{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:58:39Z","timestamp":1743145119555,"version":"3.40.3"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031376597"},{"type":"electronic","value":"9783031376603"}],"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\/978-3-031-37660-3_21","type":"book-chapter","created":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T06:02:20Z","timestamp":1690610540000},"page":"302-312","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Involving Density Prior for\u00a03D Point Cloud Contrastive Learning"],"prefix":"10.1007","author":[{"given":"Fuchen","family":"Long","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaofan","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,30]]},"reference":[{"key":"21_CR1","unstructured":"Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representation and generative models for 3D point clouds. In: ICML (2018)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Ahmed, S.M., Meng, C.C.: Density based clustering for 3D object detection in point clouds. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01062"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Armeni, I., et al.: 3D semantic parsing of large-scale indoor space. In: ICCV (2016)","DOI":"10.1109\/CVPR.2016.170"},{"key":"21_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal convnets: minkowski convolutional neural networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"21_CR6","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Engelmann, F., Bokenloh, M., Fathi, A., Leibe, B., Nie\u00dfner, M.: 3D-MPA: multi-proposal aggregation for 3D semantic instance segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"21_CR9","unstructured":"Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: SIGKDD (1996)"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Xiong, B., Girshick, R., He, K.: A large-scale study on unsupervised spatiotemporal representation learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"21_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-3-030-01234-2_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Gadelha","year":"2018","unstructured":"Gadelha, M., Wang, R., Maji, S.: Multiresolution tree networks for 3D point cloud processing. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 105\u2013122. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_7"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., van der Maaten, L.: 3D semantic segmentation with submanifold sparse convolution networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00961"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Han, Z., Wang, X., Liu, Y.S., Zwicker, M.: Multi-angle point cloud-VAE: unsupervised feature learning for 3D point clouds from multiple angles by joint self-reconstruction and half-to-half prediction. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01054"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Hassani, K., Haley, M.: Unsupervised multi-task feature learning on point clouds. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00825"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Dollar, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Hou, J., Dai, A., Nie\u00dfner, M.: 3D-SIS: 3D semantic instance segmentation of RGB-D scans. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00455"},{"key":"21_CR20","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: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, H., Yan, F., Cai, J., Zheng, J., Xiao, J.: End-to-end 3D point cloud instance segmentation without detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01281"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Jiang, L., Zhao, H., Shi, S., Liu, S., Fu, C., Jia, J.: PointGroup: dual-set point grouping for 3D instance segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"21_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/978-3-030-58548-8_18","volume-title":"Computer Vision \u2013 ECCV 2020","author":"JY Gwak","year":"2020","unstructured":"Gwak, J.Y., Choy, C., Savarese, S.: Generative sparse detection networks for 3D single-shot object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 297\u2013313. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_18"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Li, J., Chen, B.M., Lee, G.H.: SO-Net: self-organizing network for point cloud analysis. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00979"},{"key":"21_CR25","unstructured":"Li, J., Zhou, P., Xiong, C., Hoi, S.: Prototypical contrastive learning of unsupervised representations. In: ICLR (2021)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Long, F., Qiu, Z., Pan, Y., Yao, T., Luo, J., Mei, T.: Stand-alone inter-frame attention in video models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00319"},{"key":"21_CR28","doi-asserted-by":"publisher","unstructured":"Long, F., Qiu, Z., Pan, Y., Yao, T., Ngo, C.W., Mei, T.: Dynamic temporal filtering in video models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13695. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_28","DOI":"10.1007\/978-3-031-19833-5_28"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Long, F., Yao, T., Qiu, Z., Tian, X., Luo, J., Mei, T.: Gaussian temporal awareness networks for action localization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00043"},{"key":"21_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/978-3-030-58580-8_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"F Long","year":"2020","unstructured":"Long, F., Yao, T., Qiu, Z., Tian, X., Luo, J., Mei, T.: Learning to localize actions from\u00a0moments. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 137\u2013154. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_9"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Long, F., Yao, T., Qiu, Z., Tian, X., Luo, J., Mei, T.: Bi-calibration networks for weakly-supervised video representation learning. arXiv preprint arXiv:2206.10491 (2022)","DOI":"10.1007\/s11263-023-01779-w"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Long, F., Yao, T., Qiu, Z., Tian, X., Mei, T., Luo, J.: Coarse-to-fine localization of temporal action proposals. IEEE Trans. Multimed. (2019)","DOI":"10.1109\/TMM.2019.2943204"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Luo, Z., Peng, B., Huang, D.A., Alahi, A., Fei-Fei, L.: Unsupervised learning of long-term motion dynamics for videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.751"},{"key":"21_CR34","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00100"},{"key":"21_CR35","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. In: NeurIPS (2018)"},{"key":"21_CR36","unstructured":"Pan, Y., et al.: Smart director: an event-driven directing system for live broadcasting. IEEE Trans. Multimed. Comput. Commun. Appl. (2022)"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Chen, X., Litany, O., Guibas, L.J.: Imvotenet: boosting 3D object detection in point cloud with image votes. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00446"},{"key":"21_CR38","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: CVPR (2017)"},{"key":"21_CR39","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: NeurIPS (2017)"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.590"},{"issue":"3","key":"21_CR41","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vision"},{"key":"21_CR42","unstructured":"Sauder, J., Sievers, B.: Self-supervised deep learning on point clouds by reconstructing space. In: NeurIPS (2019)"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, Y., Liu, Z., Siegel, J.E., Sarma, S.E.: PointGrow: autoregressively learned point cloud generation with self-attention. In: WACV (2019)","DOI":"10.1109\/WACV45572.2020.9093430"},{"key":"21_CR44","doi-asserted-by":"crossref","unstructured":"Tchapmi, L., Choy, C., Armeni, I., Gwak, J., Savarese, S.: Segcloud: segmentation of 3D point clouds. In: 3DV (2017)","DOI":"10.1109\/3DV.2017.00067"},{"key":"21_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Unsupervised learning of visual representations using videos. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.320"},{"key":"21_CR47","unstructured":"Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shape modeling. In: CVPR (2015)"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"21_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/978-3-030-58580-8_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Xie","year":"2020","unstructured":"Xie, S., Gu, J., Guo, D., Qi, C.R., Guibas, L., Litany, O.: PointContrast: unsupervised pre-training for 3D point cloud understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 574\u2013591. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_34"},{"key":"21_CR50","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-030-01267-0_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Xie","year":"2018","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 318\u2013335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_19"},{"key":"21_CR51","doi-asserted-by":"crossref","unstructured":"Yang, J., Ahn, P., Kim, D., Lee, H., Kim, J.: Progressive seed generation auto-encoder for unsupervised point cloud learning. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00635"},{"key":"21_CR52","doi-asserted-by":"crossref","unstructured":"Yang, Y., Feng, C., Shen, Y., Tian, D.: FoldingNet: point cloud auto-encoder via deep grid deformation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00029"},{"key":"21_CR53","doi-asserted-by":"crossref","unstructured":"Yi, L., et al.: A scalable active framework for region annotation in 3D shape collections. ACM Trans. Graph. (2016)","DOI":"10.1145\/2980179.2980238"},{"key":"21_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3D features on any point-cloud. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01009"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition, Computer Vision, and Image Processing. ICPR 2022 International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-37660-3_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T06:06:10Z","timestamp":1690610770000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-37660-3_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031376597","9783031376603"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-37660-3_21","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":"30 July 2023","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":"Montr\u00e9al, QC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"21 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icpr2022","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}