{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T11:12:07Z","timestamp":1783768327597,"version":"3.55.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52571384"],"award-info":[{"award-number":["52571384"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02315-9","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:40:20Z","timestamp":1778046020000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing underwater object detection through hybrid sparse-annotation optimization"],"prefix":"10.1007","volume":"32","author":[{"given":"Haiwen","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyang","family":"Teng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"issue":"1","key":"2315_CR1","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s44295-024-00023-6","volume":"2","author":"M Jian","year":"2024","unstructured":"Jian, M., Yang, N., Tao, C., Zhi, H., Luo, H.: Underwater object detection and datasets: a survey. Intell. Mar. Technol. Syst. 2(1), 9 (2024)","journal-title":"Intell. Mar. Technol. Syst."},{"key":"2315_CR2","doi-asserted-by":"publisher","first-page":"75","DOI":"10.4031\/MTSJ.51.1.8","volume":"51","author":"Q Xi","year":"2017","unstructured":"Xi, Q., Rauschenbach, T., Daoliang, L.: Review of underwater machine vision technology and its applications. Mar. Technol. Soc. J. 51, 75\u201397 (2017)","journal-title":"Mar. Technol. Soc. J."},{"key":"2315_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s10033-020-00449-z","volume":"33","author":"M Lin","year":"2020","unstructured":"Lin, M., Yang, C.: Ocean observation technologies: A review. Chin. J. Mech. Eng. 33, 1\u201318 (2020)","journal-title":"Chin. J. Mech. Eng."},{"issue":"1","key":"2315_CR4","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1111\/fog.12619","volume":"32","author":"FB Schwing","year":"2023","unstructured":"Schwing, F.B.: Modern technologies and integrated observing systems are \u201cinstrumental\u2019\u2019 to fisheries oceanography: A brief history of ocean data collection. Fish. Oceanogr. 32(1), 28\u201369 (2023)","journal-title":"Fish. Oceanogr."},{"key":"2315_CR5","first-page":"1","volume":"62","author":"G Chen","year":"2024","unstructured":"Chen, G., Mao, Z., Tu, Q., Shen, J.: A cooperative training framework for underwater object detection on a clearer view. IEEE Trans. Geosci. Remote Sens. 62, 1\u201317 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2315_CR6","doi-asserted-by":"crossref","unstructured":"Drews-Jr, P.L.J., Nascimento, E.R., Moraes, F.C., Botelho, S.S.C., Campos, M.F.M.: Transmission estimation in underwater single images. 2013 IEEE International Conference on Computer Vision Workshops, 825\u2013830 (2013)","DOI":"10.1109\/ICCVW.2013.113"},{"key":"2315_CR7","doi-asserted-by":"crossref","unstructured":"Ancuti, C., Ancuti, C.O., Haber, T., Bekaert, P.: Enhancing underwater images and videos by fusion. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 81\u201388 (2012). IEEE","DOI":"10.1109\/CVPR.2012.6247661"},{"key":"2315_CR8","doi-asserted-by":"publisher","first-page":"122078","DOI":"10.1109\/ACCESS.2020.3006359","volume":"8","author":"G Hou","year":"2020","unstructured":"Hou, G., Zhao, X., Pan, Z., Yang, H., Tan, L., Li, J.: Benchmarking underwater image enhancement and restoration, and beyond. IEEE Access 8, 122078\u2013122091 (2020)","journal-title":"IEEE Access"},{"issue":"5","key":"2315_CR9","doi-asserted-by":"publisher","first-page":"3437","DOI":"10.1007\/s00371-024-03611-z","volume":"41","author":"S Xu","year":"2025","unstructured":"Xu, S., Wang, J., He, N., Xu, G., Zhang, G.: Optimizing underwater image enhancement: integrating semi-supervised learning and multi-scale aggregated attention. Vis. Comput. 41(5), 3437\u20133455 (2025)","journal-title":"Vis. Comput."},{"key":"2315_CR10","doi-asserted-by":"publisher","first-page":"4376","DOI":"10.1109\/TIP.2019.2955241","volume":"29","author":"C Li","year":"2019","unstructured":"Li, C., Guo, C., Ren, W., Cong, R., Hou, J., Kwong, S., Tao, D.: An underwater image enhancement benchmark dataset and beyond. IEEE Trans. Image Process. 29, 4376\u20134389 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"2315_CR11","unstructured":"Wu, Z., Bodla, N., Singh, B., Najibi, M., Chellappa, R., Davis, L.S.: Soft sampling for robust object detection. In: British Machine Vision Conference (2018). https:\/\/api.semanticscholar.org\/CorpusID:49310502"},{"key":"2315_CR12","unstructured":"Liu, Y.-C., Ma, C.-Y., He, Z., Kuo, C.-W., Chen, K., Zhang, P., Wu, B., Kira, Z., Vajda, P.: Unbiased teacher for semi-supervised object detection. ArXiv abs\/2102.09480 (2021)"},{"key":"2315_CR13","unstructured":"Sohn, K., Zhang, Z., Li, C.-L., Zhang, H., Lee, C.