{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T16:04:43Z","timestamp":1768233883187,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557547","type":"print"},{"value":"9789819557554","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-95-5755-4_29","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:31:13Z","timestamp":1768221073000},"page":"421-435","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Dimension Feature Fusion for Real-Time Object Detection"],"prefix":"10.1007","author":[{"given":"Yuanwei","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"En","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tie","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"29_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"29_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":"29_CR3","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: ECCV, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"29_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":"29_CR5","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y.: Acquisition of localization confidence for accurate object detection. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"29_CR9","unstructured":"Jocher, G., Qiu, J.: Ultralytics yolos (2024). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Li, J., Tang, J., Yang, J.: Generalized focal loss v2: Learning reliable localization quality estimation for dense object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"29_CR11","unstructured":"Li, X., et al.: Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. In: NeurIPS (2020)"},{"issue":"6","key":"29_CR12","doi-asserted-by":"publisher","first-page":"2683","DOI":"10.1109\/TCSVT.2022.3218880","volume":"33","author":"Y Li","year":"2023","unstructured":"Li, Y., Zhu, E., Chen, H., Tan, J., Shen, L.: Dense crosstalk feature aggregation for classification and localization in object detection. IEEE Trans. Circuits Syst. Video Technol. 33(6), 2683\u20132695 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"29_CR13","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":"29_CR14","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":"29_CR15","unstructured":"Lin, T.Y., et al.: Microsoft coco: Common objects in context. In: ECCV (2014)"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: CVPR, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: Ssd: Single shot multibox detector. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., et\u00a0al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"29_CR19","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":"29_CR20","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. NeurIPS 28 (2015)"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Song, G., Liu, Y., Wang, X.: Revisiting the sibling head in object detector. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: Scalable and efficient object detection. In: CVPR, pp. 10778\u201310787 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"29_CR23","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":"29_CR24","doi-asserted-by":"crossref","unstructured":"Wang, A., et al.: Yolov10: Real-time end-to-end object detection. In: NeurIPS. vol.\u00a037, pp. 107984\u2013108011 (2024)","DOI":"10.52202\/079017-3429"},{"key":"29_CR25","unstructured":"Wang, C., et al.: Gold-yolo: efficient object detector via gather-and-distribute mechanism. In: NeurIPS (2023)"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Yeh, I.H., Mark\u00a0Liao, H.Y.: Yolov9: Learning what you want to learn using programmable gradient information. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Wang, D., Shang, K., Wu, H., Wang, C.: Decoupled R-CNN: Sensitivity-specific detector for higher accurate localization. IEEE Trans. Circ. Syst. Video Technol. (2022)","DOI":"10.1109\/TCSVT.2022.3167114"},{"key":"29_CR28","unstructured":"Wang, J., et\u00a0al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. pp. 3349\u20133364 (2021)"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Rethinking classification and localization for object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: Reppoints: Point set representation for object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00975"},{"key":"29_CR31","unstructured":"Zhang, H., et\u00a0al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. In: ICLR (2023)"},{"key":"29_CR32","unstructured":"Zhang, H., Wang, Y., Dayoub, F., S\u00fcnderhauf, N.: Varifocalnet: An IOU-aware dense object detector. In: CVPR (2021)"},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Dense distinct query for end-to-end object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00708"},{"key":"29_CR35","unstructured":"Zhang, X., Wan, F., Liu, C., Ji, R., Ye, Q.: Freeanchor: Learning to match anchors for visual object detection. In: NeurIPS (2019)"},{"key":"29_CR36","unstructured":"Zhao, Y., et al.: Detrs beat yolos on real-time object detection. In: CVPR, pp. 16965\u201316974. IEEE (2024)"},{"key":"29_CR37","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. In: ICLR (2021)"}],"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\/978-981-95-5755-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:31:53Z","timestamp":1768221113000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5755-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557547","9789819557554"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5755-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 January 2026","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":"Shanghai","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}