{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T04:48:58Z","timestamp":1776487738800,"version":"3.51.2"},"reference-count":216,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T00:00:00Z","timestamp":1701216000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T00:00:00Z","timestamp":1701216000000},"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":["J Intell Robot Syst"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s10846-023-02009-8","type":"journal-article","created":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T02:02:12Z","timestamp":1701223332000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Research on Real-time Detection of Stacked Objects Based on Deep Learning"],"prefix":"10.1007","volume":"109","author":[{"given":"Kaiguo","family":"Geng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4337-9877","authenticated-orcid":false,"given":"Jinwei","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongmin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiling","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,29]]},"reference":[{"key":"2009_CR1","doi-asserted-by":"crossref","unstructured":"Viola, P.A., Jones, M.J.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, vol. 1 (2001)","DOI":"10.1109\/CVPR.2001.990517"},{"key":"2009_CR2","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol. 1, pp. 886\u20138931 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"2009_CR3","doi-asserted-by":"crossref","unstructured":"Canny, J.F.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. PAMI 8, 679\u2013698 (1986)","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"2009_CR4","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"2009_CR5","doi-asserted-by":"crossref","unstructured":"Bay, H., Tuytelaars, T., Gool, L.V.: Surf: Speeded up robust features. In: European Conference on Computer Vision (2006). https:\/\/api.semanticscholar.org\/CorpusID:461853","DOI":"10.1007\/11744023_32"},{"key":"2009_CR6","doi-asserted-by":"crossref","unstructured":"Zhao, K., Wang, Y., Zuo, Y., Zhang, C.: Palletizing robot positioning bolt detection based on improved yolo-v3. J. Intell. Robot. Syst. 104 (2022)","DOI":"10.1007\/s10846-022-01580-w"},{"key":"2009_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10846-021-01564-2","volume":"104","author":"H-Q Liu","year":"2022","unstructured":"Liu, H.-Q., Li, D., Jiang, B., Zhou, J., Wei, T., Yao, X.: Mgbm-yolo: a faster light-weight object detection model for robotic grasping of bolster spring based on image-based visual servoing. J. Intell. Robot. Syst. 104, 1\u201317 (2022)","journal-title":"J. Intell. Robot. Syst."},{"key":"2009_CR8","doi-asserted-by":"publisher","first-page":"1454","DOI":"10.1016\/j.jfranklin.2022.11.004","volume":"360","author":"H Tao","year":"2022","unstructured":"Tao, H., Qiu, J., Chen, Y., Stojanovic, V., Cheng, L.: Unsupervised cross-domain rolling bearing fault diagnosis based on time-frequency information fusion. J. Frankl. Inst. 360, 1454\u20131477 (2022)","journal-title":"J. Frankl. Inst."},{"key":"2009_CR9","doi-asserted-by":"publisher","first-page":"3461","DOI":"10.1109\/TSMC.2022.3225381","volume":"53","author":"Z Zhuang","year":"2023","unstructured":"Zhuang, Z., Tao, H., Chen, Y., Stojanovic, V., Paszke, W.: An optimal iterative learning control approach for linear systems with nonuniform trial lengths under input constraints. IEEE Trans. Syst. Man Cybern. Syst. 53, 3461\u20133473 (2023)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"2009_CR10","doi-asserted-by":"crossref","unstructured":"Sun, X., Liu, T., Yu, X., Pang, B.: Unmanned surface vessel visual object detection under all-weather conditions with optimized feature fusion network in yolov4. J. Intell. Robot. Syst. 103 (2021)","DOI":"10.1007\/s10846-021-01499-8"},{"key":"2009_CR11","doi-asserted-by":"publisher","first-page":"100301","DOI":"10.1016\/j.cosrev.2020.100301","volume":"38","author":"V Sharma","year":"2020","unstructured":"Sharma, V., Mir, R.N.: A comprehensive and systematic look up into deep learning based object detection techniques: a review. Comput. Sci. Rev. 38, 100301 (2020)","journal-title":"Comput. Sci. Rev."},{"key":"2009_CR12","doi-asserted-by":"publisher","first-page":"100057","DOI":"10.1016\/j.array.2021.100057","volume":"10","author":"A Gupta","year":"2021","unstructured":"Gupta, A., Anpalagan, A., Guan, L., Khwaja, A.S.: Deep learning for object detection and scene perception in self-driving cars: survey, challenges, and open issues. Array 10, 100057 (2021)","journal-title":"Array"},{"key":"2009_CR13","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.neucom.2023.02.006","volume":"531","author":"V Kamath","year":"2023","unstructured":"Kamath, V., Renuka, A.: Deep learning based object detection for resource constrained devices: systematic review, future trends and challenges ahead. Neurocomput. 531, 34\u201360 (2023)","journal-title":"Neurocomput."