{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T04:25:06Z","timestamp":1743049506446,"version":"3.40.3"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726422"},{"type":"electronic","value":"9783031726439"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-72643-9_9","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T20:47:53Z","timestamp":1732222073000},"page":"140-157","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Interactive 3D Object Detection with\u00a0Prompts"],"prefix":"10.1007","author":[{"given":"Ruifei","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Xiangru","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jincheng","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Xuekuan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiao","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Yingying","family":"Li","sequence":"additional","affiliation":[]},{"given":"Errui","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Bai, X., et al.: Transfusion: robust lidar-camera fusion for 3d object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1090\u20131099 (2022)","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"9_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":"9_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhao, Z., Zhang, Y., Duan, M., Qi, D., Zhao, H.: Focalclick: towards practical interactive image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1300\u20131309 (2022)","DOI":"10.1109\/CVPR52688.2022.00136"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3d object detection network for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"9_CR6","unstructured":"Chen, Y., Chen, Q., Sun, P., Chen, S., Wang, J., Cheng, J.: Enhancing your trained detrs with box refinement. arXiv preprint arXiv:2307.11828 (2023)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Choi, D., Cho, W., Kim, K., Choo, J.: idet3d: towards efficient interactive object detection for lidar point clouds. arXiv preprint arXiv:2312.15449 (2023)","DOI":"10.1609\/aaai.v38i2.27897"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Ge, C., et al.: Metabev: solving sensor failures for Bev detection and map segmentation. arXiv preprint arXiv:2304.09801 (2023)","DOI":"10.1109\/ICCV51070.2023.00801"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The Kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"9_CR10","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\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"9_CR11","unstructured":"Huang, J., Huang, G.: Bevdet4d: exploit temporal cues in multi-camera 3d object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"9_CR12","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: Bevdet: high-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"9_CR13","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Lee, C., et al.: Interactive multi-class tiny-object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14136\u201314145 (2022)","DOI":"10.1109\/CVPR52688.2022.01374"},{"key":"9_CR16","first-page":"18442","volume":"35","author":"Y Li","year":"2022","unstructured":"Li, Y., Chen, Y., Qi, X., Li, Z., Sun, J., Jia, J.: Unifying voxel-based representation with transformer for 3d object detection. Adv. Neural. Inf. Process. Syst. 35, 18442\u201318455 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, F., Wang, N.: Lidar r-cnn: An efficient and universal 3d object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7546\u20137555 (2021)","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"9_CR18","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from\u00a0multi-camera images via\u00a0spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part IX, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"9_CR20","unstructured":"Liu, S., et al.: Dab-detr: dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329 (2022)"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: Petr: position embedding transformation for multi-view 3d object detection. In: European Conference on Computer Vision, pp. 531\u2013548. Springer, Heidelberg (2022)","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Petrv2: a unified framework for 3d perception from multi-camera images. arXiv preprint arXiv:2206.01256 (2022)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Bevfusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 2774\u20132781. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Geometry uncertainty projection network for monocular 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3111\u20133121 (2021)","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Maninis, K.K., Caelles, S., Pont-Tuset, J., Van\u00a0Gool, L.: Deep extreme cut: from extreme points to object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 616\u2013625 (2018)","DOI":"10.1109\/CVPR.2018.00071"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional detr for fast training convergence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Meng, Q., Wang, W., Zhou, T., Shen, J., Jia, Y., Van Gool, L.: Towards a weakly supervised framework for 3d point cloud object detection and annotation. IEEE Trans. Pattern Anal. Mach. Intell. 