{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T23:57:50Z","timestamp":1773446270358,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004921","name":"Shanghai Jiao Tong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004921","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,14]]},"DOI":"10.1109\/icip55913.2025.11084645","type":"proceedings-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:41:38Z","timestamp":1755546098000},"page":"1780-1785","source":"Crossref","is-referenced-by-count":1,"title":["Exploring The Potential of Vision-Language Models for Pure-Image and Text-Guided-Image Saliency Prediction"],"prefix":"10.1109","author":[{"given":"Yuxin","family":"Zhu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Communication and Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Communication and Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Communication and Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Communication and Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick Le","family":"Callet","sequence":"additional","affiliation":[{"name":"Nantes Université, Ecole Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10182000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2851672"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.080"},{"key":"ref6","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref7","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref9","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref11","article-title":"A benchmark of computational models of saliency to predict human fixations","author":"Judd","year":"2012","journal-title":"MIT Technical Report"},{"key":"ref12","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref15","article-title":"Qwen2 technical report","author":"Qwen","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900174"},{"key":"ref17","article-title":"Salgan: Visual saliency prediction with generative adversarial networks","author":"Pan","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00625"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111279"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3461956"},{"key":"ref21","article-title":"Align before fuse: vision and language representation learning with momentum distillation","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)","author":"Li"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1167\/8.7.32"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.147"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.272"},{"key":"ref25","first-page":"681","article-title":"Dynamic visual attention: searching for coding length increments","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)","author":"Hou"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2011.5995506"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2009.5204207"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.103887"},{"key":"ref29","article-title":"Mistral 7b","author":"Jiang","year":"2023"},{"key":"ref30","article-title":"Opencompass: A universal evaluation platform for foundation models","year":"2023"}],"event":{"name":"2025 IEEE International Conference on Image Processing (ICIP)","location":"Anchorage, AK, USA","start":{"date-parts":[[2025,9,14]]},"end":{"date-parts":[[2025,9,17]]}},"container-title":["2025 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11084272\/11083968\/11084645.pdf?arnumber=11084645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T05:02:01Z","timestamp":1755579721000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11084645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icip55913.2025.11084645","relation":{},"subject":[],"published":{"date-parts":[[2025,9,14]]}}}