{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T01:26:50Z","timestamp":1769650010127,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819530601","type":"print"},{"value":"9789819530618","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-3061-8_12","type":"book-chapter","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T05:02:39Z","timestamp":1762923759000},"page":"105-115","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TRVP: Transformer-VAE Framework for\u00a03D Point Cloud Instance Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7820-2506","authenticated-orcid":false,"given":"Jiangmai","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1402-7947","authenticated-orcid":false,"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2536-3302","authenticated-orcid":false,"given":"Tianfang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3789-0128","authenticated-orcid":false,"given":"Boyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,13]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Armeni, I., Sener, O., Zamir, A. R., Jiang, H., Brilakis, I., Fischer, M., et al.: 3d semantic parsing of large-scale indoor spaces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1534-1543 (2016)","DOI":"10.1109\/CVPR.2016.170"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Bozic, V., Dordevic, D., Coppola, D., Thommes, J., Singh, S.P.: Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformer. arXiv preprint arXiv:2311.10642 (2023)","DOI":"10.1609\/aaai.v38i21.30436"},{"key":"12_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"12_CR4","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828-5839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"12_CR5","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., et al.: An Image is Worth 16x16 Words: Transformer for Image Recognition at Scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Fan, H., Yang, Y., Kankanhalli, M.: Point 4d transformer networks for spatio-temporal modeling in point cloud videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14204-14213 (2021)","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Guan, T., Wang, J., Lan, S., Chandra, R., Wu, Z., Davis, L., et al.: M3detr: multi-representation, multi-scale, mutual-relation 3d object detection with transformers. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 772-782 (2022)","DOI":"10.1109\/WACV51458.2022.00235"},{"key":"12_CR8","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","volume":"7","author":"M-H Guo","year":"2021","unstructured":"Guo, M.-H., Cai, J.-X., Liu, Z.-N., Mu, T.-J., Martin, R.R., Hu, S.-M.: Pct: point cloud transformer. Comput. Vis. Media 7, 187\u2013199 (2021)","journal-title":"Comput. Vis. Media"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961-2969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"12_CR10","unstructured":"Ilbert, R., et al.: Samformer: Unlocking the potential of transformers in time series forecasting with sharpness-aware minimization and channel-wise attention. arXiv preprint arXiv:2402.10198 (2024)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Lahoud, J., Ghanem, B.: 2d-driven 3d object detection in rgb-d images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4622-4630 (2017)","DOI":"10.1109\/ICCV.2017.495"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Lai, X., Yuan, Y., Chu, R., Chen, Y., Hu, H., Jia, J.: Mask-attention-free transformer for 3d instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3693-3703 (2023)","DOI":"10.1109\/ICCV51070.2023.00342"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, M., Liu, H., Wang, P., Cai, J., Sebe, N.: Hourglass tokenizer for efficient transformer-based 3D human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 604-613 (2024)","DOI":"10.1109\/CVPR52733.2024.00064"},{"key":"12_CR14","first-page":"12934","volume":"35","author":"Y Li","year":"2022","unstructured":"Li, Y., Yuan, G., Wen, Y., Hu, J., Evangelidis, G., Tulyakov, S., et al.: Efficientformer: vision transformers at mobilenet speed. Adv. Neural. Inf. Process. Syst. 35, 12934\u201312949 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012-10022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"12","key":"12_CR16","doi-asserted-by":"publisher","first-page":"24854","DOI":"10.1109\/TITS.2022.3198836","volume":"23","author":"D Lu","year":"2022","unstructured":"Lu, D., Xie, Q., Gao, K., Xu, L., Li, J.: 3DCTN: 3D convolution-transformer network for point cloud classification. IEEE Trans. Intell. Transp. Syst. 23(12), 24854\u201324865 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"12_CR17","unstructured":"Lu, D., Xie, Q., Wei, M., Gao, K., Xu, L., Li, J.: Transformer in 3d point clouds: A survey. arXiv preprint arXiv:2205.07417 (2022b)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Mo, K., et al. Partnet: a large-scale benchmark for fine-grained and hierarchical part-level 3d object understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 909-918 (2019)","DOI":"10.1109\/CVPR.2019.00100"},{"key":"12_CR19","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, pp. 652-660 (2017a)"},{"key":"12_CR20","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 (2017b)"},{"key":"12_CR21","unstructured":"Ross, T.-Y., Doll\u00e1r, G.: Focal loss for dense object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2980-2988 (2017)"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X.,Li, H.: Pointrcnn: 3d object proposal generation and detection from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770-779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"12_CR23","unstructured":"Vaswani, A.: Attention is all you need. Adv. Neural Inform. Process. Syst. (2017)"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Wang, W., Yu, R., Huang, Q., Neumann, U.: Sgpn: Similarity group proposal network for 3d point cloud instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2569-2578 (2018)","DOI":"10.1109\/CVPR.2018.00272"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X., Liu, S., Shen, X., Shen, C., Jia, J.: Associatively segmenting instances and semantics in point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4096-4105 (2019)","DOI":"10.1109\/CVPR.2019.00422"},{"key":"12_CR26","unstructured":"Yang, B., et al.: Learning object bounding boxes for 3d instance segmentation on point clouds. Adv. Neural Inform. Process. Syst. 32 (2019)"},{"key":"12_CR27","unstructured":"Yuan, W., Gu, X., Li, H., Dong, Z., Zhu, S.: 3D Former: Monocular Scene Reconstruction with 3D SDF Transformer. arXiv preprint arXiv:2301.13510 (2023)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Ram, D., Hawkins, C., Zha, S., Zhao, T.: Efficient long-range transformers: You need to attend more, but not necessarily at every layer. arXiv preprint arXiv:2310.12442 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.183"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P. H., Koltun, V.: Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16259-16268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"12_CR30","unstructured":"Zhong-yu, C., Wan, H., Liu, S., Shen, X., Wu, Z.: PVT: Point-Voxel Transformer for 3D Deep Learning. arXiv preprint arXiv:2108.06076 (2021)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3061-8_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T12:14:24Z","timestamp":1769602464000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3061-8_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,13]]},"ISBN":["9789819530601","9789819530618"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3061-8_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,13]]},"assertion":[{"value":"13 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2025.scimeeting.cn\/en\/web\/index\/27434","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}