{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T06:22:18Z","timestamp":1794637338755,"version":"4.9.1"},"reference-count":60,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["EP\/X040186\/1"],"award-info":[{"award-number":["EP\/X040186\/1"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T028572\/1"],"award-info":[{"award-number":["EP\/T028572\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000272","name":"National Institute for Health and Care Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["ERC-ADG-2015 694581"],"award-info":[{"award-number":["ERC-ADG-2015 694581"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1016\/j.media.2025.103611","type":"journal-article","created":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T02:12:14Z","timestamp":1746151934000},"page":"103611","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":7,"special_numbering":"C","title":["TIER-LOC: Visual Query-based Video Clip Localization in fetal ultrasound videos with a multi-tier transformer"],"prefix":"10.1016","volume":"103","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3264-8739","authenticated-orcid":false,"given":"Divyanshu","family":"Mishra","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pramit","family":"Saha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8264-9297","authenticated-orcid":false,"given":"He","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3603-4806","authenticated-orcid":false,"given":"Netzahualcoyotl","family":"Hernandez-Cruz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olga","family":"Patey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aris T.","family":"Papageorghiou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3060-3772","authenticated-orcid":false,"given":"J. Alison","family":"Noble","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"11","key":"10.1016\/j.media.2025.103611_b1","doi-asserted-by":"crossref","first-page":"2204","DOI":"10.1109\/TMI.2017.2712367","article-title":"SonoNet: real-time detection and localisation of fetal standard scan planes in freehand ultrasound","volume":"36","author":"Baumgartner","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2025.103611_b2","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19","first-page":"203","article-title":"Real-time standard scan plane detection and localisation in fetal ultrasound using fully convolutional neural networks","author":"Baumgartner","year":"2016"},{"key":"10.1016\/j.media.2025.103611_b3","series-title":"European Conference on Computer Vision","first-page":"548","article-title":"A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses","author":"Boudiaf","year":"2020"},{"key":"10.1016\/j.media.2025.103611_b4","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part I","first-page":"871","article-title":"Multi-task sonoeyenet: detection of fetal standardized planes assisted by generated sonographer attention maps","author":"Cai","year":"2018"},{"key":"10.1016\/j.media.2025.103611_b5","series-title":"ISUOG practice guidelines (updated): sonographic screening examination of the fetal heart","author":"Carvalho","year":"2013"},{"key":"10.1016\/j.media.2025.103611_b6","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part I 18","first-page":"507","article-title":"Automatic fetal ultrasound standard plane detection using knowledge transferred recurrent neural networks","author":"Chen","year":"2015"},{"key":"10.1016\/j.media.2025.103611_b7","first-page":"10551","article-title":"Rethinking the bottom-up framework for query-based video localization","volume":"vol. 34","author":"Chen","year":"2020"},{"issue":"5","key":"10.1016\/j.media.2025.103611_b8","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/JBHI.2015.2425041","article-title":"Standard plane localization in fetal ultrasound via domain transferred deep neural networks","volume":"19","author":"Chen","year":"2015","journal-title":"IEEE J. Biomed. Heal. Informatics"},{"issue":"6","key":"10.1016\/j.media.2025.103611_b9","doi-asserted-by":"crossref","first-page":"1576","DOI":"10.1109\/TCYB.2017.2685080","article-title":"Ultrasound standard plane detection using a composite neural network framework","volume":"47","author":"Chen","year":"2017","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.media.2025.103611_b10","series-title":"2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1","first-page":"539","article-title":"Learning a similarity metric discriminatively, with application to face verification","author":"Chopra","year":"2005"},{"key":"10.1016\/j.media.2025.103611_b11","series-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"issue":"1","key":"10.1016\/j.media.2025.103611_b12","doi-asserted-by":"crossref","first-page":"14109","DOI":"10.1038\/s41598-021-92829-1","article-title":"Transforming obstetric ultrasound into data science using eye tracking, voice recording, transducer motion and ultrasound video","volume":"11","author":"Drukker","year":"2021","journal-title":"Sci. Rep."