{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:25:20Z","timestamp":1742941520950,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031270659"},{"type":"electronic","value":"9783031270666"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-27066-6_22","type":"book-chapter","created":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T06:02:54Z","timestamp":1678255374000},"page":"308-324","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Convolutional Point Transformer"],"prefix":"10.1007","author":[{"given":"Chaitanya","family":"Kaul","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua","family":"Mitton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roderick","family":"Murray-Smith","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,9]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: GCNet: non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 1971\u20131980 (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"22_CR2","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":"22_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"issue":"2","key":"22_CR4","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. Compu. Visual Media 7(2), 187\u2013199 (2021). https:\/\/doi.org\/10.1007\/s41095-021-0229-5","journal-title":"Compu. Visual Media"},{"key":"22_CR5","unstructured":"Hassani, A., Walton, S., Shah, N., Abuduweili, A., Li, J., Shi, H.: escaping the big data paradigm with Compact Transformers. arXiv preprint arXiv:2104.05704 (2021)"},{"key":"22_CR6","unstructured":"Ho, J., Kalchbrenner, N., Weissenborn, D., Salimans, T.: Axial attention in multidimensional transformers. arXiv preprint arXiv:1912.12180 (2019)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Iida, H., Thai, D., Manjunatha, V., Iyyer, M.: Tabbie: pretrained representations of tabular data. arXiv preprint arXiv:2105.02584 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.270"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Kaul, C., Manandhar, S., Pears, N.: FocusNet: an attention-based fully convolutional network for medical image segmentation. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 455\u2013458. IEEE (2019)","DOI":"10.1109\/ISBI.2019.8759477"},{"key":"22_CR10","unstructured":"Kaul, C., Pears, N., Manandhar, S.: SAWNet: a spatially aware deep neural network for 3D point cloud processing. arXiv preprint arXiv:1905.07650 (2019)"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Kaul, C., Pears, N., Manandhar, S.: FatNet: A feature-attentive network for 3D point cloud processing. In: 2020 25th International Conference on Pattern Recognition (ICPR). pp. 7211\u20137218. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412731"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Klokov, R., Lempitsky, V.: Escape from cells: Deep KD-networks for the recognition of 3d point cloud models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 863\u2013872 (2017)","DOI":"10.1109\/ICCV.2017.99"},{"key":"22_CR13","doi-asserted-by":"publisher","unstructured":"Landrieu, L., Simonovsky, M.: Large-scale point cloud semantic segmentation with superpoint graphs. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4558\u20134567 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00479","DOI":"10.1109\/CVPR.2018.00479"},{"key":"22_CR14","unstructured":"Lee, J., Lee, Y., Kim, J., Kosiorek, A., Choi, S., Teh, Y.W.: Set transformer: a framework for attention-based permutation-invariant neural networks. In: International Conference on Machine Learning, pp. 3744\u20133753. PMLR (2019)"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., Chen, B.M., Lee, G.H.: SO-Net: self-organizing network for point cloud analysis. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9397\u20139406. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00979"},{"key":"22_CR16","first-page":"820","volume":"31","author":"Y Li","year":"2018","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: PointCNN: convolution on $$\\cal{X} $$-transformed points. Adv. Neural. Inf. Process. Syst. 31, 820\u2013830 (2018)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Liu, X., Han, Z., Liu, Y.S., Zwicker, M.: Point2sequence: learning the shape representation of 3D point clouds with an attention-based sequence to sequence network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8778\u20138785 (2019)","DOI":"10.1609\/aaai.v33i01.33018778"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Fan, B., Xiang, S., Pan, C.: Relation-shape convolutional neural network for point cloud analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8895\u20138904 (2019)","DOI":"10.1109\/CVPR.2019.00910"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1412\u20131421 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"22_CR21","doi-asserted-by":"publisher","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 (2015). https:\/\/doi.org\/10.1109\/IROS.2015.7353481","DOI":"10.1109\/IROS.2015.7353481"},{"key":"22_CR22","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\u2013660 (2017)"},{"key":"22_CR23","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: 30th Proceedings Conference on Advances in Neural Information Processing Systems (2017)"},{"key":"22_CR24","unstructured":"Rao, R.M., et al.: MSA transformer. