{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T01:09:27Z","timestamp":1769044167517,"version":"3.49.0"},"reference-count":24,"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\/cbmi66578.2025.11339280","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Media Search: A Multi-Stage Image Retrieval Framework with Enriched Image Captioning"],"prefix":"10.1109","author":[{"given":"Ay\u015fe Vildan","family":"Nurda\u011f","sequence":"first","affiliation":[{"name":"Bahçeşehir University,Istanbul,Türkiye"}]},{"given":"Mete Mert","family":"Birdal","sequence":"additional","affiliation":[{"name":"Turkcell Technology,Istanbul,Türkiye"}]},{"given":"Yusuf","family":"Yaz\u0131c\u0131","sequence":"additional","affiliation":[{"name":"Turkcell Technology,Istanbul,Türkiye"}]},{"given":"Bar\u0131\u015f","family":"\u00d6zcan","sequence":"additional","affiliation":[{"name":"Bahçeşehir University,Istanbul,Türkiye"}]},{"given":"Erkut","family":"Ar\u0131can","sequence":"additional","affiliation":[{"name":"Bahçeşehir University,Istanbul,Türkiye"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/9658350"},{"key":"ref2","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of Machine Learning Research","volume":"202","author":"Li","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref5","article-title":"Deep visual-semantic alignments for generating image descriptions","volume":"abs\/1412.2306","author":"Karpathy","year":"2014","journal-title":"CoRR"},{"key":"ref6","article-title":"Learning transferable visual models from natural language supervision","volume":"abs\/2103.00020","author":"Radford","year":"2021","journal-title":"CoRR"},{"key":"ref7","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Li","year":"2022"},{"key":"ref8","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume":"abs\/2102.05918","author":"Jia","year":"2021","journal-title":"CoRR"},{"key":"ref9","volume-title":"Datacomp: In search of the next generation of multimodal datasets","author":"Gadre","year":"2023"},{"key":"ref10","article-title":"Sentence-bert: Sentence embeddings using siamese bert-networks","volume":"abs\/1908.10084","author":"Reimers","year":"2019","journal-title":"CoRR"},{"key":"ref11","article-title":"Billion-scale similarity search with gpus","volume":"abs\/1702.08734","author":"Johnson","year":"2017","journal-title":"CoRR"},{"key":"ref12","article-title":"Language-agnostic BERT sentence embedding","volume":"abs\/2007.01852","author":"Feng","year":"2020","journal-title":"CoRR"},{"key":"ref13","article-title":"Universal sentence encoder","volume":"abs\/1803.11175","author":"Cer","year":"2018","journal-title":"CoRR"},{"issue":"4","key":"ref14","first-page":"207","article-title":"A systematic review on stopword removal algorithms","volume":"4","author":"Kaur","year":"2018","journal-title":"International Journal on Future Revolution in Computer Science & Communication Engineering"},{"key":"ref15","volume-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022"},{"key":"ref16","article-title":"MURAL: multimodal, multitask retrieval across languages","volume":"abs\/2109.05125","author":"Jain","year":"2021","journal-title":"CoRR"},{"key":"ref17","volume-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"ref18","article-title":"A deep look into neural ranking models for information retrieval","volume":"abs\/1903.06902","author":"Guo","year":"2019","journal-title":"CoRR"},{"key":"ref19","article-title":"Text embeddings by weakly-supervised contrastive pre-training","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","volume-title":"Natural language processing with Python: analyzing text with the natural language toolkit","author":"Bird","year":"2009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref23","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref24","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee","year":"2005"}],"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\/11339280.pdf?arnumber=11339280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:11:18Z","timestamp":1768979478000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339280","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}