{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:35:02Z","timestamp":1750224902037,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":40,"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_13","type":"book-chapter","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:01:48Z","timestamp":1715414508000},"page":"186-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Efficient Multi-object Detection for\u00a0Complexity Spatio-Temporal Scenes"],"prefix":"10.1007","author":[{"given":"Kai","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xiangyu","family":"Song","sequence":"additional","affiliation":[]},{"given":"Shijie","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Juan","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Cai","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Huansheng","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,5,12]]},"reference":[{"key":"13_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv:2004.10934 [cs, eess] (2020)"},{"issue":"5","key":"13_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":"13_CR3","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"13_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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6569\u20136578 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"13_CR5","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 107, 3\u201311 (2018)","journal-title":"Neural Netw."},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"13_CR7","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":"13_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"9","key":"13_CR9","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"13_CR11","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"key":"13_CR12","doi-asserted-by":"publisher","unstructured":"Jocher, G.: YOLOv5 by Ultralytics (2020). https:\/\/doi.org\/10.5281\/zenodo.3908559, https:\/\/github.com\/ultralytics\/yolov5","DOI":"10.5281\/zenodo.3908559"},{"key":"13_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"13_CR14","doi-asserted-by":"publisher","unstructured":"Kowol, K., Rottmann, M., Bracke, S., Gottschalk, H.: YOdar: uncertainty-based sensor fusion for vehicle detection with camera and radar sensors (2020). https:\/\/doi.org\/10.48550\/arXiv.2010.03320","DOI":"10.48550\/arXiv.2010.03320"},{"key":"13_CR15","doi-asserted-by":"publisher","unstructured":"Li, C., et al.: YOLOv6 v3.0: a full-scale reloading (2023).https:\/\/doi.org\/10.48550\/arXiv.2301.05586","DOI":"10.48550\/arXiv.2301.05586"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., Chen, Y., Hu, R., Urtasun, R.: Multi-task multi-sensor fusion for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7345\u20137353 (2019)","DOI":"10.1109\/CVPR.2019.00752"},{"key":"13_CR17","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":"13_CR18","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"13_CR19","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":"13_CR20","doi-asserted-by":"crossref","unstructured":"Marriott, R.T., Romdhani, S., Chen, L.: A 3D GAN for improved large-pose facial recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13445\u201313455 (2021)","DOI":"10.1109\/CVPR46437.2021.01324"},{"issue":"9","key":"13_CR21","doi-asserted-by":"publisher","first-page":"15898","DOI":"10.1109\/TITS.2022.3146271","volume":"23","author":"L Qin","year":"2022","unstructured":"Qin, L., et al.: Id-yolo: real-time salient object detection based on the driver\u2019s fixation region. IEEE Trans. Intell. Transp. Syst. 23(9), 15898\u201315908 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"13_CR22","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":"13_CR23","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"13_CR24","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"13_CR25","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. syst. 28 (2015)"},{"key":"13_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110036","volume":"258","author":"X Song","year":"2022","unstructured":"Song, X., et al.: A survey on deep learning based knowledge tracing. Knowl.-Based Syst. 258, 110036 (2022)","journal-title":"Knowl.-Based Syst."},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"13_CR28","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. arXiv preprint arXiv:2207.02696 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., Yeh, I.H.: CSPNet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"13_CR30","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1007\/s11280-021-00877-4","volume":"24","author":"F Wang","year":"2021","unstructured":"Wang, F., Xu, J., Liu, C., Zhou, R., Zhao, P.: On prediction of traffic flows in smart cities: a multitask deep learning based approach. World Wide Web 24, 805\u2013823 (2021)","journal-title":"World Wide Web"},{"key":"13_CR31","unstructured":"Wang, J., Xu, C., Yang, W., Yu, L.: A normalized gaussian wasserstein distance for tiny object detection. arXiv preprint arXiv:2110.13389 (2021)"},{"issue":"2","key":"13_CR32","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1109\/TCSS.2019.2962819","volume":"7","author":"L Wang","year":"2020","unstructured":"Wang, L., et al.: Model: motif-based deep feature learning for link prediction. IEEE Trans. Comput. Soc. Syst. 7(2), 503\u2013516 (2020)","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Wen, L., et al.: UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking. Comput. Vis. Image Underst, 193, 102907 (2020)","DOI":"10.1016\/j.cviu.2020.102907"},{"issue":"2","key":"13_CR34","doi-asserted-by":"publisher","first-page":"1456","DOI":"10.1109\/TII.2022.3206343","volume":"19","author":"C Xu","year":"2022","unstructured":"Xu, C., et al.: Uncertainty-aware multi-view deep learning for internet of things applications. IEEE Trans. Industr. Inf. 19(2), 1456\u20131466 (2022)","journal-title":"IEEE Trans. Industr. Inf."},{"key":"13_CR35","unstructured":"Yang, X., Yan, J., Ming, Q., Wang, W., Zhang, X., Tian, Q.: Rethinking rotated object detection with gaussian wasserstein distance loss. In: International Conference on Machine Learning, pp. 11830\u201311841. PMLR (2021)"},{"key":"13_CR36","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1007\/s11280-020-00850-7","volume":"24","author":"H Yin","year":"2021","unstructured":"Yin, H., Yang, S., Song, X., Liu, W., Li, J.: Deep fusion of multimodal features for social media retweet time prediction. World Wide Web 24, 1027\u20131044 (2021)","journal-title":"World Wide Web"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: Bdd100k: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2636\u20132645 (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: Unitbox: an advanced object detection network. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 516\u2013520 (2016)","DOI":"10.1145\/2964284.2967274"},{"issue":"3","key":"13_CR39","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1007\/s12652-020-02573-z","volume":"13","author":"Wei Zhang","year":"2020","unstructured":"Zhang, Wei, Gao, Xian-zhong, Yang, Chi-fu, Jiang, Feng, Chen, Zhi-yuan: A object detection and tracking method for security in intelligence of unmanned surface vehicles. J. Ambient Intell. Humanized Comput. 13(3), 1279\u20131291 (2020). https:\/\/doi.org\/10.1007\/s12652-020-02573-z","journal-title":"J. Ambient Intell. Humanized Comput."},{"issue":"8","key":"13_CR40","doi-asserted-by":"publisher","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","volume":"52","author":"Z Zheng","year":"2021","unstructured":"Zheng, Z., et al.: Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 52(8), 8574\u20138586 (2021)","journal-title":"IEEE Trans. Cybern."}],"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_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:04:34Z","timestamp":1715414674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2421-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819724208","9789819724215"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2421-5_13","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"}}]}}