},{"key":"2009_CR14","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1109\/TSMC.2020.3005231","volume":"52","author":"G Chen","year":"2022","unstructured":"Chen, G., Wang, H., Chen, K., Li, Z., Song, Z., Liu, Y., Chen, W., Knoll, A.: A survey of the four pillars for small object detection: multiscale representation, contextual information, super-resolution, and region proposal. IEEE Trans. Syst. Man Cybern. Syst. 52, 936\u2013953 (2022)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"2009_CR15","doi-asserted-by":"publisher","unstructured":"Tong, K., Wu, Y.: Deep learning-based detection from the perspective of small or tiny objects: a survey. Image Vis. Comput. 123 (2022). https:\/\/doi.org\/10.1016\/j.imavis.2022.104471","DOI":"10.1016\/j.imavis.2022.104471"},{"key":"2009_CR16","unstructured":"Chahal, K.S., Dey, K.: A survey of modern object detection literature using deep learning (2018). arXiv:1808.07256"},{"key":"2009_CR17","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv:1409.1556"},{"key":"2009_CR18","first-page":"442","volume":"12","author":"S-H Noh","year":"2021","unstructured":"Noh, S.-H.: Analysis of gradient vanishing of rnns and performance comparison. Inf. 12, 442 (2021)","journal-title":"Inf."},{"key":"2009_CR19","unstructured":"Canziani, A., Paszke, A., Culurciello, E.: An analysis of deep neural network models for practical applications (2016). arXiv:1605.07678"},{"key":"2009_CR20","doi-asserted-by":"crossref","unstructured":"Broy, M.: Software engineering\u2013from auxiliary to key technologies. In: Broy, M., Denert, E. (eds.) Software Pioneers. Springer, New York, pp. 10\u201313 (1992)","DOI":"10.1007\/978-3-642-59412-0_1"},{"key":"2009_CR21","doi-asserted-by":"publisher","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, pp. 1\u20139. https:\/\/doi.org\/10.1109\/cvpr.2015.7298594 (2015)","DOI":"10.1109\/cvpr.2015.7298594"},{"key":"2009_CR22","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Comp Soc; Comp Vis Fdn, Seattle, pp. 779\u2013788. https:\/\/doi.org\/10.1109\/CVPR.2016.91 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"2009_CR23","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: efficient convolutional neural networks for mobile vision applications (2017). arXiv:1704.04861"},{"key":"2009_CR24","doi-asserted-by":"publisher","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V., Le, Q.V., Adam, H.: Searching for mobilenetv3. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV 2019). IEEE; IEEE Comp Soc; CVF, Seoul, pp. 1314\u20131324. https:\/\/doi.org\/10.1109\/ICCV.2019.00140 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"2009_CR25","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale (2020). arXiv:2010.11929"},{"key":"2009_CR26","doi-asserted-by":"publisher","unstructured":"Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., Wei, F., Guo, B.: Swin transformer v2: scaling up capacity and resolution. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE; CVF; IEEE Comp Soc., New Orleans, pp. 11999\u201312009. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01170 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"2009_CR27","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers (2020). arXiv:2005.12872","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"6","key":"2009_CR28","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"2009_CR29","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2009_CR30","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.S.: Unitbox: an advanced object detection network. In: Proceedings of the 24th ACM International Conference on Multimedia (2016)","DOI":"10.1145\/2964284.2967274"},{"key":"2009_CR31","doi-asserted-by":"publisher","unstructured":"Zheng, Z., Wang, P., Ren, D., Liu, W., Ye, R., Hu, Q., Zuo, W.: Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 52(8), 8574\u20138586 (2022). https:\/\/doi.org\/10.1109\/TCYB.2021.3095305","DOI":"10.1109\/TCYB.2021.3095305"},{"key":"2009_CR32","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","volume":"506","author":"Y-F Zhang","year":"2022","unstructured":"Zhang, Y.-F., Ren, W., Zhang, Z., Jia, Z., Wang, L., Tan, T.: Focal and efficient iou loss for accurate bounding box regression. Neurocomput. 506, 146\u2013157 (2022). https:\/\/doi.org\/10.1016\/j.neucom.2022.07.042","journal-title":"Neurocomput."},{"key":"2009_CR33","doi-asserted-by":"publisher","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-nms: improving object detection with one line of code. IEEE, pp. 5562\u20135570 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.593","DOI":"10.1109\/ICCV.2017.593"},{"key":"2009_CR34","doi-asserted-by":"crossref","unstructured":"Du, L., Zhang, R., Wang, X.: Overview of two-stage object detection algorithms. J. Phys. Conf. Ser. 1544 (2020)","DOI":"10.1088\/1742-6596\/1544\/1\/012033"},{"key":"2009_CR35","unstructured":"Chen, Y., Han, C., Wang, N., Zhang, Z.: Revisiting feature alignment for one-stage object detection (2019). arXiv:1908.01570"},{"key":"2009_CR36","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: 30TH IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017). IEEE; IEEE Comp Soc; CVF, Honolulu, pp. 6517\u20136525. https:\/\/doi.org\/10.1109\/CVPR.2017.690 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"2009_CR37","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S.E., Fu, C.