{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:10:50Z","timestamp":1778051450339,"version":"3.51.4"},"reference-count":89,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00161","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1597-1609","source":"Crossref","is-referenced-by-count":0,"title":["ORCA: Object Recognition and Comprehension for Archiving Marine Species"],"prefix":"10.1109","author":[{"given":"Yuk-Kwan","family":"Wong","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haixin","family":"Liang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiwei","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqiang","family":"Zheng","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rinaldi","family":"Gotama","sequence":"additional","affiliation":[{"name":"Indo Ocean Foundation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pascal","family":"Sebastian","sequence":"additional","affiliation":[{"name":"Indo Ocean Foundation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lauren D.","family":"Sparks","sequence":"additional","affiliation":[{"name":"Indo Ocean Foundation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sai-Kit","family":"Yeung","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4v(ision) system card","year":"2023"},{"key":"ref2","article-title":"World register of marine species (worms)","author":"Ahyong","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s23104643"},{"key":"ref4","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"},{"key":"ref5","article-title":"Seamapd21: A large-scale reef fish dataset for fine-grained categorization","volume-title":"Proceedings of the FGVC8: The Eight Workshop on Fine-Grained Visual Categorization","author":"Boulais"},{"key":"ref6","article-title":"Mmdetection: Open mmlab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01570"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18731-w"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref11","article-title":"RedCaps: Web-curated image-text data created by the people, for the people","author":"Desai","year":"2021","journal-title":"NeurIPS Datasets and Benchmarks"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.34133\/2022\/9870950"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1093\/icesjms\/fsab100"},{"key":"ref15","article-title":"Yolox: Exceeding yolo series in 2021","author":"Ge","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref19","article-title":"Trashcan: A semantically-segmented dataset towards visual detection of marine debris","author":"Hong","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340821"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01874"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.12.002"},{"key":"ref28","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021"},{"key":"ref29","first-page":"12888","article-title":"Blip: Bootstrapping language-image pretraining for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref30","article-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref31","article-title":"BLIP-2: bootstrapping language-image pretraining with frozen image encoders and large language models","volume-title":"ICML","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71058-3_12"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3093890"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00126"},{"key":"ref35","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/w13131847"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455997"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref40","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2021.06.084"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00754"},{"key":"ref45","article-title":"Introducing chatgpt","year":"2022"},{"key":"ref46","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref47","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"Ordonez","year":"2011","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.marpol.2024.106133"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref51","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01236"},{"key":"ref53","first-page":"139","article-title":"Collecting image annotations using Amazon\u2019s Mechanical Turk","volume-title":"Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon\u2019s Mechanical Turk","author":"Rashtchian"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref55","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref57","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28278"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328185"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01836"},{"key":"ref63","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref64","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01100"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2025.103402"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321501"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681071"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1057\/9781137410405.0018"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2022.155939"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03622-0"},{"key":"ref74","article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yuksekgonul"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5808206"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.70767\/jebe.v1i1.102"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124932"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3389\/fmars.2024.1396322"},{"key":"ref81","article-title":"Vl-checklist: Evaluating pre-trained vision-language models with objects, attributes and relations","author":"Zhao","year":"2022"},{"key":"ref82","article-title":"Marinegpt: Unlocking secrets of ocean to the public","author":"Zheng","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_14"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02661"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01857"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref87","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240616"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3028482"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492143.pdf?arnumber=11492143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:11:59Z","timestamp":1778047919000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492143\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00161","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}