{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:45:09Z","timestamp":1755798309327,"version":"3.44.0"},"reference-count":32,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,14]]},"DOI":"10.1109\/icip55913.2025.11084527","type":"proceedings-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:41:38Z","timestamp":1755546098000},"page":"1864-1869","source":"Crossref","is-referenced-by-count":0,"title":["SLICE: Synthetic Caption-Trained Lightweight Image Captioner for Edge Devices"],"prefix":"10.1109","author":[{"given":"Shayan","family":"Joya","sequence":"first","affiliation":[{"name":"Samsung Research,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soroush","family":"Fatemifar","sequence":"additional","affiliation":[{"name":"Samsung Research,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Akbari","sequence":"additional","affiliation":[{"name":"Samsung Research,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Sheppard","sequence":"additional","affiliation":[{"name":"Samsung Research,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Alder","sequence":"additional","affiliation":[{"name":"Samsung Research,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPHYS.2019.8780171"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.320"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCICT50803.2021.9510102"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref5","article-title":"Tinybert: Distilling BERT for natural language understanding","author":"Jiao","year":"2019","journal-title":"CoRR"},{"key":"ref6","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","author":"Wang","year":"2022","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00668"},{"article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25359"},{"key":"ref10","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume-title":"NIPS","volume":"28","author":"Ren"},{"article-title":"Deformable transformers for end-to-end object detection","volume-title":"ICLR","author":"Zhu","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref13","article-title":"Efficientvlm: Fast and accurate vision-language models via knowledge distillation and modal-adaptive pruning","author":"Wang","year":"2022","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref15","article-title":"Clipcap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49357.2023.10096424","article-title":"I-tuning: Tuning frozen language models with image for lightweight image captioning","volume-title":"ICASSP","author":"Luo"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"ref20","article-title":"Are sixteen heads really better than one?","volume-title":"NIPS","volume":"32","author":"Michel"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","key":"ref21"},{"key":"ref22","article-title":"LAION-400M: open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Geoffrey","key":"ref28"},{"key":"ref29","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"CoRR"},{"article-title":"Git: A generative image-to-text transformer for vision and language","year":"2022","author":"Wang","key":"ref30"},{"key":"ref31","article-title":"Minivlm: A smaller and faster vision-language model","author":"Wang","year":"2020","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00146"}],"event":{"name":"2025 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2025,9,14]]},"location":"Anchorage, AK, USA","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\/11084527.pdf?arnumber=11084527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T04:51:50Z","timestamp":1755579110000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11084527\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icip55913.2025.11084527","relation":{},"subject":[],"published":{"date-parts":[[2025,9,14]]}}}