-Y., Pfister, T.: A simple semi-supervised learning framework for object detection. ArXiv abs\/2005.04757 (2020)"},{"key":"2315_CR14","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In: Neural Information Processing Systems (2017). https:\/\/api.semanticscholar.org\/CorpusID:263861232"},{"key":"2315_CR15","doi-asserted-by":"crossref","unstructured":"Deng, J., Li, W., Chen, Y., Duan, L.: Unbiased mean teacher for cross-domain object detection. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4089\u20134099 (2020)","DOI":"10.1109\/CVPR46437.2021.00408"},{"key":"2315_CR16","doi-asserted-by":"crossref","unstructured":"Wang, K., Zhuang, J., Li, G., Fang, C., Cheng, L., Lin, L., Zhou, F.: De-biased teacher: Rethinking iou matching for semi-supervised object detection. In: AAAI Conference on Artificial Intelligence (2023). https:\/\/api.semanticscholar.org\/CorpusID:259720938","DOI":"10.1609\/aaai.v37i2.25355"},{"key":"2315_CR17","doi-asserted-by":"crossref","unstructured":"Wang, X., Yang, X., Zhang, S., Li, Y., Feng, L., Fang, S., Lyu, C., Chen, K., Zhang, W.: Consistent-teacher: Towards reducing inconsistent pseudo-targets in semi-supervised object detection. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 3240\u20133249 (2022)","DOI":"10.1109\/CVPR52729.2023.00316"},{"key":"2315_CR18","doi-asserted-by":"crossref","unstructured":"Zhou, H., Ge, Z., Liu, S., Mao, W., Li, Z., Yu, H., Sun, J.: Dense teacher: Dense pseudo-labels for semi-supervised object detection. ArXiv abs\/2207.02541 (2022)","DOI":"10.1007\/978-3-031-20077-9_3"},{"key":"2315_CR19","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Hu, H., Wang, J., Wang, L., Wei, F., Bai, X., Liu, Z.: End-to-end semi-supervised object detection with soft teacher. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 3040\u20133049 (2021)","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"2315_CR20","doi-asserted-by":"crossref","unstructured":"Yang, Q., Wei, X., Wang, B., Hua, X., Zhang, L.: Interactive self-training with mean teachers for semi-supervised object detection. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 5937\u20135946 (2021)","DOI":"10.1109\/CVPR46437.2021.00588"},{"key":"2315_CR21","doi-asserted-by":"crossref","unstructured":"Niitani, Y., Akiba, T., Kerola, T., Ogawa, T., Sano, S., Suzuki, S.: Sampling techniques for large-scale object detection from sparsely annotated objects. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6503\u20136511 (2018)","DOI":"10.1109\/CVPR.2019.00667"},{"key":"2315_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, H., Chen, F., Shen, Z., Hao, Q., Zhu, C., Savvides, M.: Solving missing-annotation object detection with background recalibration loss. ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1888\u20131892 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053738"},{"key":"2315_CR23","doi-asserted-by":"crossref","unstructured":"Rambhatla, S.S., Suri, S., Chellappa, R., Shrivastava, A.: Sparsedet: Improving sparsely annotated object detection with pseudo-positive mining. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), 6747\u20136758 (2022)","DOI":"10.1109\/ICCV51070.2023.00623"},{"key":"2315_CR24","doi-asserted-by":"crossref","unstructured":"Wang, H., Liu, L., Zhang, B., Zhang, J., Zhang, W., Gan, Z., Wang, Y., Wang, C., Wang, H.: Calibrated teacher for sparsely annotated object detection. In: AAAI Conference on Artificial Intelligence (2023). https:\/\/api.semanticscholar.org\/CorpusID:257504807","DOI":"10.1609\/aaai.v37i2.25349"},{"key":"2315_CR25","doi-asserted-by":"crossref","unstructured":"Wu, L., Han, J., Zheng, Z., Wang, X.: Co-student: Collaborating strong and weak students for sparsely annotated object detection. In: European Conference on Computer Vision (2024). https:\/\/api.semanticscholar.org\/CorpusID:274435375","DOI":"10.1007\/978-3-031-72970-6_26"},{"key":"2315_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111414","volume":"159","author":"Z Lu","year":"2025","unstructured":"Lu, Z., Liao, L., Li, C., Xie, X., Yuan, H.: A diffusion model and knowledge distillation framework for robust coral detection in complex underwater environments. Eng. Appl. Artif. Intell. 