{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:09:45Z","timestamp":1771952985311,"version":"3.50.1"},"publisher-location":"Cham","reference-count":73,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726262","type":"print"},{"value":"9783031726279","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72627-9_14","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"239-257","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["MarineInst: A Foundation Model for\u00a0Marine Image Analysis with\u00a0Instance Visual Description"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1477-6040","authenticated-orcid":false,"given":"Ziqiang","family":"Zheng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7790-6503","authenticated-orcid":false,"given":"Yiwei","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7101-0495","authenticated-orcid":false,"given":"Huimin","family":"Zeng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8872-0875","authenticated-orcid":false,"given":"Tuan-Anh","family":"Vu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5706-8634","authenticated-orcid":false,"given":"Binh-Son","family":"Hua","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7974-0607","authenticated-orcid":false,"given":"Sai-Kit","family":"Yeung","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"14_CR1","unstructured":"Flickr. https:\/\/www.flickr.com\/"},{"key":"14_CR2","unstructured":"Getty Images. https:\/\/www.gettyimages.com\/"},{"key":"14_CR3","unstructured":"Shutterstock. https:\/\/www.shutterstock.com\/"},{"key":"14_CR4","unstructured":"Encyclopedia of life (2018). http:\/\/eol.org"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Akkaynak, D., Treibitz, T.: Sea-Thru: a method for removing water from underwater images. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1682\u20131691 (2019)","DOI":"10.1109\/CVPR.2019.00178"},{"key":"14_CR6","doi-asserted-by":"publisher","unstructured":"Alawode, B., et al.: UTB180: a high-quality benchmark for underwater tracking. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds.) Computer Vision, ACCV 2022. LNCS, vol. 13845, pp. 3326\u20133342. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-26348-4_26","DOI":"10.1007\/978-3-031-26348-4_26"},{"issue":"7","key":"14_CR7","doi-asserted-by":"publisher","first-page":"e0130312","DOI":"10.1371\/journal.pone.0130312","volume":"10","author":"O Beijbom","year":"2015","unstructured":"Beijbom, O., et al.: Towards automated annotation of benthic survey images: variability of human experts and operational modes of automation. PLoS ONE 10(7), e0130312 (2015)","journal-title":"PLoS ONE"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Bovcon, B., Muhovi\u010d, J., Per\u0161, J., Kristan, M.: The MaSTr1325 dataset for training deep USV obstacle detection models. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3431\u20133438. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8967909"},{"key":"14_CR9","unstructured":"Chen, J., Yang, Z., Zhang, L.: Semantic segment anything (2023). https:\/\/github.com\/fudan-zvg\/Semantic-Segment-Anything"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, Y., et al.: FloW: a dataset and benchmark for floating waste detection in inland waters. In: IEEE\/CVF International Conference on Computer Vision (ICCV), October 2021, pp. 10953\u201310962 (2021)","DOI":"10.1109\/ICCV48922.2021.01077"},{"key":"14_CR11","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https:\/\/vicuna.lmsys.org"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"14_CR13","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"14_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/978-3-030-58565-5_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Fan","year":"2020","unstructured":"Fan, B., Chen, W., Cong, Y., Tian, J.: Dual refinement underwater object detection network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 275\u2013291. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_17"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Fulton, M., Hong, J., Islam, M.J., Sattar, J.: Robotic detection of marine litter using deep visual detection models. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 5752\u20135758. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793975"},{"key":"14_CR16","unstructured":"Gunasekar, S., et\u00a0al.: Textbooks are all you need. arXiv preprint arXiv:2306.11644 (2023)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"14_CR18","unstructured":"Haixin, L., Ziqiang, Z., Zeyu, M., Yeung, S.K.: MarineDet: towards open-marine object detection. arXiv preprint arXiv:2310.01931 (2023)"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"14_CR20","unstructured":"Hong, J., Fulton, M., Sattar, J.: TrashCan: a semantically-segmented dataset towards visual detection of marine debris. arXiv preprint arXiv:2007.08097 (2020)"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Hong, L., Wang, X., Zhang, G., Zhao, M.: USOD10K: a new benchmark dataset for underwater salient object detection. IEEE Trans. Image Process. (TIP) (2023)","DOI":"10.1109\/TIP.2023.3266163"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Huynh, D., Kuen, J., Lin, Z., Gu, J., Elhamifar, E.: Open-vocabulary instance segmentation via robust cross-modal pseudo-labeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7020\u20137031 (2022)","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Islam, M.J., et al.: Semantic segmentation of underwater imagery: dataset and benchmark. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1769\u20131776. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9340821"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Islam, M.J., Wang, R., Sattar, J.: SVAM: saliency-guided visual attention modeling by autonomous underwater robots. In: Robotics: Science and Systems (2022)","DOI":"10.15607\/RSS.2022.XVIII.048"},{"key":"14_CR25","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning (ICML), pp. 4904\u20134916. PMLR (2021)"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Khan, F.F., Li, X., Temple, A.J., Elhoseiny, M.: FishNet: a large-scale dataset and benchmark for fish recognition, detection, and functional trait prediction. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 20496\u201320506 (2023)","DOI":"10.1109\/ICCV51070.2023.01874"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Kim, D., Angelova, A., Kuo, W.: Region-aware pretraining for open-vocabulary object detection with vision transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11144\u201311154 (2023)","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"14_CR29","unstructured":"Li, C., et al.: ELEVATER: a benchmark and toolkit for evaluating language-augmented visual models. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 35, pp. 9287\u20139301 (2022)"},{"key":"14_CR30","unstructured":"Li, F., et al.: Semantic-SAM: segment and recognize anything at any granularity. arXiv preprint arXiv:2307.04767 (2023)"},{"key":"14_CR31","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning (ICML) (2023)"},{"key":"14_CR32","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning (ICML), pp. 12888\u201312900. PMLR (2022)"},{"issue":"4","key":"14_CR33","doi-asserted-by":"publisher","first-page":"2303","DOI":"10.1109\/TCSVT.2021.3093890","volume":"32","author":"L Li","year":"2021","unstructured":"Li, L., Dong, B., Rigall, E., Zhou, T., Dong, J., Chen, G.: Marine animal segmentation. IEEE Trans. Circ. Syst. Video Technol. (TCSVT) 32(4), 2303\u20132314 (2021)","journal-title":"IEEE Trans. Circ. Syst. Video Technol. (TCSVT)"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2359\u20132367 (2017)","DOI":"10.1109\/CVPR.2017.472"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Lian, S., Li, H., Cong, R., Li, S., Zhang, W., Kwong, S.: WaterMask: instance segmentation for underwater imagery. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1305\u20131315 (2023)","DOI":"10.1109\/ICCV51070.2023.00126"},{"key":"14_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Lin, X., Sanket, N.J., Karapetyan, N., Aloimonos, Y.: OysterNet: enhanced oyster detection using simulation. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 5170\u20135176. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160830"},{"key":"14_CR38","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"14_CR40","doi-asserted-by":"crossref","unstructured":"Marques, T.P., Albu, A.B.: L2UWE: a framework for the efficient enhancement of low-light underwater images using local contrast and multi-scale fusion. In: IEEE\/CVF conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 538\u2013539 (2020)","DOI":"10.1109\/CVPRW50498.2020.00277"},{"key":"14_CR41","unstructured":"OpenAI: Introducing ChatGPT (2022). https:\/\/openai.com\/blog\/chatgpt"},{"key":"14_CR42","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Palnitkar, A., Kapu, R., Lin, X., Liu, C., Karapetyan, N., Aloimonos, Y.: ChatSim: underwater simulation with natural language prompting. arXiv preprint arXiv:2308.04029 (2023)","DOI":"10.23919\/OCEANS52994.2023.10337406"},{"key":"14_CR44","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML), pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR45","unstructured":"Ren, T., et al.: Grounded SAM: assembling open-world models for diverse visual tasks (2024)"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR47","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"14_CR48","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 8430\u20138439 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"issue":"4","key":"14_CR49","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1109\/JOE.2022.3162864","volume":"47","author":"Z Shi","year":"2022","unstructured":"Shi, Z., et al.: Detecting marine organisms via joint attention-relation learning for marine video surveillance. IEEE J. Oceanic Eng. 47(4), 959\u2013974 (2022)","journal-title":"IEEE J. Oceanic Eng."},{"key":"14_CR50","doi-asserted-by":"crossref","unstructured":"Sun, G., et al.: Indiscernible object counting in underwater scenes. In: IEEE\/CVF International Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01325"},{"key":"14_CR51","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: Alpha-CLIP: A CLIP model focusing on wherever you want. arXiv preprint arXiv:2312.03818 (2023)","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"14_CR52","unstructured":"Tang, L., Xiao, H., Li, B.: Can SAM segment anything? When SAM meets camouflaged object detection. arXiv preprint arXiv:2304.04709 (2023)"},{"issue":"1","key":"14_CR53","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1038\/s41559-022-01937-2","volume":"7","author":"SB Tebbett","year":"2023","unstructured":"Tebbett, S.B., Connolly, S.R., Bellwood, D.R.: Benthic composition changes on coral reefs at global scales. Nat. Ecol. Evol. 7(1), 71\u201381 (2023)","journal-title":"Nat. Ecol. Evol."