{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:56:03Z","timestamp":1763060163658,"version":"3.45.0"},"reference-count":61,"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":["62322212","U23A20387"],"award-info":[{"award-number":["62322212","U23A20387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAS Project for Young Scientists in Basic Research","award":["YSBR-116"],"award-info":[{"award-number":["YSBR-116"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3607726","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:33:09Z","timestamp":1757439189000},"page":"8888-8899","source":"Crossref","is-referenced-by-count":0,"title":["SPDQ: Synergetic Prompts as Disentanglement Queries for Compositional Zero-Shot Learning"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6760-6914","authenticated-orcid":false,"given":"Han","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-9755","authenticated-orcid":false,"given":"Xiaoshan","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7970-7698","authenticated-orcid":false,"given":"Chaofan","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547798"},{"key":"ref2","first-page":"1462","article-title":"A causal view of compositional zero-shot recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Atzmon","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_7"},{"key":"ref4","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chen","year":"2022"},{"key":"ref5","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3156938"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3399453"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2984091"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01470"},{"key":"ref10","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"issue":"2","key":"ref11","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"1","author":"Hu","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02266"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28026"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00085"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28043"},{"key":"ref19","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Mahabadi","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00912"},{"key":"ref21","first-page":"3828","article-title":"Learning attention propagation for compositional zero-shot learning","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis.","author":"Gul","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"article-title":"ADAM: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref23"},{"article-title":"Towards more human-like concept learning in machines: Compositionality, causality, and learning-to-learn","year":"2014","author":"Lake","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref26","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755208"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00911"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01133"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01612"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02536"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00029"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02256"},{"article-title":"DRPT: Disentangled and recurrent prompt tuning for compositional zero-shot learning","year":"2023","author":"Lu","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00518"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3163667"},{"key":"ref37","article-title":"Mixed precision training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Micikevicius","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3033124"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.129"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_11"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018811"},{"key":"ref43","article-title":"Learning to compose soft prompts for compositional zero-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nayak","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00369"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref47","first-page":"10641","article-title":"Independent prototype propagation for zero-shot compositionality","volume":"34","author":"Ruis","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01329"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/163"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01077"},{"article-title":"Task-aware feature generation for zero-shot compositional learning","year":"2019","author":"Wang","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00384"},{"article-title":"Prompting large pre-trained vision-language models for compositional concept learning","year":"2022","author":"Xu","key":"ref53"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3104411"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3200578"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3125134"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.32"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00174"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11154064.pdf?arnumber=11154064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:45:01Z","timestamp":1763059501000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11154064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3607726","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}