{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T05:51:03Z","timestamp":1781761863866,"version":"3.54.5"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,25]]},"DOI":"10.1109\/fg67764.2026.11556984","type":"proceedings-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:37:10Z","timestamp":1781725030000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Depth-Copy-Paste: Multimodal and Depth-Aware Compositing for Robust Face Detection"],"prefix":"10.1109","author":[{"given":"Qiushi","family":"Guo","sequence":"first","affiliation":[{"name":"Coffee AI Lab, Great Wall Motor (GWM),Chengdu,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiufeng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Coffee AI Lab, Great Wall Motor (GWM),Chengdu,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonglong","family":"Wang","sequence":"additional","affiliation":[{"name":"Coffee AI Lab, Great Wall Motor (GWM),Chengdu,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Luo","sequence":"additional","affiliation":[{"name":"Coffee AI Lab, Great Wall Motor (GWM),Chengdu,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiye","family":"Lin","sequence":"additional","affiliation":[{"name":"Coffee AI Lab, Great Wall Motor (GWM),Chengdu,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanqing","family":"Luo","sequence":"additional","affiliation":[{"name":"Coffee AI Lab, Great Wall Motor (GWM),Chengdu,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Sub-millisecond neural face detection on mobile gpus. arXiv preprint arXiv:1907.05047","author":"Bazarevsky","year":"2019"},{"key":"ref2","volume-title":"Segment anything with concepts. arXiv preprint arXiv:2511.16719","author":"Carion","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-020-01831-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref6","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv preprint arXiv:1708.04552"},{"key":"ref7","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"Eigen","year":"2014","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298641"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref12","article-title":"Enrich the content of the image using context-aware copy paste","author":"Guo","year":"2024","journal-title":"arXiv preprint arXiv:2407.08151"},{"key":"ref13","article-title":"Synrailobs: A synthetic dataset for obstacle detection in railway scenarios","volume-title":"arXiv preprint arXiv:2505.10784","author":"Guo","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00513"},{"key":"ref15","article-title":"Stereo processing by semiglobal matching and mutual information","author":"Hirschmuller","year":"2007","journal-title":"IEEE TPAMI"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00116"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01223"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref19","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00520"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3019967"},{"key":"ref25","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1014573219977"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_49"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2017.8272675"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"}],"event":{"name":"2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Kyoto, Japan","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11556508\/11556510\/11556984.pdf?arnumber=11556984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:52:11Z","timestamp":1781758331000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11556984\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/fg67764.2026.11556984","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}