{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T22:03:57Z","timestamp":1769033037494,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339319","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Personalizing Retrieval Using Joint Embeddings; or \u201cthe Return of Fluffy\u201d"],"prefix":"10.1109","author":[{"given":"Bruno","family":"Korbar","sequence":"first","affiliation":[{"name":"Visual Geometry Group, University of Oxford,Oxford,UK"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"Visual Geometry Group, University of Oxford,Oxford,UK"}]}],"member":"263","reference":[{"key":"ref1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Evaluation of test-time adaptation under computational time constraints","volume-title":"Forty-first International Conference on Machine Learning, 2024","author":"Alfarra"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_32"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref6","article-title":"A versatile benchmark for detection, pose estimation, segmentation and reidentification of clothing images","author":"Ge","journal-title":"CVPR, 2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref8","article-title":"Compodiff: Versatile composed image retrieval with latent diffusion","volume-title":"Transactions on Machine Learning Research, z2024, expert Certification","author":"Gu"},{"key":"ref9","volume-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref10","article-title":"Vision-by-language for training-free compositional image retrieval","volume-title":"International Conference on Learning Representations (ICLR)","author":"Karthik"},{"key":"ref11","article-title":"Personalised clip or: how to find your vacation videos","author":"Korbar","year":"2022","journal-title":"BMVC"},{"key":"ref12","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref13","article-title":"Composing ensembles of pre-trained models via iterative consensus","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref15","article-title":"Clipcap: Clip prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref19","article-title":"Two effects, one trigger: On the modality gap, object bias, and information imbalance in contrastive vision-language representation learning","author":"Schrodi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01251"},{"key":"ref22","volume-title":"Reka core, flash, and edge: A series of powerful multimodal language models","author":"Team","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref27","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume":"35","author":"Yang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01833"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.01100","volume-title":"Sigmoid loss for language image pre-training","author":"Zhai","year":"2023"},{"key":"ref30","article-title":"Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhao"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.56"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339319.pdf?arnumber=11339319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:11:31Z","timestamp":1768979491000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339319\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339319","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}