{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:33:38Z","timestamp":1743003218193,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785070"},{"type":"electronic","value":"9789819785087"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8508-7_33","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:08:14Z","timestamp":1730527694000},"page":"476-490","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross Modality Fusion Network with\u00a0Feature Alignment and\u00a0Salient Object Exchange for\u00a0Single Image 3D Shape Retrieval"],"prefix":"10.1007","author":[{"given":"Zhenyu","family":"Diao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongmei","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofan","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiuyang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Aubry, M., Russell, B.C.: Understanding deep features with computer-generated imagery. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2875\u20132883 (2015)","DOI":"10.1109\/ICCV.2015.329"},{"key":"33_CR2","unstructured":"Chang, A.X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et\u00a0al.: Shapenet: an information-rich 3D model repository (2015). arXiv preprint arXiv:1512.03012"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Feng, Y., Zhang, Z., Zhao, X., Ji, R., Gao, Y.: GVCNN: group-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 264\u2013272 (2018)","DOI":"10.1109\/CVPR.2018.00035"},{"key":"33_CR4","first-page":"14675","volume":"33","author":"H Fu","year":"2020","unstructured":"Fu, H., Li, S., Jia, R., Gong, M., Zhao, B., Tao, D.: Hard example generation by texture synthesis for cross-domain shape similarity learning. Adv. Neural. Inf. Process. Syst. 33, 14675\u201314687 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR5","first-page":"1","volume":"2021","author":"XY Gao","year":"2021","unstructured":"Gao, X.Y., Li, K.P., Zhang, C.X., Yu, B.: 3D model classification based on Bayesian classifier with AdaBoost. Discret. Dyn. Nat. Soc. 2021, 1\u201312 (2021)","journal-title":"Discret. Dyn. Nat. Soc."},{"issue":"4","key":"33_CR6","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.1109\/TCSVT.2021.3091581","volume":"32","author":"Z Gao","year":"2021","unstructured":"Gao, Z., Zhang, Y., Zhang, H., Guan, W., Feng, D., Chen, S.: Multi-level view associative convolution network for view-based 3D model retrieval. IEEE Trans. Circ. Syst. Video Technol. 32(4), 2264\u20132278 (2021)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Grabner, A., Roth, P.M., Lepetit, V.: 3D pose estimation and 3D model retrieval for objects in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3022\u20133031 (2018)","DOI":"10.1109\/CVPR.2018.00319"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Grabner, A., Roth, P.M., Lepetit, V.: Location field descriptors: single image 3D model retrieval in the wild. In: 2019 International Conference on 3D vision (3DV), pp. 583\u2013593. IEEE (2019)","DOI":"10.1109\/3DV.2019.00070"},{"key":"33_CR9","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila Pires, B., Guo, Z., Gheshlaghi Azar, M., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"7","key":"33_CR10","doi-asserted-by":"publisher","first-page":"3499","DOI":"10.1007\/s00521-023-09279-1","volume":"36","author":"Q Guo","year":"2024","unstructured":"Guo, Q., He, F., Fan, B., Song, Y., Dai, J., Fan, L.: Walkformer: 3D mesh analysis via transformer on random walk. Neural Comput. Appl. 36(7), 3499\u20133511 (2024)","journal-title":"Neural Comput. Appl."},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Hamdi, A., Giancola, S., Ghanem, B.: MVTN: multi-view transformation network for 3D shape recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1\u201311 (2021)","DOI":"10.1109\/ICCV48922.2021.00007"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"issue":"11","key":"33_CR13","doi-asserted-by":"publisher","first-page":"8010","DOI":"10.1109\/TCSVT.2022.3182533","volume":"32","author":"N Hu","year":"2022","unstructured":"Hu, N., Zhou, H., Huang, X., Li, X., Liu, A.A.: A feature transformation framework with selective pseudo-labeling for 2D image-based 3D shape retrieval. IEEE Trans. Circ. Syst. Video Technol. 32(11), 8010\u20138021 (2022)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"33_CR14","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.T., Parekh, Z., Pham, H., Le, Q., Sung, Y.H., Li, Z., Duerig, T.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Kanezaki, A., Matsushita, Y., Nishida, Y.: Rotationnet: joint object categorization and pose estimation using multiviews from unsupervised viewpoints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5010\u20135019 (2018)","DOI":"10.1109\/CVPR.2018.00526"},{"key":"33_CR16","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., Krishnan, D.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661\u201318673 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR17","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Li, T.B., Liu, A.A., Song, D., Li, W.H., Li, X.Y., Su, Y.T.: Focus on hard samples: hierarchical unbiased constraints for cross-domain 3D model retrieval. IEEE Trans. Circ. Syst. Video Technol. (2023)","DOI":"10.1109\/TCSVT.2023.3266920"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Li, T.B., Su, Y.T., Song, D., Li, W.H., Wei, Z.Q., Liu, A.A.: Progressive Fourier adversarial domain adaptation for object classification and retrieval. IEEE Trans. Multimedia (2023)","DOI":"10.1109\/TMM.2023.3323862"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, Y., Wang, F., Li, X., Duan, Y., Liu, A.A.: Instance-prototype similarity consistency for unsupervised 2D image-based 3D model retrieval. Inform. Process. Manag. 60(4), 103372 (2023)","DOI":"10.1016\/j.ipm.2023.103372"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., Seah, H.S., Guo, B., Yang, M.: MLGPnet: multi-granularity neural network for 3D shape recognition using pyramid data. Comput. Vis. Image Underst. 