{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:19:57Z","timestamp":1761895197658,"version":"build-2065373602"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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\/501100017607","name":"Shenzhen Fundamental Research Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210151","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["GiVE: Guiding Visual Encoder to Perceive Overlooked Information"],"prefix":"10.1109","author":[{"given":"Junjie","family":"Li","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}]},{"given":"Jianghong","family":"Ma","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}]},{"given":"Xiaofeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}]},{"given":"Yuhang","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}]},{"given":"Jianyang","family":"Shi","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107320"},{"key":"ref5","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023","journal-title":"CoRR"},{"key":"ref6","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2017","journal-title":"NIPS"},{"article-title":"Masked image residual learning for scaling deeper vision transformers","volume-title":"NeurIPS","author":"Huang","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612036"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","volume":"139","author":"Radford"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3318216"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3218275"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"article-title":"Simple open-vocabulary object detection with vision transformers","volume-title":"ECCV","author":"Minderer","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5040\/9798881817916.ch-004"},{"article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume-title":"NeurIPS","author":"Dai","key":"ref22"},{"article-title":"FILIP: fine-grained interactive language-image pre-training","volume-title":"ICLR","author":"Yao","key":"ref23"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210151.pdf?arnumber=11210151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:45:40Z","timestamp":1761889540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210151","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}