44(8), 4454\u20134468 (2021)","DOI":"10.1109\/TPAMI.2021.3063611"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Papadopoulos, D.P., Uijlings, J.R., Keller, F., Ferrari, V.: Extreme clicking for efficient object annotation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4930\u20134939 (2017)","DOI":"10.1109\/ICCV.2017.528"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Papadopoulos, D.P., Uijlings, J.R., Keller, F., Ferrari, V.: Training object class detectors with click supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6374\u20136383 (2017)","DOI":"10.1109\/CVPR.2017.27"},{"key":"9_CR30","doi-asserted-by":"publisher","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"9_CR31","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: dlearning 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":"9_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"9_CR33","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\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Shin, K., Kwon, Y.P., Tomizuka, M.: Roarnet: a robust 3d object detection based on region approximation refinement. In: 2019 IEEE Intelligent Vehicles Symposium (IV), pp. 2510\u20132515. IEEE (2019)","DOI":"10.1109\/IVS.2019.8813895"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Sofiiuk, K., Petrov, I.A., Konushin, A.: Reviving iterative training with mask guidance for interactive segmentation. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 3141\u20133145. IEEE (2022)","DOI":"10.1109\/ICIP46576.2022.9897365"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Sun, P., et\u00a0al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Wang, B., Wu, V., Wu, B., Keutzer, K.: Latte: accelerating lidar point cloud annotation via sensor fusion, one-click annotation, and tracking. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp. 265\u2013272. IEEE (2019)","DOI":"10.1109\/ITSC.2019.8916980"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Wang, K., et al.: De-biased teacher: Rethinking IOU matching for semi-supervised object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2573\u20132580 (2023)","DOI":"10.1609\/aaai.v37i2.25355"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: Fcos3d: fully convolutional one-stage monocular 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 913\u2013922 (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor detr: query design for transformer-based detector. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2567\u20132575 (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"9_CR41","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: Detr3d: 3d object detection from multi-view images via 3d-to-2d queries. In: Conference on Robot Learning, pp. 180\u2013191. PMLR (2022)"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Xie, Y., et al.: Sparsefusion: fusing multi-modal sparse representations for multi-sensor 3d object detection. arXiv preprint arXiv:2304.14340 (2023)","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: End-to-end semi-supervised object detection with soft teacher. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3060\u20133069 (2021)","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Xu, N., Price, B., Cohen, S., Yang, J., Huang, T.S.: Deep interactive object selection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 373\u2013381 (2016)","DOI":"10.1109\/CVPR.2016.47"},{"key":"9_CR45","unstructured":"Yan, J., et al.: Cross modal transformer via coordinates encoding for 3d object dectection. arXiv preprint arXiv:2301.01283 (2023)"},{"key":"9_CR46","doi-asserted-by":"crossref","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","DOI":"10.3390\/s18103337"},{"key":"9_CR47","doi-asserted-by":"crossref","unstructured":"Yang, J., Zeng, A., Li, F., Liu, S., Zhang, R., Zhang, L.: Neural interactive keypoint detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15122\u201315132 (2023)","DOI":"10.1109\/ICCV51070.2023.01388"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3dssd: point-based 3d single stage object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11040\u201311048 (2020)","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"Yao, A., Gall, J., Leistner, C., Van\u00a0Gool, L.: Interactive object detection. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3242\u20133249. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248060"},{"key":"9_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Semi-detr: semi-supervised object detection with detection transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23809\u201323818 (2023)","DOI":"10.1109\/CVPR52729.2023.02280"},{"key":"9_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Monodetr: depth-guided transformer for monocular 3d object detection. arXiv preprint arXiv:2203.13310 (2022)","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"9_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, J., Sun, L., Li, Q.: Recursivedet: end-to-end region-based recursive object detection. arXiv preprint arXiv:2307.13619 (2023)","DOI":"10.1109\/ICCV51070.2023.00580"},{"key":"9_CR53","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"},{"key":"9_CR54","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhu, H., Liu, Q., Chang, S., Guo, M.: Monoatt: online monocular 3d object detection with adaptive token transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17493\u201317503 (2023)","DOI":"10.1109\/CVPR52729.2023.01678"}],"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\/978-3-031-72643-9_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T21:25:19Z","timestamp":1732224319000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72643-9_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031726422","9783031726439"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72643-9_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 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"}}]}}