-Y., Berg, A.C.: Ssd: single shot multibox detector. In: European Conference on Computer Vision (2015)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2009_CR38","unstructured":"Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: Dssd: deconvolutional single shot detector (2017). arXiv:1701.06659"},{"key":"2009_CR39","doi-asserted-by":"crossref","unstructured":"Jeong, J., Park, H., Kwak, N.: Enhancement of ssd by concatenating feature maps for object detection (2017). arXiv:1705.09587","DOI":"10.5244\/C.31.76"},{"key":"2009_CR40","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: 2017 16th IEEE International Conference on Computer Vision (ICCV). IEEE; IEEE Comp Soc, Venice, pp. 2999\u20133007. https:\/\/doi.org\/10.1109\/ICCV.2017.324 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"2009_CR41","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement (2018). arXiv:1804.02767"},{"key":"2009_CR42","doi-asserted-by":"publisher","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y.-G., Chen, Y., Xue, X.: Dsod: learning deeply supervised object detectors from scratch. In: 2017 16th IEEE International Conference on Computer Vision (ICCV). IEEE; IEEE Comp Soc, Venice, pp. 1937\u20131945. https:\/\/doi.org\/10.1109\/ICCV.2017.212 (2017)","DOI":"10.1109\/ICCV.2017.212"},{"key":"2009_CR43","unstructured":"Li, Z., Zhou, F.: Fssd: feature fusion single shot multibox detector (2017). arXiv:1712.00960"},{"key":"2009_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.: Single-shot refinement neural network for object detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4203\u20134212 (2017)","DOI":"10.1109\/CVPR.2018.00442"},{"key":"2009_CR45","doi-asserted-by":"publisher","unstructured":"Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer vision - ECCV 2018, PT XIV. Lecture notes in computer science, vol. 11218, pp. 765\u2013781. 15th European Conference on Computer Vision (ECCV), Munich. https:\/\/doi.org\/10.1007\/978-3-030-01264-9_45 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"2009_CR46","doi-asserted-by":"publisher","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: keypoint triplets for object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV 2019). IEEE; IEEE Comp Soc; CVF, Seoul, pp. 6568\u20136577. https:\/\/doi.org\/10.1109\/ICCV.2019.00667 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"2009_CR47","doi-asserted-by":"publisher","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: Fully convolutional one-stage object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV 2019). IEEE; IEEE Comp Soc; CVF, Seoul, pp. 9626\u20139635. https:\/\/doi.org\/10.1109\/ICCV.2019.00972 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2009_CR48","doi-asserted-by":"publisher","unstructured":"Zhou, X., Zhuo, J., Krahenbuhl, P.: Bottom-up object detection by grouping extreme and center points. In: 2019 32nd IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019). IEEE; CVF; IEEE Comp Soc, Long Beach, pp. 850\u2013859. https:\/\/doi.org\/10.1109\/CVPR.2019.00094 (2019)","DOI":"10.1109\/CVPR.2019.00094"},{"key":"2009_CR49","doi-asserted-by":"publisher","unstructured":"Zhou, X., Zhuo, J., Krahenbuhl, P.: Bottom-up object detection by grouping extreme and center points. In: 2019 32nd IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019). IEEE; CVF; IEEE Comp Soc, Long Beach, pp. 850\u2013859. https:\/\/doi.org\/10.1109\/CVPR.2019.00094 (2019)","DOI":"10.1109\/CVPR.2019.00094"},{"key":"2009_CR50","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: optimal speed and accuracy of object detection (2020). arXiv:2004.10934"},{"key":"2009_CR51","unstructured":"Jocher, G.R., Stoken, A., Borovec, J., NanoCode, ChristopherSTAN, Changyu, L., Laughing, tkianai, Hogan, A., lorenzomammana, yxNONG, AlexWang, Diaconu, L., Marc, wanghaoyang, ah, Doug, Ingham, F., Frederik, Guilhen, Hatovix, Poznanski, J., Fang, J., Yu, L., Changyu, Wang, M., Gupta, N.K., Akhtar, O., PetrDvoracek, Rai, P.: ultralytics\/yolov5: v3.1 - bug fixes and performance improvements (2020)"},{"key":"2009_CR52","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: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9756\u20139765 (2019)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"2009_CR53","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: scalable and efficient object detection. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8\u201310787 (2019)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2009_CR54","first-page":"691","volume":"39","author":"C-Y Wang","year":"2021","unstructured":"Wang, C.-Y., Yeh, I.-H., Liao, H.: You only learn one representation: unified network for multiple tasks. J. Inf. Sci. Eng. 39, 691\u2013709 (2021)","journal-title":"J. Inf. Sci. Eng."