239, 103904 (2024)","DOI":"10.1016\/j.cviu.2023.103904"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Lin, M.X., Yang, J., Wang, H., Lai, Y.K., Jia, R., Zhao, B., Gao, L.: Single image 3D shape retrieval via cross-modal instance and category contrastive learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11405\u201311415 (2021)","DOI":"10.1109\/ICCV48922.2021.01121"},{"issue":"4","key":"33_CR23","doi-asserted-by":"publisher","first-page":"1995","DOI":"10.1007\/s00530-023-01086-x","volume":"29","author":"AA Liu","year":"2023","unstructured":"Liu, A.A., Zhang, Y., Zhang, C., Li, W., Lv, B., Lei, L., Li, X.: Prototype-based semantic consistency learning for unsupervised 2D image-based 3D shape retrieval. Multimedia Syst. 29(4), 1995\u20132007 (2023)","journal-title":"Multimedia Syst."},{"issue":"2","key":"33_CR24","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1007\/s00371-023-02826-w","volume":"40","author":"H Liu","year":"2024","unstructured":"Liu, H., Tian, S.: Deep 3D point cloud classification and segmentation network based on GateNet. Vis. Comput. 40(2), 971\u2013981 (2024)","journal-title":"Vis. Comput."},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Maturana, D., Scherer, S.: Voxnet: a 3D convolutional neural network for real-time object recognition. In: 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922\u2013928. IEEE (2015)","DOI":"10.1109\/IROS.2015.7353481"},{"key":"33_CR26","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"33_CR27","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"33_CR28","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.cag.2023.06.033","volume":"115","author":"D Song","year":"2023","unstructured":"Song, D., Jiang, X.J., Zhang, Y., Zhang, F.L., Jin, Y., Zhang, Y.: Domain-specific modeling and semantic alignment for image-based 3D model retrieval. Comput. Graph. 115, 25\u201334 (2023)","journal-title":"Comput. Graph."},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Song, D., Yang, Y., Li, W., Shao, Z., Nie, W., Li, X., Liu, A.A.: Adaptive semantic transfer network for unsupervised 2D image-based 3D model retrieval. Comput. Vis. Image Underst. 238, 103858 (2024)","DOI":"10.1016\/j.cviu.2023.103858"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 945\u2013953 (2015)","DOI":"10.1109\/ICCV.2015.114"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Sun, X., Wu, J., Zhang, X., Zhang, Z., Zhang, C., Xue, T., Tenenbaum, J.B., Freeman, W.T.: Pix3D: dataset and methods for single-image 3D shape modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2974\u20132983 (2018)","DOI":"10.1109\/CVPR.2018.00314"},{"key":"33_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Y., Tan, X., Yang, Y., Liu, X., Ding, E., Zhou, F., Davis, L.S.: 3D pose estimation for fine-grained object categories. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops, pp.\u00a00\u20130 (2018)","DOI":"10.1007\/978-3-030-11009-3_38"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Wei, X., Yu, R., Sun, J.: Learning view-based graph convolutional network for multi-view 3D shape analysis. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3221785"},{"key":"33_CR34","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J.: 3D shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912\u20131920 (2015)"},{"key":"33_CR35","first-page":"1","volume":"19","author":"S Xu","year":"2022","unstructured":"Xu, S., Zhou, X., Ye, W., Ye, Q.: Classification of 3D point clouds by a new augmentation convolutional neural network. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2022)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"33_CR36","doi-asserted-by":"crossref","unstructured":"Xu, X., Todorovic, S.: Beam search for learning a deep convolutional neural network of 3D shapes. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 3506\u20133511. IEEE (2016)","DOI":"10.1109\/ICPR.2016.7900177"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Xuan, H., Stylianou, A., Pless, R.: Improved embeddings with easy positive triplet mining. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2474\u20132482 (2020)","DOI":"10.1109\/WACV45572.2020.9093432"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Xue, L., Gao, M., Xing, C., Mart\u00edn-Mart\u00edn, R., Wu, J., Xiong, C., Xu, R., Niebles, J.C., Savarese, S.: ULIP: learning a unified representation of language, images, and point clouds for 3D understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1179\u20131189 (2023)","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"33_CR39","doi-asserted-by":"crossref","unstructured":"Yang, J., Duan, J., Tran, S., Xu, Y., Chanda, S., Chen, L., Zeng, B., Chilimbi, T., Huang, J.: Vision-language pre-training with triple contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15671\u201315680 (2022)","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"33_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, H.: Deep cross-modal projection learning for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 686\u2013701 (2018)","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"33_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Liu, Y., Song, D., Li, J., Li, X., Liu, A.A.: Cross-domain prototype contrastive loss for few-shot 2D image-based 3D model retrieval. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 2897\u20132902. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00492"},{"key":"33_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Liu, Y., Xiao, J., Liu, M., Li, X., Liu, A.A.: Unsupervised self-training correction learning for 2D image-based 3D model retrieval. Inform. Process. Manag. 60(4), 103351 (2023)","DOI":"10.1016\/j.ipm.2023.103351"}],"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\/978-981-97-8508-7_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:18:37Z","timestamp":1730528317000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8508-7_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785070","9789819785087"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8508-7_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","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":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}