{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T05:58:48Z","timestamp":1743141528973,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785070"},{"type":"electronic","value":"9789819785087"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8508-7_14","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:04:55Z","timestamp":1730527495000},"page":"196-210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Quat-DGNet: Enhancing 3D Dense Captioning with Quaternion-Based Spatial Offsets and Dynamic Neighborhood Graphs"],"prefix":"10.1007","author":[{"given":"Shu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangdong","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fujun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Achlioptas, P., Abdelreheem, A., Xia, F., Elhoseiny, M., Guibas, L.: Referit3d: neural listeners for fine-grained 3d object identification in real-world scenes. In: ECCV, Proceedings, Part I 16, pp. 422\u2013440. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"14_CR2","unstructured":"Banerjee, S., Lavie, A.: Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. In: ACL Workshop, pp. 65\u201372 (2005)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Cai, D., Zhao, L., Zhang, J., Sheng, L., Xu, D.: 3djcg: a unified framework for joint dense captioning and visual grounding on 3d point clouds. In: CVPR, pp. 16464\u201316473 (2022)","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Chang, A.X., Niener, M.: Scanrefer: 3d object localization in rgb-d scans using natural language. In: ECCV, pp. 202\u2013221. Springer (2020)","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Wu, Q., Nie\u00dfner, M.: D3net: A speaker-listener architecture for semi-supervised dense captioning and visual grounding in rgb-d scans (2021)","DOI":"10.1007\/978-3-031-19824-3_29"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Lei, B., Song, Q., Ying, H., Chen, D.Z., Wu, J.: A hierarchical graph network for 3d object detection on point clouds. In: CVPR, pp. 392\u2013401 (2020)","DOI":"10.1109\/CVPR42600.2020.00047"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhu, H., Chen, X., Lei, Y., Yu, G., Chen, T.: End-to-end 3d dense captioning with vote2cap-detr. In: CVPR, pp. 11124\u201311133 (2023)","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"14_CR8","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: CVPR, pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Gholami, A., Nie\u00dfner, M., Chang, A.X.: Scan2cap: context-aware dense captioning in rgb-d scans. In: CVPR, pp. 3193\u20133203 (2021)","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Engelmann, F., Bokeloh, M., Fathi, A., Leibe, B.: 3d-mpa: multi-proposal aggregation for 3d semantic instance segmentation. In: CVPR, pp. 9031\u20139040 (2020)","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Jiao, Y., Chen, S., Jie, Z., Chen, J., Ma, L., Jiang, Y.G.: More: Multi-order relation mining for dense captioning in 3d scenes. In: ECCV, pp. 528\u2013545. Springer (2022)","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"14_CR12","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: CVPR, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3d object detection. In: ICCV, pp. 2906\u20132917 (2021)","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"14_CR16","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: ICCV, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"14_CR17","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"14_CR18","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. NeurIPS 28 (2015)"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: Pointrcnn: 3d object proposal generation and detection from point cloud. In: CVPR, pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: CVPR, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, C., Yu, J., Cai, W.: Spatiality-guided transformer for 3d dense captioning on point clouds. In: IJCAI (2022)","DOI":"10.24963\/ijcai.2022\/194"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Pillar-based object detection for autonomous driving. In: ECCV, pp. 18\u201334. Springer (2020)","DOI":"10.1007\/978-3-030-58542-6_2"},{"issue":"10","key":"14_CR23","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","journal-title":"Sensors"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Yuan, Z., et al.: X-trans2cap: Cross-modal knowledge transfer using transformer for 3d dense captioning. In: CVPR, pp. 8563\u20138573 (2022)","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Sun, B., Yang, H., Huang, Q.: H3dnet: 3d object detection using hybrid geometric primitives. In: ECCV, pp. 311\u2013329. Springer (2020)","DOI":"10.1007\/978-3-030-58610-2_19"},{"key":"14_CR26","unstructured":"Zhong, Y., Xu, L., Luo, J., Ma, L.: Contextual modeling for 3d dense captioning on point clouds (2022). arXiv:2210.03925"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3d object detection. In: CVPR, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8508-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:14:40Z","timestamp":1730528080000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8508-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785070","9789819785087"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8508-7_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}