},{"key":"2009_CR55","unstructured":"e, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021 (2021). hyperimagehttp:\/\/arxiv.org\/abs\/2107.08430arXiv:2107.08430"},{"key":"2009_CR56","unstructured":"hu, 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"},{"key":"2009_CR57","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., Li, Y., Zhang, B., Liang, Y., Zhou, L., Xu, X., Chu, X., Wei, X., Wei, X.: Yolov6: a single-stage object detection framework for industrial applications (2022). arXiv:2209.02976"},{"key":"2009_CR58","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 (2022). arXiv:2207.02696","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"2009_CR59","doi-asserted-by":"publisher","unstructured":"Zhang, X., Zeng, H., Guo, S., Zhang, L.: Efficient long-range attention network for image super-resolution. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G., Hassner, T. (eds.) Computer vision - ECCV 2022, PT XVII. Lecture notes in computer science. 17th European Conference on Computer Vision (ECCV), Tel Aviv, vol. 13677, pp. 649\u2013667. https:\/\/doi.org\/10.1007\/978-3-031-19790-1_39 (2022)","DOI":"10.1007\/978-3-031-19790-1_39"},{"key":"2009_CR60","unstructured":"Ultralytics: ultralytics\u2019s official github repository (2023). Available at: https:\/\/github.com\/ultralytics\/ultralytics#documentation"},{"key":"2009_CR61","unstructured":"Fang, Y., Liao, B., Wang, X., Fang, J., Qi, J., Wu, R., Niu, J., Liu, W.: You only look at one sequence: rethinking transformer in vision through object detection. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J. (eds.) Advances in Neural Information Processing Systems 34 (NEURIPS 2021). 35th Conference on Neural Information Processing Systems (NeurIPS), ELECTR NETWORK (2021)"},{"key":"2009_CR62","doi-asserted-by":"publisher","unstructured":"Ying, Z., Lin, Z., Wu, Z., Liang, K., Hu, X.: A modified-yolov5s model for detection of wire braided hose defects. Measurement 190 (2022). https:\/\/doi.org\/10.1016\/j.measurement.2021.110683","DOI":"10.1016\/j.measurement.2021.110683"},{"key":"2009_CR63","doi-asserted-by":"publisher","unstructured":"Zhao, K., Wang, Y., Zuo, Y., Zhang, C.: Palletizing robot positioning bolt detection based on improved yolo-v3. J. Intell. Robot. Syst. 104(3) (2022). https:\/\/doi.org\/10.1007\/s10846-022-01580-w","DOI":"10.1007\/s10846-022-01580-w"},{"key":"2009_CR64","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Liang, J., Lu, Q., Luo, L., Zhu, W., Wang, Q., Lin, J.: A novel efficient convolutional neural algorithm for multi-category aliasing hardware recognition. Sensors 22(14) (2022). https:\/\/doi.org\/10.3390\/s22145358","DOI":"10.3390\/s22145358"},{"key":"2009_CR65","doi-asserted-by":"publisher","unstructured":"Li, Y., Wang, J., Huang, J., Li, Y.: Research on deep learning automatic vehicle recognition algorithm based on res-yolo model. Sensors 22(10) (2022). https:\/\/doi.org\/10.3390\/s22103783","DOI":"10.3390\/s22103783"},{"key":"2009_CR66","doi-asserted-by":"publisher","unstructured":"Bie, M., Liu, Y., Li, G., Hong, J., Li, J.: Real-time vehicle detection algorithm based on a lightweight you-only-look-once (yolov5n-l) approach. Exp. Syst. Appl. 213(B) (2023). https:\/\/doi.org\/10.1016\/j.eswa.2022.119108","DOI":"10.1016\/j.eswa.2022.119108"},{"key":"2009_CR67","doi-asserted-by":"publisher","unstructured":"Gong, X., Zhang, X., Zhang, R., Wu, Q., Wang, H., Guo, R., Chen, Z.: U3-yoloxs: an improved yoloxs for uncommon unregular unbalance detection of the rape subhealth regions. Comput. Electron. Agri. 203 (2022). https:\/\/doi.org\/10.1016\/j.compag.2022.107461","DOI":"10.1016\/j.compag.2022.107461"},{"key":"2009_CR68","doi-asserted-by":"publisher","unstructured":"Yang, R., Hu, Y., Yao, Y., Gao, M., Liu, R.: Fruit target detection based on bco-yolov5 model. Mobile Inf. Syst. 2022 (2022). https:\/\/doi.org\/10.1155\/2022\/8457173","DOI":"10.1155\/2022\/8457173"},{"key":"2009_CR69","doi-asserted-by":"publisher","unstructured":"Jin, Z., Liu, L., Gong, D., Li, L.: Target recognition of industrial robots using machine vision in 5g environment. Front. Neurorobot. 15 (2021). https:\/\/doi.org\/10.3389\/fnbot.2021.624466","DOI":"10.3389\/fnbot.2021.624466"},{"key":"2009_CR70","doi-asserted-by":"crossref","unstructured":"Kapoor, A., Singhal, A.: A comparative study of k-means, k-means++ and fuzzy c-means clustering algorithms. In: 2017 3rd International Conference on Computational Intelligence & Communication Technology (CICT), pp. 1\u20136 (2017)","DOI":"10.1109\/CIACT.2017.7977272"},{"key":"2009_CR71","doi-asserted-by":"publisher","unstructured":"Li, F., Gao, D., Yang, Y., Zhu, J.: Small target deep convolution recognition algorithm based on improved yolov4. Int. J Mach. Learn. Cybern. 14(2, SI), 387\u2013394 (2023) .https:\/\/doi.org\/10.1007\/s13042-021-01496-1","DOI":"10.1007\/s13042-021-01496-1"},{"key":"2009_CR72","doi-asserted-by":"publisher","unstructured":"Yang, J., Wu, S., Gou, L., Yu, H., Lin, C., Wang, J., Wang, P., Li, M., Li, X.: Scd: a stacked carton dataset for detection and segmentation. SENSORS 22(10) (2022). https:\/\/doi.org\/10.3390\/s22103617","DOI":"10.3390\/s22103617"},{"key":"2009_CR73","doi-asserted-by":"publisher","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z.: Occlusion-aware r-cnn: detecting pedestrians in a crowd. