{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:29:25Z","timestamp":1766068165441,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T00:00:00Z","timestamp":1729209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,18]]},"DOI":"10.1145\/3711129.3711337","type":"proceedings-article","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T12:46:06Z","timestamp":1740055566000},"page":"1228-1234","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["PP-DETR: Progressive Proposal Detection Transformer for 3D Visual Grounding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1875-7712","authenticated-orcid":false,"given":"Jinyuan","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen, Fujian, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5354-4321","authenticated-orcid":false,"given":"Duxin","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen, Fujian, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4175-3609","authenticated-orcid":false,"given":"Zhuangzhi","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen, Fujian, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8719-3938","authenticated-orcid":false,"given":"Yang","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen, Fujian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1707-5685","authenticated-orcid":false,"given":"Jinhe","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen, Fujian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8091-271X","authenticated-orcid":false,"given":"Guorong","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen, Fujian, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3554-5549","authenticated-orcid":false,"given":"Yundong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen, Fujian, China"}]}],"member":"320","published-online":{"date-parts":[[2025,2,20]]},"reference":[{"key":"e_1_3_3_1_1_2","first-page":"202","volume-title":"3d object localization in rgb-d scans using natural language.\" In European conference on computer vision","author":"Zhenyu Dave","year":"2020","unstructured":"Chen, Dave Zhenyu, Angel X. Chang, and Matthias Nie\u00dfner. \"Scanrefer: 3d object localization in rgb-d scans using natural language.\" In European conference on computer vision, pp. 202-221. Cham: Springer International Publishing, 2020."},{"key":"e_1_3_3_1_2_2","first-page":"422","volume-title":"Proceedings, Part I 16","author":"Abdelreheem Ahmed","year":"2020","unstructured":"Achlioptas, Panos, Ahmed Abdelreheem, Fei Xia, Mohamed Elhoseiny, and Leonidas Guibas. \"Referit3d: Neural listeners for fine-grained 3d object identification in real-world scenes.\" In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16, pp. 422-440. Springer International Publishing, 2020."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"e_1_3_3_1_4_2","first-page":"1791","article-title":"Instancerefer: Cooperative holistic understanding for visual grounding on point clouds through instance multi-level contextual referring","author":"Yan Xu","year":"2021","unstructured":"Yuan, Zhihao, Xu Yan, Yinghong Liao, Ruimao Zhang, Sheng Wang, Zhen Li, and Shuguang Cui. \"Instancerefer: Cooperative holistic understanding for visual grounding on point clouds through instance multi-level contextual referring.\" In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1791-1800. 2021.","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"e_1_3_3_1_5_2","first-page":"1856","article-title":"Sat: 2d semantics assisted training for 3d visual grounding","author":"Zhang Songyang","year":"2021","unstructured":"Yang, Zhengyuan, Songyang Zhang, Liwei Wang, and Jiebo Luo. \"Sat: 2d semantics assisted training for 3d visual grounding.\" In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1856-1866. 2021.","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"e_1_3_3_1_6_2","first-page":"16454","article-title":"3d-sps: Single-stage 3d visual grounding via referred point progressive selection","author":"Fu Jiahui","year":"2022","unstructured":"Luo, Junyu, Jiahui Fu, Xianghao Kong, Chen Gao, Haibing Ren, Hao Shen, Huaxia Xia, and Si Liu. \"3d-sps: Single-stage 3d visual grounding via referred point progressive selection.\" In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16454-16463. 2022.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_3_1_7_2","volume-title":"Cham: Springer Nature Switzerland","author":"Gkanatsios Nikolaos","year":"2022","unstructured":"Jain, Ayush, Nikolaos Gkanatsios, Ishita Mediratta, and Katerina Fragkiadaki. \"Bottom up top down detection transformers for language grounding in images and point clouds.\" In European Conference on Computer Vision, pp. 417-433. Cham: Springer Nature Switzerland, 2022."},{"key":"e_1_3_3_1_8_2","first-page":"19231","article-title":"Eda: Explicit text-decoupling and dense alignment for 3d visual grounding","author":"Cheng Xinhua","year":"2023","unstructured":"Wu, Yanmin, Xinhua Cheng, Renrui Zhang, Zesen Cheng, and Jian Zhang. \"Eda: Explicit text-decoupling and dense alignment for 3d visual grounding.\" In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19231-19242. 2023.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_3_1_9_2","first-page":"213","volume-title":"Cham","author":"Massa Francisco","year":"2020","unstructured":"Carion, Nicolas, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. \"End-to-end object detection with transformers.\" In European conference on computer vision, pp. 213-229. Cham: Springer International Publishing, 2020."},{"key":"e_1_3_3_1_10_2","first-page":"2961","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Gkioxari Georgia","year":"2017","unstructured":"He, Kaiming, Georgia Gkioxari, Piotr Doll\u00e1r, and Ross Girshick. \"Mask r-cnn.\" In Proceedings of the IEEE international conference on computer vision, pp. 2961-2969. 2017."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Ren Shaoqing Kaiming He Ross Girshick and Jian Sun. \"Faster R-CNN: Towards real-time object detection with region proposal networks.\" IEEE transactions on pattern analysis and machine intelligence 39 no. 6 (2016): 1137-1149.","DOI":"10.1109\/TPAMI.2016.2577031"}],"event":{"name":"EITCE 2024: 2024 8th International Conference on Electronic Information Technology and Computer Engineering","acronym":"EITCE 2024","location":"Haikou Guangdong China"},"container-title":["Proceedings of the 2024 8th International Conference on Electronic Information Technology and Computer Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711129.3711337","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711129.3711337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:03Z","timestamp":1750295883000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711129.3711337"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,18]]},"references-count":11,"alternative-id":["10.1145\/3711129.3711337","10.1145\/3711129"],"URL":"https:\/\/doi.org\/10.1145\/3711129.3711337","relation":{},"subject":[],"published":{"date-parts":[[2024,10,18]]},"assertion":[{"value":"2025-02-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}