159, 111414 (2025)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"2315_CR27","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: Eapt: efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"2315_CR28","doi-asserted-by":"crossref","unstructured":"Wen, Y., Luo, B., Shi, W., Ji, J., Cao, W., Yang, X., Sheng, B.: Sat-net: structure-aware transformer-based attention fusion network for low-quality retinal fundus images enhancement. IEEE Transactions on Multimedia (2025)","DOI":"10.1109\/TMM.2025.3565935"},{"key":"2315_CR29","first-page":"1","volume":"63","author":"G Chen","year":"2025","unstructured":"Chen, G., Mao, Z., Shen, J., Cheng, Z.: Pseudo-label guided object detection in sparsely annotated underwater optical images. IEEE Trans. Geosci. Remote Sens. 63, 1\u201321 (2025)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"6","key":"2315_CR30","doi-asserted-by":"publisher","first-page":"4033","DOI":"10.1007\/s00371-024-03644-4","volume":"41","author":"Q Cen","year":"2025","unstructured":"Cen, Q., Zhu, Q., Wang, Y., Chen, W., Liu, S.: Yolov9-yx: Lightweight algorithm for underwater target detection. Vis. Comput. 41(6), 4033\u20134045 (2025)","journal-title":"Vis. Comput."},{"key":"2315_CR31","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. ArXiv abs\/2002.05709 (2020)"},{"key":"2315_CR32","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9726\u20139735 (2019)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2315_CR33","unstructured":"Chen, X., Fan, H., Girshick, R.B., He, K.: Improved baselines with momentum contrastive learning. ArXiv abs\/2003.04297 (2020)"},{"key":"2315_CR34","unstructured":"Grill, J.-B., Strub, F., Altch\u2019e, F., Tallec, C., Richemond, P.H., Buchatskaya, E., Doersch, C., Pires, B.\u00c1., Guo, Z.D., Azar, M.G., Piot, B., Kavukcuoglu, K., Munos, R., Valko, M.: Bootstrap your own latent: A new approach to self-supervised learning. ArXiv abs\/2006.07733 (2020)"},{"key":"2315_CR35","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. ArXiv abs\/2006.09882 (2020)"},{"key":"2315_CR36","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: Self-supervised learning via redundancy reduction. ArXiv abs\/2103.03230 (2021)"},{"key":"2315_CR37","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u2019egou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 9630\u20139640 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2315_CR38","doi-asserted-by":"crossref","unstructured":"Xie, E., Ding, J., Wang, W., Zhan, X., Xu, H., Li, Z., Luo, P.: Detco: Unsupervised contrastive learning for object detection. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 8372\u20138381 (2021)","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"2315_CR39","unstructured":"Jeong, J., Lee, S., Kim, J., Kwak, N.: Consistency-based semi-supervised learning for object detection. In: Neural Information Processing Systems (2019). https:\/\/api.semanticscholar.org\/CorpusID:202782547"},{"key":"2315_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, Q.-f., Yu, C., Wang, Z., Qian, Q., Li, H.: Instant-teaching: An end-to-end semi-supervised object detection framework. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4079\u20134088 (2021)","DOI":"10.1109\/CVPR46437.2021.00407"},{"key":"2315_CR41","unstructured":"Wang, T., Yang, T., Cao, J., Zhang, X.: Co-mining: Self-supervised learning for sparsely annotated object detection. ArXiv abs\/2012.01950 (2020)"},{"key":"2315_CR42","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: Fully convolutional one-stage object detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), 9626\u20139635 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2315_CR43","doi-asserted-by":"crossref","unstructured":"Liu, C., Li, H., Wang, S., Zhu, M., Wang, D., Fan, X., Wang, Z.: A dataset and benchmark of underwater object detection for robot picking. 2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), 1\u20136 (2021)","DOI":"10.1109\/ICMEW53276.2021.9455997"},{"key":"2315_CR44","doi-asserted-by":"publisher","first-page":"4985","DOI":"10.1109\/TIP.2021.3076367","volume":"30","author":"C Li","year":"2021","unstructured":"Li, C., Anwar, S., Hou, J., Cong, R., Guo, C., Ren, W.: Underwater image enhancement via medium transmission-guided multi-color space embedding. IEEE Trans. Image Process. 30, 4985\u20135000 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"2315_CR45","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S.J., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: European Conference on Computer Vision (2014). https:\/\/api.semanticscholar.org\/CorpusID:14113767","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02315-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02315-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02315-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:19:02Z","timestamp":1783765142000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02315-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2315"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02315-9","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"9 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"250"}}