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision - ECCV 2018, PT III. Lecture Notes in Computer Science. 15th European Conference on Computer Vision (ECCV), Munich, vol. 11207, pp. 657\u2013674. https:\/\/doi.org\/10.1007\/978-3-030-01219-9_39 (2018)","DOI":"10.1007\/978-3-030-01219-9_39"},{"key":"2009_CR74","doi-asserted-by":"crossref","unstructured":"Gupta, A., Anpalagan, A., Guan, L., Khwaja, A.S.: Deep learning for object detection and scene perception in self-driving cars: survey, challenges, and open issues. Array 10, 100057 (2021)","DOI":"10.1016\/j.array.2021.100057"},{"issue":"10","key":"2009_CR75","doi-asserted-by":"publisher","first-page":"17952","DOI":"10.1109\/TITS.2022.3156267","volume":"23","author":"T Ye","year":"2022","unstructured":"Ye, T., Zhao, Z., Wang, S., Zhou, F., Gao, X.: A stable lightweight and adaptive feature enhanced convolution neural network for efficient railway transit object detection. IEEE Trans. Intell. Transp. Syst. 23(10), 17952\u201317965 (2022). https:\/\/doi.org\/10.1109\/TITS.2022.3156267","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"2009_CR76","doi-asserted-by":"publisher","unstructured":"Zheng, H., Liu, H., Qi, W., Xie, H.: Little-yolov4: a lightweight pedestrian detection network based on yolov4 and ghostnet. Wireless Commun. Mobile Comput. 2022 (2022). https:\/\/doi.org\/10.1155\/2022\/5155970","DOI":"10.1155\/2022\/5155970"},{"key":"2009_CR77","doi-asserted-by":"publisher","unstructured":"Yun, J., Jiang, D., Liu, Y., Sun, Y., Tao, B., Kong, J., Tian, J., Tong, X., Xu, M., Fang, Z.: Real-time target detection method based on lightweight convolutional neural network. Frontiers Bioeng. Biotechnol. 10 (2022). https:\/\/doi.org\/10.3389\/fbioe.2022.861286","DOI":"10.3389\/fbioe.2022.861286"},{"key":"2009_CR78","doi-asserted-by":"publisher","unstructured":"Zhang, F., Lv, Z., Zhang, H., Guo, J., Wang, J., Lu, T., Zhangzhong, L.: Verification of improved YOLOX model in detection of greenhouse crop organs: Considering tomato as example. Comput. Electron. Agric. 205, (2023). https:\/\/doi.org\/10.1016\/j.compag.2022.107582","DOI":"10.1016\/j.compag.2022.107582"},{"key":"2009_CR79","doi-asserted-by":"publisher","unstructured":"Liu, M., Jia, W., Wang, Z., Niu, Y., Yang, X., Ruan, C.: An accurate detection and segmentation model of obscured green fruits. Comput. Electron. Agri. 197 (2022). https:\/\/doi.org\/10.1016\/j.compag.2022.106984","DOI":"10.1016\/j.compag.2022.106984"},{"key":"2009_CR80","doi-asserted-by":"publisher","unstructured":"Yan, B., Fan, P., Lei, X., Liu, Z., Yang, F.: A real-time apple targets detection method for picking robot based on improved yolov5. Remote Sens. 13(9) (2021). https:\/\/doi.org\/10.3390\/rs13091619","DOI":"10.3390\/rs13091619"},{"key":"2009_CR81","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Zhang, W., Yu, J., He, L., Chen, J., He, Y.: Complete and accurate holly fruits counting using yolox object detection. Comput. Electron. Agri. 198 (2022). https:\/\/doi.org\/10.1016\/j.compag.2022.107062","DOI":"10.1016\/j.compag.2022.107062"},{"key":"2009_CR82","doi-asserted-by":"publisher","unstructured":"Zhao, F., Wei, R., Chao, Y., Shao, S., Jing, C.: Infrared bird target detection based on temporal variation filtering and a gaussian heat-map perception network. Appl. Sciences-Basel 12(11) (2022). https:\/\/doi.org\/10.3390\/app12115679","DOI":"10.3390\/app12115679"},{"key":"2009_CR83","doi-asserted-by":"publisher","first-page":"25101","DOI":"10.1109\/ACCESS.2021.3057086","volume":"9","author":"G Zhu","year":"2021","unstructured":"Zhu, G., Wei, Z., Lin, F.: An object detection method combining multi-level feature fusion and region channel attention. IEEE ACCESS 9, 25101\u201325109 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3057086","journal-title":"IEEE ACCESS"},{"key":"2009_CR84","doi-asserted-by":"publisher","unstructured":"Luo, Y., Cao, X., Zhang, J., Pan, L., Wang, T., Feng, Q.: Multi-scale reinforcement learning strategy for object detection. In: 2022 47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Inst Elect & Elect Engineers; Inst Elect & Elect Engineers Signal Proc Soc, Singapore, pp. 2015\u20132019. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746264 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746264"},{"key":"2009_CR85","doi-asserted-by":"publisher","unstructured":"Priyanka, Baranwal, N., Singh, K.N., Singh, A.K.: Yolo-based roi selection for joint encryption and compression of medical images with reconstruction through super-resolution network. Future Gen. Comput. Syst.(2023). https:\/\/doi.org\/10.1016\/j.future.2023.08.018","DOI":"10.1016\/j.future.2023.08.018"},{"key":"2009_CR86","doi-asserted-by":"publisher","unstructured":"Hsu, W.-Y., Chen, P.