{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:36:20Z","timestamp":1778258180393,"version":"3.51.4"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031703430","type":"print"},{"value":"9783031703447","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70344-7_23","type":"book-chapter","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T08:02:43Z","timestamp":1724918563000},"page":"392-408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SaccadeDet: A Novel Dual-Stage Architecture for\u00a0Rapid and\u00a0Accurate Detection in\u00a0Gigapixel Images"],"prefix":"10.1007","author":[{"given":"Wenxi","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruxin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haozhe","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"issue":"2","key":"23_CR1","first-page":"550","volume":"38","author":"P Bandi","year":"2018","unstructured":"Bandi, P., et al.: From detection of individual metastases to classification of lymph node status at the patient level: the CAMELYON17 challenge. TMI 38(2), 550\u2013560 (2018)","journal-title":"TMI"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"23_CR3","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.neucom.2021.12.049","volume":"477","author":"K Chen","year":"2022","unstructured":"Chen, K., et al.: Towards real-time object detection in gigapixel-level video. Neurocomputing 477, 14\u201324 (2022)","journal-title":"Neurocomputing"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Fan, J., Liu, H., Yang, W., See, J., Zhang, A., Lin, W.: Speed up object detection on gigapixel-level images with patch arrangement. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00461"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Gao, M., Yu, R., Li, A., Morariu, V.I., Davis, L.S.: Dynamic zoom-in network for fast object detection in large images. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00724"},{"key":"23_CR7","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"22","key":"23_CR10","doi-asserted-by":"publisher","first-page":"2184","DOI":"10.1001\/jama.2017.14580","volume":"318","author":"JA Golden","year":"2017","unstructured":"Golden, J.A.: Deep learning algorithms for detection of lymph node metastases from breast cancer: helping artificial intelligence be seen. JAMA 318(22), 2184\u20132186 (2017)","journal-title":"JAMA"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, S., Lin, Z., Li, Y., Shu, Y., Liu, Y.: Flexible high-resolution object detection on edge devices with tunable latency. In: MobiCom (2021)","DOI":"10.1145\/3447993.3483274"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, X., et al.: Attention scaling for crowd counting. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00476"},{"key":"23_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-030-00934-2_18","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"B Kong","year":"2018","unstructured":"Kong, B., Sun, S., Wang, X., Song, Q., Zhang, S.: Invasive cancer detection utilizing compressed convolutional neural network and transfer learning. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 156\u2013164. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00934-2_18"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Lan, S., Ren, Z., Wu, Y., Davis, L.S., Hua, G.: SaccadeNet: a fast and accurate object detector. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01041"},{"issue":"3","key":"23_CR17","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1007\/s11263-019-01204-1","volume":"128","author":"H Law","year":"2019","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. Int. J. Comput. Vis. 128(3), 642\u2013656 (2019). https:\/\/doi.org\/10.1007\/s11263-019-01204-1","journal-title":"Int. J. Comput. Vis."},{"key":"23_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1007\/978-3-030-00934-2_93","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"B Lee","year":"2018","unstructured":"Lee, B., Paeng, K.: A robust and effective approach towards accurate metastasis detection and pN-stage classification in breast cancer. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 841\u2013850. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00934-2_93"},{"key":"23_CR19","unstructured":"Lempitsky, V., Zisserman, A.: Learning to count objects in images. In: NeurIPS (2010)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Li, W., Cao, Z., Wang, Q., Chen, S., Feng, R.: Learning error-driven curriculum for crowd counting. In: ICPR (2021)","DOI":"10.1109\/ICPR48806.2021.9413068"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00615"},{"key":"23_CR22","unstructured":"Li, Y., Ping, W.: Cancer metastasis detection with neural conditional random field. arXiv preprint arXiv:1806.07064 (2018)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, X., Chen, D.: CSRNet: dilated convolutional neural networks for understanding the highly congested scenes. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00120"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Lian, D., Li, J., Zheng, J., Luo, W., Gao, S.: Density map regression guided detection network for RGB-D crowd counting and localization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00192"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Lin, H., et al.: GigaTraj: predicting long-term trajectories of hundreds of pedestrians in gigapixel complex scenes. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01829"},{"issue":"8","key":"23_CR26","first-page":"1948","volume":"38","author":"H Lin","year":"2019","unstructured":"Lin, H., Chen, H., Graham, S., Dou, Q., Rajpoot, N., Heng, P.A.: Fast ScanNet: fast and dense analysis of multi-gigapixel whole-slide images for cancer metastasis detection. TMI 38(8), 1948\u20131958 (2019)","journal-title":"TMI"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"23_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: GigaHumanDet: exploring full-body detection on gigapixel-level images. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i9.28873"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Liu, J., Gao, C., Meng, D., Hauptmann, A.G.: DecideNet: counting varying density crowds through attention guided detection and density estimation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00545"},{"key":"23_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"23_CR33","unstructured":"Liu, Y., et\u00a0al.: Detecting cancer metastases on gigapixel pathology images. arXiv preprint arXiv:1703.02442 (2017)"},{"issue":"7","key":"23_CR34","doi-asserted-by":"publisher","first-page":"859","DOI":"10.5858\/arpa.2018-0147-OA","volume":"143","author":"Y Liu","year":"2019","unstructured":"Liu, Y., et al.: Artificial intelligence-based breast cancer nodal metastasis detection: insights into the black box for pathologists. Arch. Pathol. Lab. Med. 143(7), 859\u2013868 (2019)","journal-title":"Arch. Pathol. Lab. Med."},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin Transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"23_CR36","unstructured":"Lyu, C., et al.: RTMDet: an empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784 (2022)"},{"key":"23_CR37","unstructured":"Ma, T., et al.: When visual grounding meets gigapixel-level large-scale scenes: benchmark and approach. In: CVPR (2024)"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Najibi, M., Singh, B., Davis, L.S.: AutoFocus: efficient multi-scale inference. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00984"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"23_CR40","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"23_CR41","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"23_CR42","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2014)"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Singh, B., Davis, L.S.: An analysis of scale invariance in object detection SNIP. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00377"},{"key":"23_CR44","unstructured":"Singh, B., Najibi, M., Davis, L.S.: SNIPER: efficient multi-scale training. In: NeurIPS (2018)"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"23_CR46","unstructured":"Wang, D., Khosla, A., Gargeya, R., Irshad, H., Beck, A.H.: Deep learning for identifying metastatic breast cancer. arXiv preprint arXiv:1606.05718 (2016)"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Wang, X., et\u00a0al.: PANDA: a gigapixel-level human-centric video dataset. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00333"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Yang, F., Fan, H., Chu, P., Blasch, E., Ling, H.: Clustered object detection in aerial images. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00840"},{"key":"23_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, D., Chen, S., Gao, S., Ma, Y.: Single-image crowd counting via multi-column convolutional neural network. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.70"},{"key":"23_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xue, W., Zhang, K., Chen, S.: \u2018Skimming-perusal\u2019 detection: a simple object detection baseline in gigapixel-level images. In: ICME (2023)","DOI":"10.1109\/ICME55011.2023.00421"},{"key":"23_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1007\/978-3-030-32239-7_65","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"Z Zhao","year":"2019","unstructured":"Zhao, Z., Lin, H., Chen, H., Heng, P.-A.: PFA-ScanNet: pyramidal feature aggregation with synergistic learning for breast cancer metastasis analysis. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11764, pp. 586\u2013594. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32239-7_65"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70344-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T12:14:57Z","timestamp":1732709697000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70344-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703430","9783031703447"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70344-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}