},{"key":"14_CR54","doi-asserted-by":"publisher","unstructured":"Truong, Q.T., et al.: Marine video kit: a new marine video dataset for content-based analysis and retrieval. In: Dang-Nguyen, DT., et al. (eds.) MultiMedia Modeling, MMM 2023. LNCS, vol. 13833, pp. 539\u2013550. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-27077-2_42","DOI":"10.1007\/978-3-031-27077-2_42"},{"key":"14_CR55","doi-asserted-by":"crossref","unstructured":"Urbanek, J., Bordes, F., Astolfi, P., Williamson, M., Sharma, V., Romero-Soriano, A.: A picture is worth more than 77 text tokens: evaluating clip-style models on dense captions. arXiv preprint arXiv:2312.08578 (2023)","DOI":"10.1109\/CVPR52733.2024.02521"},{"key":"14_CR56","doi-asserted-by":"crossref","unstructured":"Varghese, N., Kumar, A., Rajagopalan, A.: Self-supervised monocular underwater depth recovery, image restoration, and a real-sea video dataset. In: IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 12248\u201312258 (2023)","DOI":"10.1109\/ICCV51070.2023.01125"},{"key":"14_CR57","unstructured":"Xu, H., et al.: Demystifying clip data. arXiv preprint arXiv:2309.16671 (2023)"},{"key":"14_CR58","doi-asserted-by":"crossref","unstructured":"Xu, X., Xiong, T., Ding, Z., Tu, Z.: MasQCLIP for open-vocabulary universal image segmentation. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 887\u2013898 (2023)","DOI":"10.1109\/ICCV51070.2023.00088"},{"key":"14_CR59","unstructured":"Yu, Q., He, J., Deng, X., Shen, X., Chen, L.C.: Convolutions die hard: open-vocabulary segmentation with single frozen convolutional clip. arXiv preprint arXiv:2308.02487 (2023)"},{"key":"14_CR60","doi-asserted-by":"crossref","unstructured":"Yuan, H., Li, X., Zhou, C., Li, Y., Chen, K., Loy, C.C.: Open-vocabulary SAM: segment and recognize twenty-thousand classes interactively. arXiv preprint (2024)","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"14_CR61","doi-asserted-by":"publisher","first-page":"210041","DOI":"10.1109\/ACCESS.2020.3038643","volume":"8","author":"X Zhang","year":"2020","unstructured":"Zhang, X., Zeng, H., Liu, X., Yu, Z., Zheng, H., Zheng, B.: In situ holothurian noncontact counting system: a general framework for holothurian counting. IEEE Access 8, 210041\u2013210053 (2020)","journal-title":"IEEE Access"},{"key":"14_CR62","unstructured":"Zheng, Z., et al.: Exploring boundary of GPT-4V on marine analysis: a preliminary case study. arXiv preprint arXiv:2401.02147 (2024)"},{"key":"14_CR63","doi-asserted-by":"crossref","unstructured":"Zheng, Z., et al.: Marine video cloud: a cloud-based video analytics platform for collaborative marine research. In: OCEANS, pp.\u00a01\u20136. IEEE (2023)","DOI":"10.1109\/OCEANSLimerick52467.2023.10244597"},{"key":"14_CR64","doi-asserted-by":"crossref","unstructured":"Zheng, Z., et al.: CoralSCOP: segment any coral image on this planet. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28170\u201328180 (2024)","DOI":"10.1109\/CVPR52733.2024.02661"},{"key":"14_CR65","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Xin, Z., Yu, Z., Yeung, S.K.: Real-time GAN-based image enhancement for robust underwater monocular SLAM. Front. Marine Sci. 10 (2023)","DOI":"10.3389\/fmars.2023.1161399"},{"key":"14_CR66","unstructured":"Zheng, Z., Zhang, J., Vu, T.A., Diao, S., Tim, Y.H.W., Yeung, S.K.: MarineGPT: unlocking secrets of ocean to the public. arXiv preprint arXiv:2310.13596 (2023)"},{"key":"14_CR67","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: RegionCLIP: region-based language-image pretraining. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"14_CR68","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"14_CR69","doi-asserted-by":"publisher","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from CLIP. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13688, pp. 696\u2013712. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_40","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"14_CR70","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"key":"14_CR71","doi-asserted-by":"crossref","unstructured":"Zhuang, P., Wang, Y., Qiao, Y.: WildFish: a large benchmark for fish recognition in the wild. In: ACM International Conference on Multimedia (ACM MM), pp. 1301\u20131309 (2018)","DOI":"10.1145\/3240508.3240616"},{"key":"14_CR72","doi-asserted-by":"publisher","first-page":"3603","DOI":"10.1109\/TMM.2020.3028482","volume":"23","author":"P Zhuang","year":"2020","unstructured":"Zhuang, P., Wang, Y., Qiao, Y.: WildFish++: a comprehensive fish benchmark for multimedia research. IEEE Trans. Multimedia (TMM) 23, 3603\u20133617 (2020)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"14_CR73","unstructured":"Ziqiang, Z., Yaofeng, X., Haixin, L., Zhibin, Y., Yeung, S.K.: CoralVOS: dataset and benchmark for coral video segmentation. arXiv preprint arXiv:2310.01946 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72627-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T22:45:54Z","timestamp":1732920354000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72627-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9783031726262","9783031726279"],"references-count":73,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72627-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}