{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T18:37:39Z","timestamp":1743014259090,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031784552"},{"type":"electronic","value":"9783031784569"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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\/978-3-031-78456-9_1","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T11:23:28Z","timestamp":1733138608000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Depth-Enhanced Alignment for\u00a0Label-Free 3D Semantic Segmentation"],"prefix":"10.1007","author":[{"given":"Shangjin","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zibo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Xu, J., Zhang, R., Dou, J., Zhu, Y., Sun, J., Pu, S.: Rpvnet: a deep and efficient range-point-voxel fusion network for lidar point cloud segmentation. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 16004\u201316013 (2021)","key":"1_CR1","DOI":"10.1109\/ICCV48922.2021.01572"},{"doi-asserted-by":"crossref","unstructured":"Ando, A., Gidaris, S., Bursuc, A., Puy, G., Boulch, A., Marlet, R.: Rangevit: towards vision transformers for 3D semantic segmentation in autonomous driving. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5240\u20135250 (2023)","key":"1_CR2","DOI":"10.1109\/CVPR52729.2023.00507"},{"doi-asserted-by":"crossref","unstructured":"\u00dcckermann, A., Haschke, R., Ritter, H.: Real-time 3D segmentation of cluttered scenes for robot grasping. In: 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012), pp. 198\u2013203. IEEE (2012)","key":"1_CR3","DOI":"10.1109\/HUMANOIDS.2012.6651520"},{"doi-asserted-by":"crossref","unstructured":"\u00dcckermann, A., Elbrechter, C., Haschke, R., Ritter, H.: 3D scene segmentation for autonomous robot grasping. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1734\u20131740. IEEE (2012)","key":"1_CR4","DOI":"10.1109\/IROS.2012.6385692"},{"doi-asserted-by":"crossref","unstructured":"\u00dcckermann, A., Haschke, R., Ritter, H.: Realtime 3D segmentation for human-robot interaction. In: 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 2136\u20132143. IEEE (2013)","key":"1_CR5","DOI":"10.1109\/IROS.2013.6696655"},{"doi-asserted-by":"crossref","unstructured":"Guo, Y., Wang, H., Hu, Q., Liu, H., Liu, L., Bennamoun, M.: Deep learning for 3D point clouds: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2020)","key":"1_CR6","DOI":"10.1109\/TPAMI.2020.3005434"},{"unstructured":"Yang, Y.-Q., et al.: Swin3d: a pretrained transformer backbone for 3D indoor scene understanding. arXiv, vol. abs\/2304.06906 (2023)","key":"1_CR7"},{"key":"1_CR8","doi-asserted-by":"publisher","first-page":"134826","DOI":"10.1109\/ACCESS.2021.3116304","volume":"9","author":"N Engel","year":"2020","unstructured":"Engel, N., Belagiannis, V., Dietmayer, K.C.J.: Point transformer. IEEE Access 9, 134826\u2013134840 (2020)","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Chen, R., et al.: Clip2scene: towards label-efficient 3D scene understanding by clip. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7020\u20137030 (2023)","key":"1_CR9","DOI":"10.1109\/CVPR52729.2023.00678"},{"doi-asserted-by":"crossref","unstructured":"Zhang, J., Dong, R., Ma, K.: Clip-fo3d: learning free open-world 3D scene representations from 2D dense clip. arXiv, vol. abs\/2303.04748 (2023)","key":"1_CR10","DOI":"10.1109\/ICCVW60793.2023.00219"},{"unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)","key":"1_CR11"},{"key":"1_CR12","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1109\/LGRS.2018.2802944","volume":"15","author":"Z Zhang","year":"2017","unstructured":"Zhang, Z., Liu, Q., Wang, Y.: Road extraction by deep residual u-net. IEEE Geosci. Remote Sens. Lett. 15, 749\u2013753 (2017)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"unstructured":"Hu, X., Zhang, C., Zhang, Y., Hai, B., Yu, K., He, Z.: Learning to adapt clip for few-shot monocular depth estimation. arXiv, vol. abs\/2311.01034 (2023)","key":"1_CR13"},{"doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Pointclip: point cloud understanding by clip. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8542\u20138552 (2021)","key":"1_CR14","DOI":"10.1109\/CVPR52688.2022.00836"},{"doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: Scannet: richly-annotated 3D reconstructions of indoor scenes. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2432\u20132443 (2017)","key":"1_CR15","DOI":"10.1109\/CVPR.2017.261"},{"doi-asserted-by":"crossref","unstructured":"Fang, H., Wang, C., Gou, M., Lu, C.: Graspnet-1billion: a large-scale benchmark for general object grasping. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11441\u201311450 (2020)","key":"1_CR16","DOI":"10.1109\/CVPR42600.2020.01146"},{"doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G., Dai, D.: Decoupling zero-shot semantic segmentation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11573\u201311582 (2021)","key":"1_CR17","DOI":"10.1109\/CVPR52688.2022.01129"},{"unstructured":"Xu, M., et al.: A simple baseline for zero-shot semantic segmentation with pre-trained vision-language model. arXiv, vol. abs\/2112.14757 (2021)","key":"1_CR18"},{"doi-asserted-by":"crossref","unstructured":"Zhou, Z., Lei, Y., Zhang, B., Liu, L., Liu, Y.: Zegclip: towards adapting clip for zero-shot semantic segmentation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11175\u201311185 (2022)","key":"1_CR19","DOI":"10.1109\/CVPR52729.2023.01075"},{"doi-asserted-by":"crossref","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from clip. In: European Conference on Computer Vision (2021)","key":"1_CR20","DOI":"10.1007\/978-3-031-19815-1_40"},{"doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Delving into shape-aware zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2999\u20133009 (2023)","key":"1_CR21","DOI":"10.1109\/CVPR52729.2023.00293"},{"doi-asserted-by":"crossref","unstructured":"Jiang, L., Zhao, H., Shi, S., Liu, S., Fu, C.-W., Jia, J.: Pointgroup: dual-set point grouping for 3D instance segmentation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4866\u20134875 (2020)","key":"1_CR22","DOI":"10.1109\/CVPR42600.2020.00492"},{"doi-asserted-by":"crossref","unstructured":"Qi, C. R., Chen, X., Litany, O., Guibas, L.J.: Imvotenet: boosting 3D object detection in point clouds with image votes. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4403\u20134412 (2020)","key":"1_CR23","DOI":"10.1109\/CVPR42600.2020.00446"},{"doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C., Deschaud, J.-E., Marcotegui, B., Goulette, F., Guibas, L.J.: Kpconv: flexible and deformable convolution for point clouds. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6410\u20136419 (2019)","key":"1_CR24","DOI":"10.1109\/ICCV.2019.00651"},{"doi-asserted-by":"crossref","unstructured":"Maturana, D., Scherer, S.A.: 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 (2015)","key":"1_CR25","DOI":"10.1109\/IROS.2015.7353481"},{"doi-asserted-by":"crossref","unstructured":"Choy, C.B., Gwak, J., Savarese, S.: 4D spatio-temporal convnets: minkowski convolutional neural networks. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3070\u20133079 (2019)","key":"1_CR26","DOI":"10.1109\/CVPR.2019.00319"},{"doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3D object detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4490\u20134499 (2017)","key":"1_CR27","DOI":"10.1109\/CVPR.2018.00472"},{"doi-asserted-by":"crossref","unstructured":"Hou, J., Graham, B., Nie\u00dfner, M., Xie, S.: Exploring data-efficient 3D scene understanding with contrastive scene contexts. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15582\u201315592 (2020)","key":"1_CR28","DOI":"10.1109\/CVPR46437.2021.01533"},{"doi-asserted-by":"crossref","unstructured":"Rozenberszki, D., Litany, O., Dai, A.: Language-grounded indoor 3D semantic segmentation in the wild, arXiv, vol. abs\/2204.07761 (2022)","key":"1_CR29","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"1_CR30","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/j.isprsjprs.2022.10.013","volume":"194","author":"B Tian","year":"2022","unstructured":"Tian, B., Luo, L., Zhao, H., Zhou, G.: Vibus: data-efficient 3D scene parsing with viewpoint bottleneck and uncertainty-spectrum modeling. ISPRS J. Photogramm. Remote. Sens. 194, 302\u2013318 (2022)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv, vol. abs\/2010.11929 (2020)","key":"1_CR31"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., Qi, X., Fu, C.-W.: One thing one click: a self-training approach for weakly supervised 3D semantic segmentation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1726\u20131736 (2021)","key":"1_CR32","DOI":"10.1109\/CVPR46437.2021.00177"},{"doi-asserted-by":"crossref","unstructured":"Wei, J., Lin, G., Yap, K.-H., Hung, T.-Y., Xie, L.: Multi-path region mining for weakly supervised 3D semantic segmentation on point clouds. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4383\u20134392 (2020)","key":"1_CR33","DOI":"10.1109\/CVPR42600.2020.00444"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78456-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T12:08:38Z","timestamp":1733141318000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78456-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031784552","9783031784569"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78456-9_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}