},{"key":"10.1016\/j.media.2025.103611_b13","series-title":"CVPR 2021","article-title":"Multiscale vision transformers","author":"Fan","year":"2021"},{"key":"10.1016\/j.media.2025.103611_b14","series-title":"Computer Vision \u2013 ECCV 2022 Workshops","first-page":"422","article-title":"Anatomy-aware contrastive representation learning for fetal ultrasound","author":"Fu","year":"2023"},{"key":"10.1016\/j.media.2025.103611_b15","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R., 2017. Tall: Temporal activity localization via language query. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 5267\u20135275.","DOI":"10.1109\/ICCV.2017.563"},{"key":"10.1016\/j.media.2025.103611_b16","doi-asserted-by":"crossref","unstructured":"Ge, W., 2018. Deep metric learning with hierarchical triplet loss. In: Proceedings of the European Conference on Computer Vision. ECCV, pp. 269\u2013285.","DOI":"10.1007\/978-3-030-01231-1_17"},{"key":"10.1016\/j.media.2025.103611_b17","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11-14, 2016, Proceedings, Part VI 14","first-page":"241","article-title":"Deep image retrieval: Learning global representations for image search","author":"Gordo","year":"2016"},{"key":"10.1016\/j.media.2025.103611_b18","series-title":"MINOTAUR: Multi-task video grounding from multimodal queries","author":"Goyal","year":"2023"},{"key":"10.1016\/j.media.2025.103611_b19","unstructured":"Grauman, K., Westbury, A., Byrne, E., Chavis, Z., Furnari, A., Girdhar, R., Hamburger, J., Jiang, H., Liu, M., Liu, X., et al., 2022. Ego4d: Around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18995\u201319012."},{"key":"10.1016\/j.media.2025.103611_b20","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y., 2017. Learning spatio-temporal features with 3d residual networks for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision Workshops. pp. 3154\u20133160.","DOI":"10.1109\/ICCVW.2017.373"},{"key":"10.1016\/j.media.2025.103611_b21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.media.2025.103611_b22","series-title":"Localizing moments in video with temporal language","author":"Hendricks","year":"2018"},{"key":"10.1016\/j.media.2025.103611_b23","series-title":"Single-stage visual query localization in egocentric videos","author":"Jiang","year":"2023"},{"key":"10.1016\/j.media.2025.103611_b24","series-title":"International Conference on Information Processing in Medical Imaging","first-page":"729","article-title":"Principled ultrasound data augmentation for classification of standard planes","author":"Lee","year":"2021"},{"key":"10.1016\/j.media.2025.103611_b25","doi-asserted-by":"crossref","unstructured":"Lee, S., Lee, S., Seong, H., Kim, E., 2023. Revisiting Self-Similarity: Structural Embedding for Image Retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 23412\u201323421.","DOI":"10.1109\/CVPR52729.2023.02242"},{"key":"10.1016\/j.media.2025.103611_b26","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2025.103611_b27","doi-asserted-by":"crossref","unstructured":"Li, Y., Wu, C.-Y., Fan, H., Mangalam, K., Xiong, B., Malik, J., Feichtenhofer, C., 2022. Mvitv2: Improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4804\u20134814.","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"10.1016\/j.media.2025.103611_b28","doi-asserted-by":"crossref","unstructured":"Lin, K.Q., Zhang, P., Chen, J., Pramanick, S., Gao, D., Wang, A.J., Yan, R., Shou, M.Z., 2023. Univtg: Towards unified video-language temporal grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2794\u20132804.","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"10.1016\/j.media.2025.103611_b29","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, S., Wu, Y., Chen, C.