-C.: Pedestrian detection using stationary wavelet dilated residual super-resolution. IEEE Trans. Inst. Meas. 71 (2022) https:\/\/doi.org\/10.1109\/TIM.2022.3142061","DOI":"10.1109\/TIM.2022.3142061"},{"key":"2009_CR87","doi-asserted-by":"publisher","unstructured":"Zhao, J., Guo, W., Zhang, Z., Yu, W.: A coupled convolutional neural network for small and densely clustered ship detection in sar images. Sci. China-Information Sci. 62(4) (2019). https:\/\/doi.org\/10.1007\/s11432-017-9405-6","DOI":"10.1007\/s11432-017-9405-6"},{"issue":"4","key":"2009_CR88","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1109\/TGRS.2017.2778300","volume":"56","author":"K Li","year":"2018","unstructured":"Li, K., Cheng, G., Bu, S., You, X.: Rotation-insensitive and context-augmented object detection in remote sensing images. IEEE Trans. Geosci. Remote Sens. 56(4), 2337\u20132348 (2018). https:\/\/doi.org\/10.1109\/TGRS.2017.2778300","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2009_CR89","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.isprsjprs.2020.12.015","volume":"173","author":"X Sun","year":"2021","unstructured":"Sun, X., Wang, P., Wang, C., Liu, Y., Fu, K.: Pbnet: part-based convolutional neural network for complex composite object detection in remote sensing imagery. ISPRS J. Photogramm. Remote Sens. 173, 50\u201365 (2021). https:\/\/doi.org\/10.1016\/j.isprsjprs.2020.12.015","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"issue":"6","key":"2009_CR90","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.3046647","volume":"44","author":"D Zhang","year":"2022","unstructured":"Zhang, D., Zeng, W., Yao, J., Han, J.: Weakly supervised object detection using proposal- and semantic-level relationships. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3349\u20133363 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2020.3046647","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2009_CR91","doi-asserted-by":"publisher","unstructured":"Liu, J., Li, S., Zhou, C., Cao, X., Gao, Y., Wang, B.: Sraf-net: a scene-relevant anchor-free object detection network in remote sensing images. IEEE Trans. Geosci. Remote Sens. 60 (2022). https:\/\/doi.org\/10.1109\/TGRS.2021.3124959","DOI":"10.1109\/TGRS.2021.3124959"},{"issue":"9","key":"2009_CR92","doi-asserted-by":"publisher","first-page":"1442","DOI":"10.1109\/LGRS.2019.2898893","volume":"16","author":"J Han","year":"2019","unstructured":"Han, J., Liu, S., Qin, G., Zhao, Q., Zhang, H., Li, N.: A local contrast method combined with adaptive background estimation for infrared small target detection. IEEE Geosci. Remote Sens. Lett. 16(9), 1442\u20131446 (2019). https:\/\/doi.org\/10.1109\/LGRS.2019.2898893","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"issue":"4","key":"2009_CR93","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.1109\/TITS.2019.2910643","volume":"21","author":"J Wei","year":"2020","unstructured":"Wei, J., He, J., Zhou, Y., Chen, K., Tang, Z., Xiong, Z.: Enhanced object detection with deep convolutional neural networks for advanced driving assistance. IEEE Trans. Intell. Transp. Syst. 21(4), 1572\u20131583 (2020). https:\/\/doi.org\/10.1109\/TITS.2019.2910643","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"2009_CR94","doi-asserted-by":"publisher","unstructured":"Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV 2019). IEEE; IEEE Comp Soc; CVF, Seoul, pp. 6053\u20136062. https:\/\/doi.org\/10.1109\/ICCV.2019.00615 (2019)","DOI":"10.1109\/ICCV.2019.00615"},{"key":"2009_CR95","doi-asserted-by":"publisher","unstructured":"Piao, Z., Wang, J., Tang, L., Zhao, B., Zhou, S.: Anchor-free object detection with scale-aware networks for autonomous driving. Electronics 11(20) (2022). https:\/\/doi.org\/10.3390\/electronics11203303","DOI":"10.3390\/electronics11203303"},{"key":"2009_CR96","doi-asserted-by":"publisher","first-page":"2638","DOI":"10.1117\/1.1409563","volume":"40","author":"S-G Sun","year":"2001","unstructured":"Sun, S.-G., Park, H.: Segmentation of forward-looking infrared image using fuzzy thresholding and edge detection. Optic. Eng. 40, 2638\u20132645 (2001)","journal-title":"Optic. Eng."},{"key":"2009_CR97","doi-asserted-by":"publisher","unstructured":"Liu, M., Chai, Z., Deng, H., Liu, R.: A cnn-transformer network with multiscale context aggregation for fine-grained cropland change detection. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 15, 4297\u20134306 (2022). https:\/\/doi.org\/10.1109\/JSTARS.2022.3177235","DOI":"10.1109\/JSTARS.2022.3177235"},{"key":"2009_CR98","doi-asserted-by":"crossref","unstructured":"Shakibania, H., Raoufi, S., Khotanlou, H.: Cdan: convolutional dense attention-guided network for low-light image enhancement (2023). arXiv:2308.12902","DOI":"10.2139\/ssrn.4817085"},{"key":"2009_CR99","doi-asserted-by":"publisher","first-page":"420","DOI":"10.3390\/rs14020420","volume":"14","author":"G Qi","year":"2022","unstructured":"Qi, G., Zhang, Y., Wang, K., Mazur, N., Liu, Y., Malaviya, D.: Small object detection method based on adaptive spatial parallel convolution and fast multi-scale fusion. Remote. Sens. 14, 420 (2022)","journal-title":"Remote. Sens."