{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:35:36Z","timestamp":1787013336668,"version":"build-2736575974"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Beijing Natural Science - Xiaomi Innovation Joint Foundation","award":["L253007"],"award-info":[{"award-number":["L253007"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376020"],"award-info":[{"award-number":["62376020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025307"],"award-info":[{"award-number":["62025307"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20331"],"award-info":[{"award-number":["U24A20331"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202470"],"award-info":[{"award-number":["62202470"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473363"],"award-info":[{"award-number":["62473363"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L251005"],"award-info":[{"award-number":["L251005"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Xinjiang Uyghur Autonomous Region","award":["2023B01005"],"award-info":[{"award-number":["2023B01005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tpami.2025.3642837","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T18:45:23Z","timestamp":1765478723000},"page":"4114-4131","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning-Based Sequential Parameter Tuning for Image Signal Processing"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1980-0098","authenticated-orcid":false,"given":"Xinyu","family":"Sun","sequence":"first","affiliation":[{"name":"Key Laboratory of Big Data & Artificial Intelligence in Transportation, Ministry of Education, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5888-6735","authenticated-orcid":false,"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6059-7943","authenticated-orcid":false,"given":"Congyan","family":"Lang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Big Data & Artificial Intelligence in Transportation, Ministry of Education, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3010-0738","authenticated-orcid":false,"given":"Zhikun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Big Data & Artificial Intelligence in Transportation, Ministry of Education, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3848-9433","authenticated-orcid":false,"given":"Juan","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8192-8803","authenticated-orcid":false,"given":"Weihua","family":"Xiong","sequence":"additional","affiliation":[{"name":"People AI, Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9237-8825","authenticated-orcid":false,"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7565-8788","authenticated-orcid":false,"given":"Long","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2352\/issn.2470-1173.2021.17.avm-174"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijleo.2015.05.074"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2019.01.015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging5100078"},{"key":"ref6","first-page":"1","article-title":"Understanding the in-camera image processing pipeline for computer vision","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.-Tutorial","volume":"3","author":"Brown","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ieeestd.2023.10205967"},{"key":"ref8","first-page":"199","article-title":"Collaborative hyperparameter tuning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bardenet","year":"2013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2019.15.AVM-044"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00421"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00347"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322996"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3446791"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00755"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00623"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451818"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02137"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982399"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051486"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01691"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2872858"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28307"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681666"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_3"},{"key":"ref26","first-page":"112598","article-title":"Adaptiveisp: Learning an adaptive image signal processor for object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32721"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3021904"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3055511"},{"key":"ref31","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton","year":"1999"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref33","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref36","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref37","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"},{"key":"ref38","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu","year":"2022"},{"key":"ref39","article-title":"Recursive self-improvement for camera image and signal processing pipeline","author":"Bajaj","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00189"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981361"},{"key":"ref42","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3233\/MGS-2007-3108"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2003.09.014"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.58"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref47","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref48","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"ref49","article-title":"ultralytics\/yolov5: V5.0 - YOLOv5-p6 1280 models, aws, supervise.ly and youtube integrations","author":"Jocher","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IWSSIP48289.2020.9145130"},{"key":"ref51","article-title":"Simplified action decoder for deep multi-agent reinforcement learning","author":"Hu","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00276"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1177\/1084713806289514"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/30.468045"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1407714"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1021\/acsomega.8b01270"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01358.x"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/3477.764879"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.14778\/2904121.2904125"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10035-z"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref66","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11424231\/11297856.pdf?arnumber=11297856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:34:45Z","timestamp":1773106485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11297856\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":66,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3642837","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}