-W., Shan, Y., Qie, X., 2022a. Umt: Unified multi-modal transformers for joint video moment retrieval and highlight detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3042\u20133051.","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"10.1016\/j.media.2025.103611_b30","doi-asserted-by":"crossref","unstructured":"Liu, D., Qu, X., Dong, J., Zhou, P., Cheng, Y., Wei, W., Xu, Z., Xie, Y., 2021. Context-aware biaffine localizing network for temporal sentence grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11235\u201311244.","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"10.1016\/j.media.2025.103611_b31","first-page":"1683","article-title":"Unsupervised temporal video grounding with deep semantic clustering","volume":"vol. 36","author":"Liu","year":"2022"},{"key":"10.1016\/j.media.2025.103611_b32","doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, X., Nie, L., Tian, Q., Chen, B., Chua, T.S., 2018. Cross-modal moment localization in videos. In: Proceedings of the 26th ACM International Conference on Multimedia. pp. 843\u2013851.","DOI":"10.1145\/3240508.3240549"},{"issue":"3","key":"10.1016\/j.media.2025.103611_b33","doi-asserted-by":"crossref","first-page":"276","DOI":"10.11613\/BM.2012.031","article-title":"Interrater reliability: the kappa statistic","volume":"22","author":"McHugh","year":"2012","journal-title":"Biochem. Medica"},{"key":"10.1016\/j.media.2025.103611_b34","series-title":"2023 IEEE 20th International Symposium on Biomedical Imaging","first-page":"1","article-title":"Towards standard plane prediction of fetal head ultrasound with domain adaption","author":"Men","year":"2023"},{"key":"10.1016\/j.media.2025.103611_b35","series-title":"Proceedings of Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024","article-title":"STAN-LOC: Visual Query-based Video Clip Localization for Fetal Ultrasound Sweep Videos","volume":"vol. LNCS 15004","author":"Mishra","year":"2024"},{"key":"10.1016\/j.media.2025.103611_b36","doi-asserted-by":"crossref","unstructured":"Moon, W., Hyun, S., Park, S., Park, D., Heo, J.P., 2023. Query-dependent video representation for moment retrieval and highlight detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 23023\u201323033.","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"10.1016\/j.media.2025.103611_b37","doi-asserted-by":"crossref","unstructured":"Mun, J., Cho, M., Han, B., 2020. Local-global video-text interactions for temporal grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10810\u201310819.","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"10.1016\/j.media.2025.103611_b38","doi-asserted-by":"crossref","unstructured":"Pan, T., Xu, F., Yang, X., He, S., Jiang, C., Guo, Q., Qian, F., Zhang, X., Cheng, Y., Yang, L., et al., 2023. Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15201\u201315210.","DOI":"10.1109\/CVPR52729.2023.01459"},{"key":"10.1016\/j.media.2025.103611_b39","series-title":"Machine Learning in Medical Imaging: Second International Workshop, MLMI 2011, Held in Conjunction with MICCAI 2011, Toronto, Canada, September 18, 2011. Proceedings 2","first-page":"35","article-title":"Automated selection of standardized planes from ultrasound volume","author":"Rahmatullah","year":"2011"},{"key":"10.1016\/j.media.2025.103611_b40","doi-asserted-by":"crossref","unstructured":"Sain, A., Bhunia, A.K., Chowdhury, P.N., Koley, S., Xiang, T., Song, Y.Z., 2023. Clip for all things zero-shot sketch-based image retrieval, fine-grained or not. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2765\u20132775.","DOI":"10.1109\/CVPR52729.2023.00271"},{"issue":"6","key":"10.1016\/j.media.2025.103611_b41","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1002\/uog.24888","article-title":"ISUOG practice guidelines (updated): performance of the routine mid-trimester fetal ultrasound scan","volume":"59","author":"Salomon","year":"2022","journal-title":"Ultrasound Obs. Gynecol.: Off. J. Int. Soc. Ultrasound Obs. Gynecol."},{"key":"10.1016\/j.media.2025.103611_b42","series-title":"Attention-gated networks for improving ultrasound scan plane detection","author":"Schlemper","year":"2018"},{"key":"10.1016\/j.media.2025.103611_b43","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J., 2015. Facenet: A unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 815\u2013823.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"10.1016\/j.media.2025.103611_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.101973","article-title":"Knowledge representation and learning of operator clinical workflow from full-length routine fetal ultrasound scan videos","volume":"69","author":"Sharma","year":"2021","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2025.103611_b45","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2025.103611_b46","doi-asserted-by":"crossref","unstructured":"Wang, L., Mittal, G., Sajeev, S., Yu, Y., Hall, M., Boddeti, V.N., Chen, M., 2023. ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6575\u20136585.","DOI":"10.1109\/CVPR52729.2023.00636"},{"key":"10.1016\/j.media.2025.103611_b47","series-title":"CVPR 2021","article-title":"Pyramid vision transformer: A versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.media.2025.103611_b48","first-page":"2986","article-title":"Boundary proposal network for two-stage natural language video localization","volume":"vol. 35, no. 4","author":"Xiao","year":"2021"},{"key":"10.1016\/j.media.2025.103611_b49","series-title":"Negative frames matter in egocentric visual query 2d localization","author":"Xu","year":"2022"},{"key":"10.1016\/j.media.2025.103611_b50","first-page":"9062","article-title":"Multilevel language and vision integration for text-to-clip retrieval","volume":"vol. 33, no. 01","author":"Xu","year":"2019"},{"key":"10.1016\/j.media.2025.103611_b51","doi-asserted-by":"crossref","unstructured":"Xu, M., Li, Y., Fu, C.Y., Ghanem, B., Xiang, T., P\u00e9rez-R\u00faa, J.M., 2023. Where is my wallet? modeling object proposal sets for egocentric visual query localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2593\u20132603.","DOI":"10.1109\/CVPR52729.2023.00255"},{"key":"10.1016\/j.media.2025.103611_b52","doi-asserted-by":"crossref","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C., 2022. Tubedetr: Spatio-temporal video grounding with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16442\u201316453.","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"10.1016\/j.media.2025.103611_b53","series-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","first-page":"687","article-title":"Guided random forests for identification of key fetal anatomy and image categorization in ultrasound scans","author":"Yaqub","year":"2015"},{"issue":"5","key":"10.1016\/j.media.2025.103611_b54","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1109\/TMI.2022.3226274","article-title":"A machine learning method for automated description and workflow analysis of first trimester ultrasound scans","volume":"42","author":"Yasrab","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2025.103611_b55","first-page":"9159","article-title":"To find where you talk: Temporal sentence localization in video with attention based location regression","volume":"vol. 33, no. 01","author":"Yuan","year":"2019"},{"key":"10.1016\/j.media.2025.103611_b56","doi-asserted-by":"crossref","unstructured":"Zeng, R., Xu, H., Huang, W., Chen, P., Tan, M., Gan, C., 2020. Dense regression network for video grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10287\u201310296.","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"10.1016\/j.media.2025.103611_b57","doi-asserted-by":"crossref","unstructured":"Zhang, D., Dai, X., Wang, X., Wang, Y.-F., Davis, L.S., 2019. Man: Moment alignment network for natural language moment retrieval via iterative graph adjustment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1247\u20131257.","DOI":"10.1109\/CVPR.2019.00134"},{"key":"10.1016\/j.media.2025.103611_b58","series-title":"Span-based localizing network for natural language video localization","author":"Zhang","year":"2020"},{"key":"10.1016\/j.media.2025.103611_b59","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"228","article-title":"Towards unsupervised ultrasound video clinical quality assessment with multi-modality data","author":"Zhao","year":"2022"},{"key":"10.1016\/j.media.2025.103611_b60","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102977","article-title":"Memory-based unsupervised video clinical quality assessment with multi-modality data in fetal ultrasound","volume":"90","author":"Zhao","year":"2023","journal-title":"Med. Image Anal."}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841525001586?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841525001586?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T13:11:30Z","timestamp":1774530690000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841525001586"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":60,"alternative-id":["S1361841525001586"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2025.103611","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TIER-LOC: Visual Query-based Video Clip Localization in fetal ultrasound videos with a multi-tier transformer","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2025.103611","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103611"}}