{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:10:25Z","timestamp":1755825025511,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20515, 62476262, 62206263, 62271467, 62306297, 62306296"],"award-info":[{"award-number":["U21A20515, 62476262, 62206263, 62271467, 62306297, 62306296"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["4242053, L242096"],"award-info":[{"award-number":["4242053, L242096"]}]},{"DOI":"10.13039\/501100006374","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022T150639"],"award-info":[{"award-number":["2022T150639"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733335","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:29:43Z","timestamp":1750876183000},"page":"1579-1587","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FC-MonoDETR: A Monocular 3D Object Detection Network Based on Foreground Constraint"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8217-560X","authenticated-orcid":false,"given":"Daifeng","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8306-1054","authenticated-orcid":false,"given":"Dongbo","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9648-6073","authenticated-orcid":false,"given":"Yunbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1799-3948","authenticated-orcid":false,"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4121-1675","authenticated-orcid":false,"given":"Ying","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2517-7593","authenticated-orcid":false,"given":"Lupeng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings, Part XXIII 16","author":"Brazil Garrick","year":"2020","unstructured":"Garrick Brazil, Gerard Pons-Moll, Xiaoming Liu, and Bernt Schiele. 2020. Kinematic 3d object detection in monocular video. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXIII 16. Springer, 135--152."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_4_1","volume-title":"Emerging Properties in Self-Supervised Vision Transformers. arXiv preprint arXiv:2104.14294","author":"Caron Mathilde","year":"2021","unstructured":"Mathilde Caron, Hugo Touvron, Ishan Misra, Herv\u00e9 J\u00e9gou, Julien Mairal, Piotr Bojanowski, and Armand Joulin. 2021. Emerging Properties in Self-Supervised Vision Transformers. arXiv preprint arXiv:2104.14294 (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.198"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01024"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3249909"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"e_1_3_2_1_10_1","volume-title":"DINOv2: Learning Robust Visual Features without Supervision. arXiv preprint arXiv:2304.07193","author":"Darcet Timoth\u00e9e","year":"2023","unstructured":"Timoth\u00e9e Darcet, Maxime Oquab, Julien Mairal, Piotr Bojanowski, and Armand Joulin. 2023. DINOv2: Learning Robust Visual Features without Supervision. arXiv preprint arXiv:2304.07193 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"e_1_3_2_1_12_1","volume-title":"The KITTI Vision Benchmark Suite. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Geiger Andreas","year":"2012","unstructured":"Andreas Geiger, Philip Lenz, and Raquel Urtasun. 2012. Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_13_1","volume-title":"Ssd-monodetr: Supervised scale-aware deformable transformer for monocular 3d object detection","author":"He Xuan","year":"2023","unstructured":"Xuan He, Fan Yang, Kailun Yang, Jiacheng Lin, Haolong Fu, Meng Wang, Jin Yuan, and Zhiyong Li. 2023. Ssd-monodetr: Supervised scale-aware deformable transformer for monocular 3d object detection. IEEE Transactions on Intelligent Vehicles (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00886"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20074"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00695"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00217"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.597"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"e_1_3_2_1_26_1","volume-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"Ren Shaoqing","year":"2016","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2016. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence, Vol. 39, 6 (2016), 1137--1149."},{"key":"e_1_3_2_1_27_1","volume-title":"Orthographic feature transform for monocular 3d object detection. arXiv preprint arXiv:1811.08188","author":"Roddick Thomas","year":"2018","unstructured":"Thomas Roddick, Alex Kendall, and Roberto Cipolla. 2018. Orthographic feature transform for monocular 3d object detection. arXiv preprint arXiv:1811.08188 (2018)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00208"},{"key":"e_1_3_2_1_29_1","volume-title":"FCOS: Fully Convolutional One-Stage Object Detection. arXiv. arXiv preprint arXiv:1904.01355","author":"Tian Z","year":"2019","unstructured":"Z Tian, C Shen, H Chen, and T He. 2019. FCOS: Fully Convolutional One-Stage Object Detection. arXiv. arXiv preprint arXiv:1904.01355 (2019)."},{"key":"e_1_3_2_1_30_1","volume-title":"Conference on Robot Learning. PMLR, 1475--1485","author":"Wang Tai","year":"2022","unstructured":"Tai Wang, ZHU Xinge, Jiangmiao Pang, and Dahua Lin. 2022. Probabilistic and geometric depth: Detecting objects in perspective. In Conference on Robot Learning. PMLR, 1475--1485."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"e_1_3_2_1_33_1","unstructured":"A Waswani N Shazeer N Parmar J Uszkoreit L Jones A Gomez L Kaiser and I Polosukhin. 2017. Attention is all you need. In NIPS."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161442"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"e_1_3_2_1_37_1","volume-title":"Objects as points. arXiv preprint arXiv:1904.07850","author":"Zhou Xingyi","year":"2019","unstructured":"Xingyi Zhou, Dequan Wang, and Philipp Kr\u00e4henb\u00fchl. 2019. Objects as points. arXiv preprint arXiv:1904.07850 (2019)."}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"ICMR '25"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:07:56Z","timestamp":1755749276000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733335"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":37,"alternative-id":["10.1145\/3731715.3733335","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733335","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}