{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:49:30Z","timestamp":1757310570969,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819724208"},{"type":"electronic","value":"9789819724215"}],"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\/978-981-97-2421-5_1","type":"book-chapter","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:01:48Z","timestamp":1715414508000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["YOLO-SA: An Efficient Object Detection Model Based on\u00a0Self-attention Mechanism"],"prefix":"10.1007","author":[{"given":"Ang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"ShiJie","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taotao","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huansheng","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,12]]},"reference":[{"key":"1_CR1","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"1_CR2","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: Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1_CR3","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Neural Information Processing Systems (2012)"},{"key":"1_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Simonyan: Very deep convolutional networks for large-scale image recognition. (No Title) (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"1_CR6","unstructured":"Szegedy, C., et al.: Going deeper with convolutions (2023)"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. Cornell University - arXiv (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van\u00a0der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. Computer Vision and Pattern Recognition. arxiv (2016)","DOI":"10.1109\/CVPR.2017.243"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. Computer Vision and Pattern Recognition. arxiv (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1_CR11","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Cornell University - arXiv (2015)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"1_CR14","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. Computer Vision and Pattern Recognition. arxiv (2018)"},{"key":"1_CR15","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. Computer Vision and Pattern Recognition. arxiv (2020)"},{"key":"1_CR16","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":"1_CR17","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: RepVGG: making VGG-style convnets great again. In: Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"1_CR18","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. arxiv (2019)"},{"key":"1_CR19","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021 (2021)"},{"key":"1_CR20","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2018)"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. Cornell University - arXiv (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. Computer Vision and Pattern Recognition. arxiv (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. Computer Vision and Pattern Recognition. arxiv (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. Cornell University - arXiv (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1_CR25","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. Computer Vision and Pattern Recognition. arxiv (2019)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Song, G., Liu, Y., Wang, X.: Revisiting the sibling head in object detector. Cornell University - arXiv (2020)","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Rethinking classification and localization for object detection. Cornell University - arXiv (2020)","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. Cornell University - arXiv (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. Cornell University - arXiv (2016)","DOI":"10.1109\/CVPR.2017.634"},{"key":"1_CR30","unstructured":"Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks (2019)"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: efficient channel attention for deep convolutional neural networks. Computer Vision and Pattern Recognition. arxiv (2019)","DOI":"10.1109\/CVPR42600.2020.01155"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2421-5_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:02:10Z","timestamp":1715414530000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2421-5_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819724208","9789819724215"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2421-5_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"12 May 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","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":"apwebwaim2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apweb-waim2023.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}