{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:00:23Z","timestamp":1791910823372,"version":"4.3.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225112"],"award-info":[{"award-number":["62225112"]}],"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":["62271312"],"award-info":[{"award-number":["62271312"]}],"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":["62301310"],"award-info":[{"award-number":["62301310"]}],"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":["62301316"],"award-info":[{"award-number":["62301316"]}],"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":["623B2073"],"award-info":[{"award-number":["623B2073"]}],"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":["62471290"],"award-info":[{"award-number":["62471290"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["2024NSFSC1426"],"award-info":[{"award-number":["2024NSFSC1426"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/jstsp.2025.3558652","type":"journal-article","created":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T13:57:11Z","timestamp":1747663031000},"page":"1349-1361","source":"Crossref","is-referenced-by-count":9,"title":["R-Bench: Are Your Large Multimodal Model Robust to Real-World Corruptions?"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0634-1710","authenticated-orcid":false,"given":"Chunyi","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-7938","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8642-8101","authenticated-orcid":false,"given":"Haoning","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6073-8582","authenticated-orcid":false,"given":"Yuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8162-1949","authenticated-orcid":false,"given":"Wei","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-0090","authenticated-orcid":false,"given":"Guo","family":"Lu","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6377-4730","authenticated-orcid":false,"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[{"name":"John Hopcroft Center, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9866-1947","authenticated-orcid":false,"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5241-0069","authenticated-orcid":false,"given":"Xiao-Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical, Computer and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1335-2"},{"key":"ref2","article-title":"Cisco visual networking index: Forecast and trends, 20182023","year":"2020","journal-title":"White Paper"},{"key":"ref3","article-title":"Beyond efficiency: A systematic survey of resource-efficient large language models","author":"Bai","year":"2024"},{"key":"ref4","first-page":"1","article-title":"RobustBench: A standardized adversarial robustness benchmark","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","volume":"1","author":"Croce","year":"2021"},{"key":"ref5","first-page":"34405","article-title":"Robustness analysis of video-language models against visual and language perturbations","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Schiappa","year":"2022"},{"key":"ref6","first-page":"54111","article-title":"On evaluating adversarial robustness of large vision-language models","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Zhao","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02325"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00395"},{"key":"ref9","first-page":"1","article-title":"Benchmarking robustness of multimodal image-text models under distribution shift","volume":"2","author":"Qiu","year":"2024","journal-title":"J. Data-Centric Mach. Learn. Res."},{"key":"ref10","article-title":"Benchmarking large multimodal models against common corruptions","author":"Zhang","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949270"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758239"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681152"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.13344"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref18","first-page":"1","article-title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-Level Vision","volume-title":"Proc. Twelfth Int. Conf. Learn. Representations","author":"Wu","year":"2023"},{"key":"ref19","article-title":"grok-1.5v","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref21","first-page":"57730","article-title":"MM-Vet: Evaluating large multimodal models for integrated capabilities","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Yu","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref23","first-page":"54015","article-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Wu","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"ref27","first-page":"1","article-title":"A-bench: Are lmms masters at evaluating ai-generated images?","volume-title":"Proc. Thirteenth Int. Conf. Learn. Representations","author":"Zhang","year":"2025"},{"key":"ref28","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024"},{"key":"ref29","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref30","article-title":"Deepseek-vl: Towards real-world vision-language understanding","author":"Lu","year":"2024"},{"key":"ref31","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Dai","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref33","article-title":"InternLM-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024"},{"key":"ref34","first-page":"34892","article-title":"Visual Instruction Tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref35","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3D in large multimodal models","author":"Li","year":"2024"},{"key":"ref36","first-page":"1","article-title":"Llava-onevision: Easy visual task transfer","volume":"1","author":"Li","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref37","article-title":"MiniCPM-V: A GPT-4V level MLLM on your phone","author":"Yao","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref40","article-title":"mPLUG-Owl3: Towards long image-sequence understanding in multi-modal large language models","author":"Ye","year":"2024"},{"key":"ref41","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref42","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref43","article-title":"Qwen2-VL: Enhancing vision-language models perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref49","first-page":"1","article-title":"Emergent abilities of large language models","volume":"1","author":"Wei","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_5"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_1"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02168-7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11320985\/11006523.pdf?arnumber=11006523","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T20:59:46Z","timestamp":1770929986000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11006523\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":56,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2025.3558652","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}