{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T11:35:15Z","timestamp":1780400115891,"version":"3.54.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051134","type":"print"},{"value":"9783032051141","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"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\/978-3-032-05114-1_10","type":"book-chapter","created":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:10:45Z","timestamp":1758377445000},"page":"96-106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CAT-SG: A Large Dynamic Scene Graph Dataset for\u00a0Fine-Grained Understanding of\u00a0Cataract Surgery"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8493-9941","authenticated-orcid":false,"given":"Felix","family":"Holm","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5219-8926","authenticated-orcid":false,"given":"G\u00f6zde","family":"\u00dcnver","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0792-3583","authenticated-orcid":false,"given":"Ghazal","family":"Ghazaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,21]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Al Hajj, H., et al.: Cataracts: challenge on automatic tool annotation for cataract surgery. Med. Image Anal. 52, 24\u201341 (2019)","DOI":"10.1016\/j.media.2018.11.008"},{"key":"10_CR2","unstructured":"Brody, S., Alon, U., Yahav, E.: How attentive are graph attention networks? In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=F72ximsx7C1"},{"key":"10_CR3","unstructured":"Chen, S., et al.: Valor: vision-audio-language omni-perception pretraining model and dataset. arXiv preprint arXiv:2304.08345 (2023)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"10_CR5","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: Qlora: efficient finetuning of quantized llms. arXiv preprint arXiv:2305.14314 (2023)"},{"key":"10_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (long and short papers), pp. 4171\u20134186 (2019)"},{"key":"10_CR7","unstructured":"Funke, I., Rivoir, D., Speidel, S.: Metrics matter in surgical phase recognition (2023). https:\/\/arxiv.org\/abs\/2305.13961"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Gastager, D., Ghazaei, G., Patsch, C.: Watch and learn: leveraging expert knowledge and language for surgical video understanding. ArXiv abs\/2503.11392 (2025). https:\/\/api.semanticscholar.org\/CorpusID:277044026","DOI":"10.1007\/s11548-025-03472-4"},{"key":"10_CR9","unstructured":"Grammatikopoulou, M., et al.: Cadis: cataract dataset for image segmentation. arXiv preprint arXiv:1906.11586 (2019)"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Holm, F., Ghazaei, G., Czempiel, T., \u00d6zsoy, E., Saur, S., Navab, N.: Dynamic scene graph representation for surgical video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 81\u201387 (2023)","DOI":"10.1109\/ICCVW60793.2023.00015"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Ji, J., Krishna, R., Fei-Fei, L., Niebles, J.C.: Action genome: actions as compositions of spatio-temporal scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10236\u201310247 (2020)","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"K\u00f6ksal, \u00c7., Ghazaei, G., Holm, F., Farshad, A., Navab, N.: Sangria: surgical video scene graph optimization for surgical workflow prediction. arXiv preprint arXiv:2407.20214 (2024)","DOI":"10.1007\/978-3-031-83243-7_10"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"10_CR14","unstructured":"Luo, Z., et al.: MOMA-LRG: language-refined graphs for multi-object multi-actor activity parsing. In: Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2022). https:\/\/openreview.net\/forum?id=eJhc_CPXQIT"},{"key":"10_CR15","doi-asserted-by":"publisher","unstructured":"Murali, A., et al.: Encoding surgical videos as latent spatiotemporal graphs for object and anatomy-driven reasoning. In: Greenspan, H., et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023. MICCAI 2023. LNCS, vol. 14228, pp. 647\u2013657. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43996-4_62","DOI":"10.1007\/978-3-031-43996-4_62"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Rodin, I., Furnari, A., Min, K., Tripathi, S., Farinella, G.M.: Action scene graphs for long-form understanding of egocentric videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18622\u201318632 (2024)","DOI":"10.1109\/CVPR52733.2024.01762"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Wang, G., Li, Z., Chen, Q., Liu, Y.: Oed: towards one-stage end-to-end dynamic scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27938\u201327947 (2024)","DOI":"10.1109\/CVPR52733.2024.02639"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Wang, J., Wen, Z., Li, X., Guo, Z., Yang, J., Liu, Z.: Pair then relation: pair-net for panoptic scene graph generation. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3442301"},{"key":"10_CR19","doi-asserted-by":"publisher","unstructured":"Yang, J., Ang, Y.Z., Guo, Z., Zhou, K., Zhang, W., Liu, Z.: Panoptic scene graph generation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13687, pp. 178\u2013196. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_11","DOI":"10.1007\/978-3-031-19812-0_11"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Yang, J., et\u00a0al.: Panoptic video scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18675\u201318685 (2023)","DOI":"10.1109\/CVPR52729.2023.01791"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Shi, M., Caesar, H.: Hilo: exploiting high low frequency relations for unbiased panoptic scene graph generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21637\u201321648 (2023)","DOI":"10.1109\/ICCV51070.2023.01978"},{"key":"10_CR22","unstructured":"Zhu, F., Yang, J., Jiang, H.: Towards flexible visual relationship segmentation. Adv. Neural Inf. Process. Syst. 37, 107633\u2013107661 (2025)"},{"key":"10_CR23","doi-asserted-by":"publisher","unstructured":"\u00d6zsoy, E., Pellegrini, C., Keicher, M., Navab, N.: ORacle: large vision-language models for knowledge-guided holistic OR domain modeling. In: Linguraru, M.G., et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. MICCAI 2024. LNCS, vol. 15006, pp. 455\u2013465. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72089-5_43","DOI":"10.1007\/978-3-031-72089-5_43"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05114-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:10:53Z","timestamp":1758377453000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05114-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"ISBN":["9783032051134","9783032051141"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05114-1_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,21]]},"assertion":[{"value":"21 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}