},{"key":"2009_CR100","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Q., Ruan, W., Zhu, J., Lei, L., Wu, X., Hao, G.: Alfpn: adaptive learning feature pyramid network for small object detection. Int. J. Intell. Syst. (2023)","DOI":"10.1155\/2023\/6266209"},{"key":"2009_CR101","doi-asserted-by":"publisher","first-page":"65347","DOI":"10.1109\/ACCESS.2019.2917952","volume":"7","author":"R Dong","year":"2019","unstructured":"Dong, R., Pan, X., Li, F.: Denseu-net-based semantic segmentation of objects in urban remote sensing images. IEEE ACCESS 7, 65347\u201365356 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2917952","journal-title":"IEEE ACCESS"},{"key":"2009_CR102","doi-asserted-by":"publisher","unstructured":"Luo, Y., Cao, X., Zhang, J., Cheng, P., Wang, T., Feng, Q.: Dynamic multi-scale loss balance for object detection. In: 2022 47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Inst Elect & Elect Engineers; Inst Elect & Elect Engineers Signal Proc Soc, Singapore, pp. 4873\u20134877. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747148 (2022)","DOI":"10.1109\/ICASSP43922.2022.9747148"},{"key":"2009_CR103","unstructured":"Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alche-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems (NIPS 2019). 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, vol. 32 (2019)"},{"issue":"8","key":"2009_CR104","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","volume":"42","author":"J Hu","year":"2020","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 42(8), 2011\u20132023 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2019.2913372","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2009_CR105","doi-asserted-by":"publisher","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer vision - ECCV 2018, PT VII. Lecture Notes in Computer Science. 15th European Conference on Computer Vision (ECCV), Munich, vol. 11211, pp. 3\u201319. https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2009_CR106","doi-asserted-by":"publisher","first-page":"113018","DOI":"10.1016\/j.measurement.2023.113018","volume":"218","author":"N Lang","year":"2023","unstructured":"Lang, N., Wang, D., Cheng, P.: A learning-based approach for aluminum tube defect detection using imbalanced dataset. Meas. 218, 113018 (2023). https:\/\/doi.org\/10.1016\/j.measurement.2023.113018","journal-title":"Meas."},{"key":"2009_CR107","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1007\/s00371-021-02067-9","volume":"38","author":"G Chen","year":"2021","unstructured":"Chen, G., Qin, H.: Class-discriminative focal loss for extreme imbalanced multiclass object detection towards autonomous driving. Vis. Comput. 38, 1051\u20131063 (2021)","journal-title":"Vis. Comput."},{"key":"2009_CR108","doi-asserted-by":"publisher","first-page":"57951","DOI":"10.1109\/ACCESS.2023.3284062","volume":"11","author":"S Wang","year":"2023","unstructured":"Wang, S., Wang, Y., Chang, Y., Zhao, R., She, Y.: Ebse-yolo: high precision recognition algorithm for small target foreign object detection. IEEE Access 11, 57951\u201357964 (2023)","journal-title":"IEEE Access"},{"key":"2009_CR109","doi-asserted-by":"publisher","unstructured":"Cong, P., Lv, K., Feng, H., Zhou, J.: Improved yolov3 model for workpiece stud leakage detection. Electronics 11(21) (2022). https:\/\/doi.org\/10.3390\/electronics11213430","DOI":"10.3390\/electronics11213430"},{"key":"2009_CR110","unstructured":"Phan, T.H., Yamamoto, K.: Resolving class imbalance in object detection with weighted cross entropy losses (2020). arXiv:2006.01413"},{"key":"2009_CR111","doi-asserted-by":"publisher","unstructured":"Wang, X., Wei, J., Liu, Y., Li, J., Zhang, Z., Chen, J., Jiang, B.: Research on morphological detection of fr i and fr ii radio galaxies based on improved yolov5. UNIVERSE 7(7) (2021). https:\/\/doi.org\/10.3390\/universe7070211","DOI":"10.3390\/universe7070211"},{"key":"2009_CR112","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.1109\/TCSVT.2019.2906246","volume":"30","author":"K Duan","year":"2020","unstructured":"Duan, K., Du, D., Qi, H., Huang, Q.: Detecting small objects using a channel-aware deconvolutional network. IEEE Trans. Circ. Syst. Vid. Technol. 30, 1639\u20131652 (2020)","journal-title":"IEEE Trans. Circ. Syst. Vid. Technol."},{"key":"2009_CR113","doi-asserted-by":"publisher","unstructured":"Zeng, Y., Zhang, T., He, W., Zhang, Z.: Yolov7-uav: An unmanned aerial vehicle image object detection algorithm based on improved yolov7. Electronics 12(14) (2023) https:\/\/doi.org\/10.3390\/electronics12143141","DOI":"10.3390\/electronics12143141"},{"key":"2009_CR114","doi-asserted-by":"publisher","unstructured":"Deng, C., Jing, D., Han, Y., Wang, S., Wang, H.: Far-net: fast anchor refining for arbitrary-oriented object detection. IEEE Geosci. Remote Sens. Lett. 19 (2022) https:\/\/doi.org\/10.1109\/LGRS.2022.3144513","DOI":"10.1109\/LGRS.2022.3144513"},{"key":"2009_CR115","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1023\/A:1008027403268","volume":"25","author":"Y Zhu","year":"1999","unstructured":"Zhu, Y., Seneviratne, L.D.: On the recognition and location of partially occluded objects. J. Intell. Robot. Syst. 25, 133\u2013151 (1999)","journal-title":"J. Intell. Robot. Syst."