{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:25:22Z","timestamp":1742916322789,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781124"},{"type":"electronic","value":"9783031781131"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-78113-1_2","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:00:45Z","timestamp":1733245245000},"page":"16-28","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Modal Ship Grounding: Towards Large Model for Enhanced Few-Shot Learning"],"prefix":"10.1007","author":[{"given":"Quan","family":"Hu","sequence":"first","affiliation":[]},{"given":"Li","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Zhida","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Yaojie","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2_CR2","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: International Conference on Learning Representations (2021). https:\/\/api.semanticscholar.org\/CorpusID:238744187"},{"key":"2_CR3","unstructured":"Hu, J.E., et al.: Lora: low-rank adaptation of large language models. arXiv abs\/2106.09685 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235458009"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Huang, Q., Sun, H., Wang, Y., Yuan, Y., Guo, X., Gao, Q.: Ship detection based on yolo algorithm for visible images. IET Image Process. (2023)","DOI":"10.1049\/ipr2.12963"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR-modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"2_CR6","unstructured":"Ke, L., et al.: Segment anything in high quality. arXiv preprint arXiv:2306.01567 (2023)"},{"issue":"6","key":"2_CR7","doi-asserted-by":"publisher","first-page":"936","DOI":"10.3390\/app8060936","volume":"8","author":"K Kim","year":"2018","unstructured":"Kim, K., Hong, S., Choi, B., Kim, E.: Probabilistic ship detection and classification using deep learning. Appl. Sci. 8(6), 936 (2018)","journal-title":"Appl. Sci."},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3992\u20134003 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257952310","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2_CR9","unstructured":"Koch, G., Zemel, R., Salakhutdinov, R., et\u00a0al.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, vol.\u00a02. Lille (2015)"},{"key":"2_CR10","unstructured":"Leela, S., Roh, M.I., Ohb, M.: Image-based ship detection using deep learning. Ocean Syst. Eng. 10 (2020)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Liao, Y., et al.: A real-time cross-modality correlation filtering method for referring expression comprehension. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10880\u201310889 (2020)","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Liu, D., Zhang, H., Wu, F., Zha, Z.J.: Learning to assemble neural module tree networks for visual grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4673\u20134682 (2019)","DOI":"10.1109\/ICCV.2019.00477"},{"key":"2_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2021.109435","volume":"235","author":"RW Liu","year":"2021","unstructured":"Liu, R.W., Yuan, W., Chen, X., Lu, Y.: An enhanced CNN-enabled learning method for promoting ship detection in maritime surveillance system. Ocean Eng. 235, 109435 (2021)","journal-title":"Ocean Eng."},{"key":"2_CR14","unstructured":"Liu, S., et al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. arXiv abs\/2303.05499 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257427307"},{"issue":"1","key":"2_CR15","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nat. Commun. 15(1), 654 (2024)","journal-title":"Nat. Commun."},{"key":"2_CR16","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"2_CR17","unstructured":"Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: International Conference on Learning Representations (2016). https:\/\/api.semanticscholar.org\/CorpusID:67413369"},{"key":"2_CR18","unstructured":"Reis, D., Kupec, J., Hong, J., Daoudi, A.: Real-time flying object detection with yolov8. arXiv preprint arXiv:2305.09972 (2023)"},{"issue":"3","key":"2_CR19","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1109\/TCSVT.2019.2897980","volume":"30","author":"Z Shao","year":"2019","unstructured":"Shao, Z., Wang, L., Wang, Z., Du, W., Wu, W.: Saliency-aware convolution neural network for ship detection in surveillance video. IEEE Trans. Circuits Syst. Video Technol. 30(3), 781\u2013794 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Shao, Z., Wu, W., Wang, Z., Du, W., Li, C.: Seaships: a large-scale precisely annotated dataset for ship detection. IEEE Trans. Multimedia 20, 2593\u20132604 (2018). https:\/\/api.semanticscholar.org\/CorpusID:52285314","DOI":"10.1109\/TMM.2018.2865686"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Su, J.C., Maji, S., Hariharan, B.: When does self-supervision improve few-shot learning? In: European Conference on Computer Vision, pp. 645\u2013666. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58571-6_38"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Cao, J., Shen, C., Gao, L., Hengel, A.V.D.: Neighbourhood watch: referring expression comprehension via language-guided graph attention networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1960\u20131968 (2019)","DOI":"10.1109\/CVPR.2019.00206"},{"key":"2_CR23","unstructured":"Yang, J., Chen, H., Yan, J., Chen, X., Yao, J.: Towards better understanding and better generalization of few-shot classification in histology images with contrastive learning. arXiv preprint arXiv:2202.09059 (2022)"},{"key":"2_CR24","doi-asserted-by":"publisher","first-page":"5121","DOI":"10.1109\/TIP.2022.3193223","volume":"31","author":"L Yang","year":"2022","unstructured":"Yang, L., et al.: Pdnet: toward better one-stage object detection with prediction decoupling. IEEE Trans. Image Process. 31, 5121\u20135133 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR25","doi-asserted-by":"publisher","unstructured":"Yang, Z., Chen, T., Wang, L., Luo, J.: Improving one-stage visual grounding by recursive sub-query construction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 387\u2013404. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_23","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gong, B., Wang, L., Huang, W., Yu, D., Luo, J.: A fast and accurate one-stage approach to visual grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4683\u20134693 (2019)","DOI":"10.1109\/ICCV.2019.00478"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"2_CR28","unstructured":"Zhang, C., et al.: Faster segment anything: towards lightweight SAM for mobile applications. arXiv preprint arXiv:2306.14289 (2023)"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"2_CR30","doi-asserted-by":"publisher","unstructured":"Zhu, X., Ma, Y., Wang, T., Xu, Y., Shi, J., Lin, D.: SSN: shape signature networks for multi-class object detection from point clouds. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 581\u2013597. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_35","DOI":"10.1007\/978-3-030-58595-2_35"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78113-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:03:51Z","timestamp":1733245431000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78113-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031781124","9783031781131"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78113-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}