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 8844\u20138856. PMLR (18\u201324 July 2021). https:\/\/proceedings.mlr.press\/v139\/rao21a.html"},{"key":"22_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-030-00928-1_48","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"AG Roy","year":"2018","unstructured":"Roy, A.G., Navab, N., Wachinger, C.: Concurrent spatial and channel squeeze & excitation in fully convolutional networks. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 421\u2013429. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00928-1_48"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Simonovsky, M., Komodakis, N.: Dynamic edge-conditioned filters in convolutional neural networks on graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3693\u20133702 (2017)","DOI":"10.1109\/CVPR.2017.11"},{"key":"22_CR27","unstructured":"Somepalli, G., Goldblum, M., Schwarzschild, A., Bruss, C.B., Goldstein, T.: Saint: improved neural networks for tabular data via row attention and contrastive pre-training. arXiv preprint arXiv:2106.01342 (2021)"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Su, H., et al.: SplatNet: sparse lattice networks for point cloud processing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2530\u20132539 (2018)","DOI":"10.1109\/CVPR.2018.00268"},{"key":"22_CR29","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":"22_CR30","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: KPConv: flexible and deformable convolution for point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6411\u20136420 (2019)","DOI":"10.1109\/ICCV.2019.00651"},{"key":"22_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"22_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/978-3-030-01225-0_4","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Wang","year":"2018","unstructured":"Wang, C., Samari, B., Siddiqi, K.: Local spectral graph convolution for point set feature learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 56\u201371. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_4"},{"issue":"5","key":"22_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graphics 38(5), 1\u201312 (2019)","journal-title":"ACM Trans. Graphics"},{"key":"22_CR34","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":"22_CR35","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CVT: introducing convolutions to vision transformers. arXiv preprint arXiv:2103.15808 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Wu, W., Qi, Z., Fuxin, L.: PointConv: Deep convolutional networks on 3D point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9621\u20139630 (2019)","DOI":"10.1109\/CVPR.2019.00985"},{"key":"22_CR37","unstructured":"Wu, Z., et al.: 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":"22_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1007\/978-3-030-01237-3_6","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Xu","year":"2018","unstructured":"Xu, Y., Fan, T., Xu, M., Zeng, L., Qiao, Yu.: SpiderCNN: deep learning on point sets with parameterized convolutional filters. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 90\u2013105. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_6"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Yan, X., Zheng, C., Li, Z., Wang, S., Cui, S.: PointASNL: robust point clouds processing using nonlocal neural networks with adaptive sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5589\u20135598 (2020)","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"22_CR40","doi-asserted-by":"publisher","unstructured":"Yi, L., et al.: A scalable active framework for region annotation in 3D shape collections. ACM Trans. Graph. 35(6) (2016). https:\/\/doi.org\/10.1145\/2980179.2980238","DOI":"10.1145\/2980179.2980238"},{"key":"22_CR41","unstructured":"Yun, C., Bhojanapalli, S., Rawat, A.S., Reddi, S., Kumar, S.: Are transformers universal approximators of sequence-to-sequence functions? In: International Conference on Learning Representations (2019)"},{"key":"22_CR42","unstructured":"Zaheer, M., Kottur, S., Ravanbakhsh, S., Poczos, B., Salakhutdinov, R.R., Smola, A.J.: Deep sets. In: 30th Proceedings of Conference on Advances in Neural Information Processing Systems (2017)"},{"key":"22_CR43","doi-asserted-by":"publisher","unstructured":"Zhao, H., Jiang, L., Fu, C.W., Jia, J.: PointWeb: enhancing local neighborhood features for point cloud processing. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5560\u20135568 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00571","DOI":"10.1109\/CVPR.2019.00571"},{"key":"22_CR44","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\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27066-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T06:19:59Z","timestamp":1678256399000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27066-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031270659","9783031270666"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27066-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"9 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","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 Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"33% - 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":"3.3","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":"2.6","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)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}