{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T23:42:05Z","timestamp":1775778125559,"version":"3.50.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62222207"],"award-info":[{"award-number":["62222207"]}],"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":["62072245"],"award-info":[{"award-number":["62072245"]}],"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":["61932020"],"award-info":[{"award-number":["61932020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20211520"],"award-info":[{"award-number":["BK20211520"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Anhui Jianzhu University Anhui Province Key Laboratory of Intelligent Building & Building Energy Saving","award":["IBES2024KF02"],"award-info":[{"award-number":["IBES2024KF02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521658","type":"journal-article","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T19:23:57Z","timestamp":1735327437000},"page":"401-413","source":"Crossref","is-referenced-by-count":7,"title":["GPT4Ego: Unleashing the Potential of Pre-Trained Models for Zero-Shot Egocentric Action Recognition"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4111-9334","authenticated-orcid":false,"given":"Guangzhao","family":"Dai","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-4663","authenticated-orcid":false,"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"given":"Wenhao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney, Sydney NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0694-9458","authenticated-orcid":false,"given":"Rui","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3124-9461","authenticated-orcid":false,"given":"Jiachao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Industrial Technology Research Institute, Nanjing Institute of Technology, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref2","article-title":"Florence: A new foundation model for computer","author":"Yuan","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547793"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00806"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350992"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01414"},{"key":"ref7","first-page":"7575","article-title":"Egocentric video-language pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref11","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref12","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref13","article-title":"LLAMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"issue":"1","key":"ref14","first-page":"11 324","article-title":"PALM: Scaling language modeling with pathways","volume-title":"J. Mach. Learn. Res.","volume":"24","author":"Chowdhery","year":"2024"},{"key":"ref15","article-title":"GPT4IMAGE: Can large pre-trained models help vision models on perception tasks","author":"Ding","year":"2023"},{"key":"ref16","article-title":"GPT4VIS: What can GPT-4 do for zero-shot visual recognition","author":"Wu","year":"2023"},{"key":"ref17","first-page":"69706","article-title":"ChatGPT-powered hierarchical comparisons for image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref21","article-title":"Charades-EGO: A large-scale dataset of paired third and first person videos","author":"Sigurdsson","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3199970"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361861"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806216"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942030"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3078882"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3139768"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3148588"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612144"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00315"},{"key":"ref36","first-page":"1976","article-title":"Is an object-centric video representation beneficial for transfer","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Zhang","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3015894"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6907"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS56176.2022.9959207"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_35"},{"key":"ref42","article-title":"Language models are unsupervised multitask learners","volume-title":"Proc. OpenAI Blog","author":"Alec","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00269"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01100"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01479"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25273"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3271353"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3386914"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28388"},{"key":"ref50","first-page":"5880","article-title":"DM2C: Deep mixed-modal clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang","year":"2019"},{"key":"ref51","first-page":"39090","article-title":"OTKGE: Multi-modal knowledge graph embeddings via optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01620"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28500"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475202"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239751"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3264847"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref58","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref61","first-page":"26462","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan","year":"2022"},{"key":"ref62","article-title":"Aim: Adapting image models for efficient video understanding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2023"},{"key":"ref63","article-title":"Gpt-4v(ision) system card","year":"2023"},{"key":"ref64","article-title":"MM-VID: Advancing video understanding with gpt-4v (ision)","author":"Lin","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref66","article-title":"Exploring OCR capabilities of GPT-4V (ision): A quantitative and in-depth evaluation","author":"Shi","year":"2023"},{"key":"ref67","article-title":"Exploring recommendation capabilities of GPT-4V (ision): A preliminary case study","author":"Zhou","year":"2023"},{"key":"ref68","doi-asserted-by":"crossref","article-title":"Performance of multimodal GPT-4V on USMLE with image: Potential for imaging diagnostic support with explanations","author":"Yang","DOI":"10.1101\/2023.10.26.23297629"},{"key":"ref69","doi-asserted-by":"crossref","article-title":"A comprehensive study of GPT-4V\u2019s multimodal capabilities in medical imaging","author":"Li","DOI":"10.1101\/2023.11.03.23298067"},{"key":"ref70","first-page":"1","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu","year":"2024"},{"key":"ref71","article-title":"On the road with GPT-4V (ision): Early explorations of visual-language model on autonomous driving","author":"Wen","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3709005"},{"key":"ref73","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref74","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref75","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac","year":"2022"},{"key":"ref76","first-page":"34 892","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref77","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022"},{"key":"ref78","first-page":"24 993","article-title":"Fine-grained visual prompting","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2023"},{"key":"ref79","first-page":"1","article-title":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Sudhakaran","year":"2018"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02209"},{"key":"ref82","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10817586.pdf?arnumber=10817586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:56:56Z","timestamp":1737399416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10817586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521658","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}