{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T08:16:59Z","timestamp":1772093819683,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819549719","type":"print"},{"value":"9789819549726","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:00:00Z","timestamp":1764201600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:00:00Z","timestamp":1764201600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4972-6_13","type":"book-chapter","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T08:08:37Z","timestamp":1764144517000},"page":"161-173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["When Language Model Guides Vision: Grounding DINO for\u00a0Cattle Muzzle Detection"],"prefix":"10.1007","author":[{"given":"Rabin","family":"Dulal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Ashad","family":"Kabir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,27]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Ahmed, S.U., Frnda, J., Waqas, M., Khan, M.H.: Dataset of cattle biometrics through muzzle images. Data Brief, 110125 (2024)","DOI":"10.1016\/j.dib.2024.110125"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Anitha, J., Avanthika, R., Kavipriya, B., Vishnupriya, S.: Cattle identification using muzzle images. In: Applied Data Science and Smart Systems, pp. 370\u2013377 (2024)","DOI":"10.1201\/9781003471059-48"},{"issue":"3","key":"13_CR3","doi-asserted-by":"publisher","first-page":"726","DOI":"10.26599\/BDMA.2024.9020098","volume":"8","author":"W Cao","year":"2025","unstructured":"Cao, W., Yao, X., Xu, Z., Liu, Y., Pan, Y., Ming, Z.: A survey of zero-shot object detection. Big Data Min. Analytics 8(3), 726\u2013750 (2025)","journal-title":"Big Data Min. Analytics"},{"key":"13_CR4","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: Proceedings of the European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"13_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale (2020). arXiv:2010.11929"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Dulal, R., Zheng, L., Kabir, M.A.: MHAFF: multihead attention feature fusion of CNN and transformer for cattle identification. IEEE Trans. AgriFood Electr., 1\u201312 (2025)","DOI":"10.1109\/TAFE.2025.3574708"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Dulal, R., et al.: Automatic cattle identification using YOLOv5 and mosaic augmentation: a comparative analysis. In: International Conference on Digital Image Computing: Techniques and Applications. pp.\u00a01\u20138. IEEE (2022)","DOI":"10.1109\/DICTA56598.2022.10034585"},{"key":"13_CR8","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation (2021). arXiv:2104.13921"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Hossain, M.E., Kabir, A., Zheng, L., Swain, D., McGrath, S., Medway, J.: A systematic review of machine learning techniques for cattle identification: datasets, methods and future directions. Artif. Intell. Agric. (2022)","DOI":"10.1016\/j.aiia.2022.09.002"},{"issue":"12","key":"13_CR11","doi-asserted-by":"publisher","first-page":"2056007","DOI":"10.1142\/S0218001420560078","volume":"34","author":"W Kusakunniran","year":"2020","unstructured":"Kusakunniran, W., et al.: Biometric for cattle identification using muzzle patterns. Int. J. Pattern Recognit Artif Intell. 34(12), 2056007 (2020)","journal-title":"Int. J. Pattern Recognit Artif Intell."},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Lee, T., Na, Y., Kim, B.G., Lee, S., Choi, Y.: Identification of individual Hanwoo cattle by muzzle pattern images through deep learning. Animals 13(18) (2023)","DOI":"10.3390\/ani13182856"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Lienhart, R., Maydt, J.: An extended set of Haar-like features for rapid object detection. In: Proceedings. International Conference on Image Processing, vol.\u00a01, pp.\u00a0I\u2013I. IEEE (2002)","DOI":"10.1109\/ICIP.2002.1038171"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Proceedings of the European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: European Conference on Computer Vision, pp. 38\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Minderer, M., et\u00a0al.: Simple open-vocabulary object detection. In: European Conference on Computer Vision, pp. 728\u2013755. Springer (2022)","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"13_CR20","unstructured":"Nawaz, U., et al.: AgriCLIP: adapting clip for agriculture and livestock via domain-specialized cross-model alignment (2024). arXiv:2410.01407"},{"issue":"4","key":"13_CR21","first-page":"4051","volume":"45","author":"F Pourpanah","year":"2022","unstructured":"Pourpanah, F., et al.: A review of generalized zero-shot learning methods. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4051\u20134070 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR22","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"13_CR24","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement (2018). arXiv:1804.02767"},{"key":"13_CR25","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"issue":"11","key":"13_CR26","doi-asserted-by":"publisher","first-page":"2365","DOI":"10.3390\/agronomy11112365","volume":"11","author":"A Shojaeipour","year":"2021","unstructured":"Shojaeipour, A., Falzon, G., Kwan, P., Hadavi, N., Cowley, F.C., Paul, D.: Automated muzzle detection and biometric identification via few-shot deep transfer learning of mixed breed cattle. Agronomy 11(11), 2365 (2021)","journal-title":"Agronomy"},{"key":"13_CR27","unstructured":"Ultralytics: the state-of-the-art yolo model. https:\/\/github.com\/ultralytics\/yolov5. Accessed 15 Jan 2023"},{"key":"13_CR28","unstructured":"Ultralytics: the state-of-the-art yolo model. https:\/\/ultralytics.com\/yolov8. Accessed 15 Jan 2023"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors (2022). arXiv:2207.02696","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"13_CR30","unstructured":"Xu, X., et al.: Few-shot cow identification via meta-learning. Inf. Process. Agric. (2024)"},{"key":"13_CR31","unstructured":"Yao, L., et al.: DetCLIP: dictionary-enriched visual-concept paralleled pre-training for open-world detection. In: Advances in Neural Information Processing Systems, vol. 35, pp. 9125\u20139138 (2022)"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C.: Open-vocabulary DETR with conditional matching. In: European Conference on Computer Vision. Springer (2022)","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, T., Liu, P., Lee, K.: OmDet: large-scale vision-language multi-dataset pre-training with multimodal detection network. IET Comput. Vis. 18(5) (2024)","DOI":"10.1049\/cvi2.12268"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: RegionCLIP: region-based language-image pretraining. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"}],"container-title":["Lecture Notes in Computer Science","AI 2025: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4972-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T07:23:45Z","timestamp":1772090625000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4972-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,27]]},"ISBN":["9789819549719","9789819549726"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4972-6_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,27]]},"assertion":[{"value":"27 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canberra, ACT","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}