{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:46:12Z","timestamp":1772905572799,"version":"3.50.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727535","type":"print"},{"value":"9783031727542","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-72754-2_4","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:57:07Z","timestamp":1730300227000},"page":"57-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Diff3DETR: Agent-Based Diffusion Model for\u00a0Semi-supervised 3D Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2838-0378","authenticated-orcid":false,"given":"Jiacheng","family":"Deng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3280-9447","authenticated-orcid":false,"given":"Jiahao","family":"Lu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-9564","authenticated-orcid":false,"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"issue":"10","key":"4_CR1","doi-asserted-by":"publisher","first-page":"3782","DOI":"10.1109\/TITS.2019.2892405","volume":"20","author":"E Arnold","year":"2019","unstructured":"Arnold, E., Al-Jarrah, O.Y., Dianati, M., Fallah, S., Oxtoby, D., Mouzakitis, A.: A survey on 3D object detection methods for autonomous driving applications. IEEE Trans. Intell. Transp. Syst. 20(10), 3782\u20133795 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Cao, H., et al.: A survey on generative diffusion models. IEEE Trans. Knowl. Data Eng. (2024)","DOI":"10.1109\/TKDE.2024.3361474"},{"key":"4_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":"4_CR4","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., Luo, P.: DiffusionDet: diffusion model for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19830\u201319843 (2023)","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., Li, L., Saxena, S., Hinton, G., Fleet, D.J.: A generalist framework for panoptic segmentation of images and videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 909\u2013919 (2023)","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"4_CR6","unstructured":"Chen, T., Zhang, R., Hinton, G.: Analog bits: generating discrete data using diffusion models with self-conditioning. arXiv preprint arXiv:2208.04202 (2022)"},{"key":"4_CR7","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\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"4_CR8","unstructured":"De\u00a0Groot, S.R., Mazur, P.: Non-Equilibrium Thermodynamics. Courier Corporation (2013)"},{"key":"4_CR9","unstructured":"Geiger, A., Lenzp, U.R.: Are we ready for autonomous driving (2012)"},{"key":"4_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/978-3-030-58523-5_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Griffiths","year":"2020","unstructured":"Griffiths, D., Boehm, J., Ritschel, T.: Finding your (3D) center: 3D object detection using a learned loss. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 70\u201385. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_5"},{"key":"4_CR11","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":"4_CR12","doi-asserted-by":"crossref","unstructured":"He, J., Deng, J., Zhang, T., Zhang, Z., Zhang, Y.: Hierarchical shape-consistent transformer for unsupervised point cloud shape correspondence. IEEE Trans. Image Process. (2023)","DOI":"10.1109\/TIP.2023.3272821"},{"key":"4_CR13","unstructured":"Ho, C.J., Tai, C.H., Lin, Y.Y., Yang, M.H., Tsai, Y.H.: Diffusion-SS3D: diffusion model for semi-supervised 3D object detection. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"4_CR14","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"4_CR15","unstructured":"Kingma, D., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. In: Advances in Neural Information Processing Systems, vol. 34, pp. 21696\u201321707 (2021)"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9404\u20139413 (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Liu, C., Gao, C., Liu, F., Li, P., Meng, D., Gao, X.: Hierarchical supervision and shuffle data augmentation for 3D semi-supervised object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23819\u201323828 (2023)","DOI":"10.1109\/CVPR52729.2023.02281"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, Z., Cao, Y., Hu, H., Tong, X.: Group-free 3D object detection via transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2949\u20132958 (2021)","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2906\u20132917 (2021)","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"4_CR20","unstructured":"Mukhopadhyay, S., et al.: Diffusion models beat GANs on image classification. arXiv preprint arXiv:2307.08702 (2023)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Norris, J.R.: Markov Chains, no.\u00a02. Cambridge University Press (1998)","DOI":"10.1017\/CBO9780511810633"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep Hough voting for 3D object detection in point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"4_CR24","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":"4_CR25","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"2","key":"4_CR26","doi-asserted-by":"publisher","first-page":"636","DOI":"10.3390\/app10020636","volume":"10","author":"S Rokhsaritalemi","year":"2020","unstructured":"Rokhsaritalemi, S., Sadeghi-Niaraki, A., Choi, S.M.: A review on mixed reality: current trends, challenges and prospects. Appl. Sci. 10(2), 636 (2020)","journal-title":"Appl. Sci."},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"4_CR28","unstructured":"Shen, Y., et al.: V-DETR: DETR with vertex relative position encoding for 3D object detection. arXiv preprint arXiv:2308.04409 (2023)"},{"key":"4_CR29","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"4_CR30","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: SUN RGB-D: a RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"4_CR32","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"4_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Wang, C., Deng, J., He, J., Zhang, T., Zhang, Z., Zhang, Y.: Long-short range adaptive transformer with dynamic sampling for 3D object detection. IEEE Trans. Circuits Syst. Video Technol. (2023)","DOI":"10.1109\/TCSVT.2023.3272734"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Wang, C., Yang, W., Zhang, T.: Not every side is equal: localization uncertainty estimation for semi-supervised 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3814\u20133824 (2023)","DOI":"10.1109\/ICCV51070.2023.00353"},{"key":"4_CR36","unstructured":"Wang, H., et al.: CAGroup3D: class-aware grouping for 3D object detection on point clouds. In: Advances in Neural Information Processing Systems, vol. 35, pp. 29975\u201329988 (2022)"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Wang, H., Cong, Y., Litany, O., Gao, Y., Guibas, L.J.: 3DIoUMatch: leveraging IoU prediction for semi-supervised 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14615\u201314624 (2021)","DOI":"10.1109\/CVPR46437.2021.01438"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Semi-supervised 3D object detection with PatchTeacher and PillarMix. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 6153\u20136161 (2024)","DOI":"10.1609\/aaai.v38i6.28432"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Xie, Q., et al.: MLCVNet: multi-level context VoteNet for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10447\u201310456 (2020)","DOI":"10.1109\/CVPR42600.2020.01046"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Yang, X., Song, Z., King, I., Xu, Z.: A survey on deep semi-supervised learning. IEEE Trans. Knowl. Data Eng. (2022)","DOI":"10.1109\/TKDE.2022.3220219"},{"issue":"2","key":"4_CR41","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1109\/TNSRE.2017.2748419","volume":"26","author":"C Ye","year":"2017","unstructured":"Ye, C., Qian, X.: 3-D object recognition of a robotic navigation aid for the visually impaired. IEEE Trans. Neural Syst. Rehabil. Eng. 26(2), 441\u2013450 (2017)","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"4_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-58610-2_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Sun, B., Yang, H., Huang, Q.: H3DNet: 3D object detection using hybrid geometric primitives. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 311\u2013329. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_19"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, N., Chua, T.S., Lee, G.H.: SESS: self-ensembling semi-supervised 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11079\u201311087 (2020)","DOI":"10.1109\/CVPR42600.2020.01109"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72754-2_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:58:27Z","timestamp":1730300307000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72754-2_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031727535","9783031727542"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72754-2_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","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":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}