{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T04:46:58Z","timestamp":1789015618321,"version":"build-2803163510"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["61871106"],"award-info":[{"award-number":["61871106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Open Project Program Foundation of the Key Laboratory of Opto-Electronics Information Processing, Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["OEIP-O-202002"],"award-info":[{"award-number":["OEIP-O-202002"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tce.2024.3371451","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T18:54:57Z","timestamp":1709232897000},"page":"2257-2268","source":"Crossref","is-referenced-by-count":10,"title":["Ripple Transformer: A Human-Object Interaction Backbone and a New Prediction Strategy for Smart Surveillance Devices"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1700-3358","authenticated-orcid":false,"given":"Huadong","family":"Li","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0915-5378","authenticated-orcid":false,"given":"Ying","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1134-8787","authenticated-orcid":false,"given":"Shuailei","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6061-239X","authenticated-orcid":false,"given":"Mingyu","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0140-0949","authenticated-orcid":false,"given":"Ge","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3278704"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3266506"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3113908"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2023.3278466"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3303309"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2011.6131162"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2012.6311329"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00956"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00579"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413600"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16217"},{"key":"ref15","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"arXiv:2010.11929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20229"},{"key":"ref18","first-page":"17209","article-title":"Mining the benefits of two-stage and one-stage HOI detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2987465"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2613125"},{"key":"ref21","article-title":"ICAN: Instance-centric attention network for human-object interaction detection","author":"Gao","year":"2018","journal-title":"arXiv:1808.10437"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113856"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3098839"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3130716"},{"key":"ref27","article-title":"SpectralGPT: Spectral foundation model","author":"Hong","year":"2024","journal-title":"arXiv:2311.07113"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_36"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3220219"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025170"},{"key":"ref34","first-page":"1567","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00763"},{"key":"ref36","article-title":"Decoupling object detection from human-object interaction recognition","author":"Jin","year":"2021","journal-title":"arXiv:2112.06392"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_43"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00212"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00615"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107149"},{"key":"ref41","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"arXiv:1409.1556"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2016","journal-title":"arXiv:1511.07122"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref48","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015","journal-title":"arXiv:1505.04474"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"ref50","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref51","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Tan"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_25"},{"key":"ref56","article-title":"QAHOI: Query-based anchors for human-object interaction detection","author":"Chen","year":"2021","journal-title":"arXiv:2112.08647"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref58","article-title":"Shuffle transformer: Rethinking spatial shuffle for vision transformer","author":"Huang","year":"2021","journal-title":"arXiv:2106.03650"},{"key":"ref59","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"Yang","year":"2021","journal-title":"arXiv:2107.00641"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00977"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01458-8"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00093"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01303"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878958"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/30\/10510045\/10454595.pdf?arnumber=10454595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T18:25:39Z","timestamp":1739298339000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10454595\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":70,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tce.2024.3371451","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}