{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:32:53Z","timestamp":1763191973930,"version":"3.45.0"},"reference-count":49,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228953","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data"],"prefix":"10.1109","author":[{"given":"Yiqun","family":"Duan","sequence":"first","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sameera","family":"Ramasinghe","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Gould","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajanthan","family":"Thalaiyasingam","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"article-title":"Layer normalization","year":"2016","author":"Ba","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01764"},{"article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","year":"2023","author":"Bubeck","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_32"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref12"},{"article-title":"Modality-agnostic attention fusion for visual search with text feedback","year":"2020","author":"Dodds","key":"ref13"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103617"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.05.003"},{"article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","year":"2022","author":"Gal","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"article-title":"Compodiff: Versatile composed image retrieval with latent diffusion","year":"2023","author":"Gu","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_37"},{"article-title":"Prompt-to-prompt image editing with cross attention control","year":"2022","author":"Hertz","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"article-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref25"},{"article-title":"On weight initialization in deep neural networks","year":"2017","author":"Kumar","key":"ref26"},{"article-title":"Data roaming and early fusion for composed image retrieval","year":"2023","author":"Levy","key":"ref27"},{"key":"ref28","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"article-title":"Clip surgery for better explainability with enhancement in open-vocabulary tasks","year":"2023","author":"Li","key":"ref29"},{"article-title":"Exploring visual interpretability for contrastive language-image pre-training","year":"2022","author":"Li","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"Visual instruction tuning","year":"2023","author":"Liu","key":"ref33"},{"article-title":"Zero-shot composed text-image retrieval","year":"2023","author":"Liu","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00565"},{"article-title":"Candidate set re-ranking for composed image retrieval with dual multi-modal encoder","year":"2023","author":"Liu","key":"ref37"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref38"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","year":"2022","author":"Schuhmann","key":"ref42"},{"article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","year":"2021","author":"Schuhmann","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2034"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228953.pdf?arnumber=11228953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:51Z","timestamp":1763191731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228953\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228953","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}