{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T10:00:53Z","timestamp":1742983253344,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620531"},{"type":"electronic","value":"9789819620548"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-2054-8_10","type":"book-chapter","created":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T15:48:21Z","timestamp":1735832901000},"page":"125-138","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BiCA-YOLO: Bidirectional Feature Enhancement and\u00a0Cross Coordinate Attention for\u00a0Small Object Detection"],"prefix":"10.1007","author":[{"given":"Jin Yan","family":"Lv","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guo Qiang","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"10_CR5","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":"10_CR6","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":"10_CR7","doi-asserted-by":"crossref","unstructured":"Wang, C., Bochkovskiy, A., Liao, H.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arxiv 2022. arXiv preprint arXiv:2207.02696 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"10_CR8","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":"10_CR9","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"issue":"7","key":"10_CR12","doi-asserted-by":"publisher","first-page":"3423","DOI":"10.1109\/TIP.2019.2896952","volume":"28","author":"Y Yuan","year":"2019","unstructured":"Yuan, Y., Xiong, Z., Wang, Q.: VSSA-NET: vertical spatial sequence attention network for traffic sign detection. IEEE Trans. Image Process. 28(7), 3423\u20133434 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Zhu, X., Lyu, S., Wang, X., Zhao, Q.: TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2778\u20132788 (2021)","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"10_CR14","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"10_CR15","first-page":"1","volume":"60","author":"W Ma","year":"2022","unstructured":"Ma, W., et al.: Feature split-merge-enhancement network for remote sensing object detection. IEEE Trans. Geosci. Remote Sens. 60, 1\u201317 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Bai, Y., Zhang, Y., Ding, M., Ghanem, B.: SOD-MTGAN: small object detection via multi-task generative adversarial network. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 206\u2013221 (2018)","DOI":"10.1007\/978-3-030-01261-8_13"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Yang, C., Huang, Z., Wang, N.: QueryDet: cascaded sparse query for accelerating high-resolution small object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13668\u201313677 (2022)","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Akyon, F.C., Altinuc, S.O., Temizel, A.: Slicing aided hyper inference and fine-tuning for small object detection. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 966\u2013970. IEEE (2022)","DOI":"10.1109\/ICIP46576.2022.9897990"},{"key":"10_CR19","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1007\/978-3-031-20077-9_31","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part IX","author":"C Xu","year":"2022","unstructured":"Xu, C., Wang, J., Yang, W., Yu, H., Yu, L., Xia, G.-S.: RFLA: Gaussian receptive field based label assignment for\u00a0tiny object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part IX, pp. 526\u2013543. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_31"},{"key":"10_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110714","volume":"155","author":"Z Yu","year":"2024","unstructured":"Yu, Z., Huang, H., Chen, W., Su, Y., Liu, Y., Wang, X.: YOLO-FaceV2: a scale and occlusion aware face detector. Pattern Recogn. 155, 110714 (2024)","journal-title":"Pattern Recogn."},{"key":"10_CR21","unstructured":"Du, D., et\u00a0al.: VisDrone-DET2019: the vision meets drone object detection in image challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)"},{"key":"10_CR22","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111, 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"10_CR23","unstructured":"Glenn, J.: Title, YOLOv5 release v6.1 (2022). https:\/\/github.com\/ultralytics\/yolov5\/releases\/tag\/v6.1,2022\/. Accessed 22 Nov 2022"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: ScaleKD: distilling scale-aware knowledge in, small object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19723\u201319733 (2023)","DOI":"10.1109\/CVPR52729.2023.01889"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Du, B., Huang, Y., Chen, J., Huang, D.: Adaptive sparse convolutional networks with global context enhancement for faster object detection on drone images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13435\u201313444 (2023)","DOI":"10.1109\/CVPR52729.2023.01291"},{"key":"10_CR26","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"10_CR27","first-page":"10353","volume":"35","author":"Y Rao","year":"2022","unstructured":"Rao, Y., Zhao, W., Tang, Y., Zhou, J., Lim, S.N., Lu, J.: HorNet: efficient high-order spatial interactions with recursive gated convolutions. Adv. Neural. Inf. Process. Syst. 35, 10353\u201310366 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: 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"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2054-8_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T01:42:35Z","timestamp":1742694155000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2054-8_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620531","9789819620548"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2054-8_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"3 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}