhang, J., Su, Q., Wang, C., Gu, H.: Monocular 3D vehicle detection with multi-instance depth and geometry reasoning for autonomous driving. Neurocomputing 403, 182\u2013192 (2020)","journal-title":"Neurocomputing"},{"key":"2734_CR19","doi-asserted-by":"publisher","first-page":"2567","DOI":"10.1007\/s00371-021-02206-2","volume":"37","author":"Y Li","year":"2021","unstructured":"Li, Y., Luo, F., Li, W., Zheng, S., Wu, H., Xiao, C.: Self-supervised monocular depth estimation based on image texture detail enhancement. Vis. Comput. 37, 2567\u20132580 (2021)","journal-title":"Vis. Comput."},{"key":"2734_CR20","doi-asserted-by":"crossref","unstructured":"Ding, P., Shen, Q., Huang, T., Wang, M.: A generation method and verification of virtual dataset. In: International Conference on Man-Machine-Environment System Engineering. pp. 469\u2013475. Springer (2020)","DOI":"10.1007\/978-981-15-6978-4_55"},{"key":"2734_CR21","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","volume":"109","author":"F Zhuang","year":"2020","unstructured":"Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., He, Q.: A comprehensive survey on transfer learning. Proc. IEEE 109, 43\u201376 (2020)","journal-title":"Proc. IEEE"},{"key":"2734_CR22","doi-asserted-by":"publisher","first-page":"1522","DOI":"10.2514\/2.7480","volume":"35","author":"H Luo","year":"1997","unstructured":"Luo, H., Hanagud, S.: Dynamic learning rate neural network training and composite structural damage detection. AIAA J. 35, 1522\u20131527 (1997)","journal-title":"AIAA J."},{"key":"2734_CR23","doi-asserted-by":"crossref","unstructured":"Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V., Garcia-Rodriguez, J.: A review on deep learning techniques applied to semantic segmentation. arXiv preprint arXiv:1704.06857. (2017)","DOI":"10.1016\/j.asoc.2018.05.018"},{"key":"2734_CR24","doi-asserted-by":"crossref","unstructured":"Vu, T.-H., Jain, H., Bucher, M., Cord, M., P\u00e9rez, P.: Dada: Depth-aware domain adaptation in semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 7364\u20137373 (2019)","DOI":"10.1109\/ICCV.2019.00746"},{"key":"2734_CR25","doi-asserted-by":"crossref","unstructured":"Yu, F., Wang, D., Shelhamer, E., Darrell, T.: Deep layer aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2403\u20132412 (2018)","DOI":"10.1109\/CVPR.2018.00255"},{"key":"2734_CR26","unstructured":"Li, B., Zhang, T., Xia, T.: Vehicle detection from 3d lidar using fully convolutional network. arXiv preprint arXiv:1608.07916. (2016)"},{"key":"2734_CR27","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. (2014)"},{"key":"2734_CR28","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017)"},{"key":"2734_CR29","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.M.: The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3234\u20133243 (2016)","DOI":"10.1109\/CVPR.2016.352"},{"key":"2734_CR30","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":"2734_CR31","unstructured":"Chen, X., Kundu, K., Zhu, Y., Berneshawi, A.G., Ma, H., Fidler, S., Urtasun, R.: 3d object proposals for accurate object class detection. Adv Neural Inf. Process. Syst. 28, 424\u2013432 (2015)"},{"key":"2734_CR32","doi-asserted-by":"crossref","unstructured":"Manhardt, F., Kehl, W., Gaidon, A.: Roi-10d: Monocular lifting of 2d detection to 6d pose and metric shape. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2069\u20132078 (2019)","DOI":"10.1109\/CVPR.2019.00217"},{"key":"2734_CR33","doi-asserted-by":"crossref","unstructured":"Li, P., Zhao, H., Liu, P., Cao, F.: RTM3D: Real-time monocular 3d detection from object keypoints for autonomous driving. In: European Conference on Computer Vision. pp. 644\u2013660. Springer (2020)","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"2734_CR34","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tai, L., Sun, K., Li, M.: Monopair: Monocular 3d object detection using pairwise spatial relationships. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12093\u201312102 (2020)","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"2734_CR35","doi-asserted-by":"crossref","unstructured":"Ding, M., Huo, Y., Yi, H., Wang, Z., Shi, J., Lu, Z., Luo, P.: Learning depth-guided convolutions for monocular 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 1000\u20131001 (2020)","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"2734_CR36","doi-asserted-by":"crossref","unstructured":"Brazil, G., Pons-Moll, G., Liu, X., Schiele, B.: Kinematic 3d object detection in monocular video. In: European Conference on Computer Vision. pp. 135\u2013152. Springer (2020)","DOI":"10.1007\/978-3-030-58592-1_9"},{"key":"2734_CR37","doi-asserted-by":"crossref","unstructured":"Qin, Z., Wang, J., Lu, Y.: Monogrnet: A general framework for monocular 3d object detection. IEEE Trans. Pattern Anal. Mach. Intell. 44, 5170\u20135184 (2022)","DOI":"10.1109\/TPAMI.2021.3074363"},{"key":"2734_CR38","doi-asserted-by":"publisher","first-page":"5565","DOI":"10.1109\/LRA.2021.3061343","volume":"6","author":"P Li","year":"2021","unstructured":"Li, P., Zhao, H.: Monocular 3d detection with geometric constraint embedding and semi-supervised training. IEEE Robot. Autom. Lett. 6, 5565\u20135572 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2734_CR39","doi-asserted-by":"crossref","unstructured":"Kumar, A., Brazil, G., Liu, X.: GrooMeD-NMS: Grouped mathematically differentiable NMS for monocular 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8973\u20138983 (2021)","DOI":"10.1109\/CVPR46437.2021.00886"},{"key":"2734_CR40","doi-asserted-by":"crossref","unstructured":"Shi, X., Ye, Q., Chen, X., Chen, C., Chen, Z., Kim, T.-K.: Geometry-based distance decomposition for monocular 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 15172\u201315181 (2021)","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"2734_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Du, L., Ye, X., Zou, Z., Tan, X., Ding, E., Zhang, L., Xue, X., Feng, J.: SGM3D: Stereo guided monocular 3D object detection. IEEE Robot. Autom. Lett. arXiv preprint arXiv:2112.01914. (2021)","DOI":"10.1109\/LRA.2022.3191849"},{"key":"2734_CR42","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhou, D., Lu, F., Fang, J., Zhang, L.: Autoshape: Real-time shape-aware monocular 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 15641\u201315650 (2021)","DOI":"10.1109\/ICCV48922.2021.01535"},{"key":"2734_CR43","unstructured":"Liu, C., Gu, S., Van Gool, L., Timofte, R.: Deep line encoding for monocular 3d object detection and depth prediction. In: 32nd British Machine Vision Conference (BMVC 2021). p. 354 (2021)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02734-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-022-02734-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02734-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T12:09:05Z","timestamp":1699531745000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-022-02734-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,13]]},"references-count":43,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["2734"],"URL":"https:\/\/doi.org\/10.1007\/s00371-022-02734-5","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,13]]},"assertion":[{"value":"16 November 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors certify that there is no conflict of interest with any individual\/organization for the present work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}