{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T23:52:41Z","timestamp":1783641161881,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819788576","type":"print"},{"value":"9789819788583","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8858-3_34","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T22:02:49Z","timestamp":1730584969000},"page":"492-505","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":123,"title":["Multi-branch Auxiliary Fusion YOLO with\u00a0Re-parameterization Heterogeneous Convolutional for\u00a0Accurate Object Detection"],"prefix":"10.1007","author":[{"given":"Zhiqiang","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiu","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keer","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianmin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinli","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haixia","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"34_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection (2020). arXiv:2004.10934"},{"issue":"5","key":"34_CR2","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2019","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: high quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1483\u20131498 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR3","unstructured":"Chen, Y., Yuan, X., Wu, R., et\u00a0al: Yolo-ms: rethinking multi-scale representation learning for real-time object detection (2023). arXiv:2308.05480"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Han, J., Ding, G.: Scaling up your kernels to 31x31: revisiting large kernel design in cnns. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11963\u201311975 (2022)","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., et\u00a0al: Repvgg: making vgg-style convnets great again. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13733\u201313742 (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: Tood: task-aligned one-stage object detection. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3490\u20133499. IEEE Computer Society (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"34_CR8","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021 (2021). arXiv:2107.08430"},{"key":"34_CR9","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Yolo by ultralytics (2023). https:\/\/githubcom\/ultralytics\/ultralytics"},{"key":"34_CR10","unstructured":"Jocher, G., Chaurasia, A., Stoken, A., et\u00a0al: ultralytics\/yolov5: v7. 0-yolov5 sota realtime instance segmentation. Zenodo (2022)"},{"key":"34_CR11","unstructured":"Li, C., Li, L., Geng, Y., et al: Yolov6 v3. 0: a full-scale reloading (2023). arXiv:2301.05586"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6054\u20136063 (2019)","DOI":"10.1109\/ICCV.2019.00615"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., et\u00a0al: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., et al: Microsoft coco: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., et\u00a0al: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"34_CR16","unstructured":"Lyu, C., Zhang, W., Huang, H., et\u00a0al: Rtmdet: an empirical study of designing real-time object detectors (2022). arXiv:2212.07784"},{"key":"34_CR17","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 Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"34_CR18","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement (2018). arXiv:1804.02767"},{"key":"34_CR19","unstructured":"Wang, C., He, W., Nie, Y., et\u00a0al: Gold-yolo: efficient object detector via gather-and-distribute mechanism (2023). arXiv:2309.11331"},{"key":"34_CR20","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Yeh, I.H., Liao, H.Y.M.: Yolov9: learning what you want to learn using programmable gradient information (2024). arXiv:2402.13616","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, J.H., Zou, Y., Zhou, D., Feng, J.: Panet: few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9197\u20139206 (2019)","DOI":"10.1109\/ICCV.2019.00929"},{"key":"34_CR23","unstructured":"Xu, S., Wang, X., Lv, W., Chang, Q., Cui, C., Deng, K., Wang, G., Dang, Q., Wei, S., Du, Y., et\u00a0al.: Pp-yoloe: an evolved version of yolo (2022). arXiv:2203.16250"},{"key":"34_CR24","unstructured":"Xu, X., Jiang, Y., Chen, W., et\u00a0al: Damo-yolo: a report on real-time object detection design (2022). arXiv:2211.15444"},{"key":"34_CR25","unstructured":"Zhang, H., Li, F., Liu, S., et\u00a0al: Dino: detr with improved denoising anchor boxes for end-to-end object detection (2022). arXiv:2203.03605"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization (2017). arXiv:1710.09412","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"34_CR27","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection (2020). arXiv:2010.04159"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8858-3_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T17:28:38Z","timestamp":1739467718000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8858-3_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819788576","9789819788583"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8858-3_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}