{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T15:45:58Z","timestamp":1775490358183,"version":"3.50.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3597396","type":"journal-article","created":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T17:44:23Z","timestamp":1754934263000},"page":"143688-143712","source":"Crossref","is-referenced-by-count":4,"title":["A Comprehensive Review of Recent Advances in Multimodal Multimedia Indexing and Retrieval"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8462-435X","authenticated-orcid":false,"given":"Chethan","family":"Sharma","sequence":"first","affiliation":[{"name":"Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9620-5526","authenticated-orcid":false,"given":"G.","family":"Poornalatha","sequence":"additional","affiliation":[{"name":"Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3995-1826","authenticated-orcid":false,"given":"K. B.","family":"Ajitha Shenoy","sequence":"additional","affiliation":[{"name":"Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/2.410146"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/34.895972"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1348246.1348248"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1126004.1126005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/b:mtap.0000046380.27575.a5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2006.63"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.10.019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tevc.2022.3155533"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5961-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3308911"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNB.2022.3169701"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3131340"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1126004.1126005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.35741\/issn.0258-2724.54.3.19"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icnlsp.2018.8374390"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2018.2800163"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3324021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268091"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3333294"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3330975"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.2984916"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/sym12020282"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3301042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/s20061741"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3380006"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3295776"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3218591"},{"key":"ref29","first-page":"1678","article-title":"Interactive audio indexing and speech recognition based navigation assist tool for tutoring videos","volume-title":"Proc. Int. Conf. Sustain. Comput. Data Commun. Syst. (ICSCDS)","author":"Gareshma"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc5030033"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3170711"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3487759"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2023.3241849"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3095957"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3271303"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3450920"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3302517"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3220297"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/HDIS60872.2023.10499467"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MetroXRAINE58569.2023.10405728"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3221430"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3406018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3515455"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2023.3321382"},{"key":"ref45","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2023.3271303"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.502"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2024.3359062"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3565506"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2396761.2398735"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref52","first-page":"1","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lundberg"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.29284\/ijasis.8.2.2022.18-25"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3617233.3617261"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3357939"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3043298"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3150414"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3377239"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3310245"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3324133"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3141433"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3030858"},{"key":"ref63","article-title":"Flamingo: A visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"arXiv:2204.14198"},{"key":"ref64","volume-title":"MiniGPT-4: Enhancing Vision-Language Understanding With GPT-4","author":"Zhu","year":"2023"},{"key":"ref65","article-title":"Language is not all you need: Aligning perception with language models","author":"Huang","year":"2023","journal-title":"arXiv:2302.14045"},{"key":"ref66","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref67","article-title":"Enhancing historical image retrieval with compositional cues","author":"Lin","year":"2024","journal-title":"arXiv:2403.14287"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3011102"},{"key":"ref69","article-title":"Unsupervised semantic deep hashing","author":"Jin","year":"2018","journal-title":"arXiv:1803.06911"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2018.2868826"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3610949"},{"key":"ref72","article-title":"Multimodal sentiment analysis based on causal reasoning","author":"Chen","year":"2024","journal-title":"arXiv:2412.07292"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02008"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3161156"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3390\/e25050730"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02238"},{"key":"ref77","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Lewis"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11121833.pdf?arnumber=11121833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:43:40Z","timestamp":1755715420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11121833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3597396","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}