},{"key":"2009_CR116","doi-asserted-by":"publisher","unstructured":"Sun, J., He, X., Wu, M., Wu, X., Shen, J., Lu, B.: Detection of tomato organs based on convolutional neural network under the overlap and occlusion backgrounds. Mach. Vis. Appl. 31(5) (2020). https:\/\/doi.org\/10.1007\/s00138-020-01081-6","DOI":"10.1007\/s00138-020-01081-6"},{"key":"2009_CR117","doi-asserted-by":"publisher","unstructured":"Zhou, J., Yang, D., Cui, Z., Wang, S., Sheng, H.: Lrfnet: an occlusion robust fusion network for semantic segmentation with light field. In: 2021 IEEE 33RD International Conference on Tools with Artificial Intelligence (ICTAI 2021). Proceedings-International Conference on Tools With Artificial Intelligence. IEEE; IEEE Comp Soc; Biol Artificial Intelligence Fdn, pp. 1178\u20131186. Electr Network. https:\/\/doi.org\/10.1109\/ICTAI52525.2021.00186 (2021)","DOI":"10.1109\/ICTAI52525.2021.00186"},{"key":"2009_CR118","doi-asserted-by":"publisher","unstructured":"Sahin, G., Itti, L.: Multi-task occlusion learning for real-time visual object tracking. In: 2021 IEEE International Conference on Image Processing (ICIP), Electr network. IEEE; Inst Elect & Elect Engineers Signal Proc Soc, pp. 524\u2013528 (2021). https:\/\/doi.org\/10.1109\/ICIP42928.2021.9506239","DOI":"10.1109\/ICIP42928.2021.9506239"},{"key":"2009_CR119","doi-asserted-by":"publisher","unstructured":"Hanson, N., Lvov, G., Padir, T.: Occluded object detection and exposure in cluttered environments with automated hyperspectral anomaly detection. Front. Robot. AI 9 (2022). https:\/\/doi.org\/10.3389\/frobt.2022.982131","DOI":"10.3389\/frobt.2022.982131"},{"key":"2009_CR120","unstructured":"Deng, B., Lin, M., Long, S.: Object occlusion of adding new categories in objection detection (2022). arXiv:2206.05730"},{"key":"2009_CR121","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.biosystemseng.2022.07.009","volume":"222","author":"Z Jiao","year":"2022","unstructured":"Jiao, Z., Huang, K., Jia, G., Lei, H., Cai, Y., Zhong, Z.: An effective litchi detection method based on edge devices in a complex scene. Biosyst. Eng. 222, 15\u201328 (2022). https:\/\/doi.org\/10.1016\/j.biosystemseng.2022.07.009","journal-title":"Biosyst. Eng."},{"key":"2009_CR122","doi-asserted-by":"publisher","first-page":"109627","DOI":"10.1016\/j.patcog.2023.109627","volume":"141","author":"X Yang","year":"2023","unstructured":"Yang, X., Wu, J., He, L., Ma, S., Hou, Z., Sun, W.: Cpss-fat: a consistent positive sample selection for object detection with full adaptive threshold. Pattern Recognit. 141, 109627 (2023). https:\/\/doi.org\/10.1016\/j.patcog.2023.109627","journal-title":"Pattern Recognit."},{"issue":"8","key":"2009_CR123","doi-asserted-by":"publisher","first-page":"101670","DOI":"10.1016\/j.jksuci.2023.101670","volume":"35","author":"J Zhao","year":"2023","unstructured":"Zhao, J., Zhu, H., Niu, L.: Bitnet: a lightweight object detection network for real-time classroom behavior recognition with transformer and bi-directional pyramid network. J. King Saud Univ. Comput. Inf. Sci. 35(8), 101670 (2023). https:\/\/doi.org\/10.1016\/j.jksuci.2023.101670","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"2009_CR124","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.patrec.2022.05.006","volume":"159","author":"J Heo","year":"2022","unstructured":"Heo, J., Wang, Y., Park, J.: Occlusion-aware spatial attention transformer for occluded object recognition. Pattern Recognit. Lett. 159, 70\u201376 (2022). https:\/\/doi.org\/10.1016\/j.patrec.2022.05.006","journal-title":"Pattern Recognit. Lett."},{"key":"2009_CR125","doi-asserted-by":"publisher","first-page":"102481","DOI":"10.1016\/j.displa.2023.102481","volume":"79","author":"Q Shang","year":"2023","unstructured":"Shang, Q., Zhang, J., Yan, G., Hong, L., Zhang, R., Li, W., Xia, H.: Target tracking algorithm based on occlusion prediction. Displays 79, 102481 (2023). https:\/\/doi.org\/10.1016\/j.displa.2023.102481","journal-title":"Displays"},{"key":"2009_CR126","doi-asserted-by":"publisher","first-page":"107788","DOI":"10.1016\/j.compag.2023.107788","volume":"208","author":"X Sheng","year":"2023","unstructured":"Sheng, X., Kang, C., Zheng, J., Lyu, C.: An edge-guided method to fruit segmentation in complex environments. Comput. Electro. Agri. 208, 107788 (2023). https:\/\/doi.org\/10.1016\/j.compag.2023.107788","journal-title":"Comput. Electro. Agri."},{"key":"2009_CR127","doi-asserted-by":"publisher","first-page":"103189","DOI":"10.1016\/j.jvcir.2021.103189","volume":"78","author":"C Xu","year":"2021","unstructured":"Xu, C., Lang, W., Xin, R., Mao, K., Jiang, H.: Generative detect for occlusion object based on occlusion generation and feature completing. J. Vis. Commun. Image Repre. 78, 103189 (2021). https:\/\/doi.org\/10.1016\/j.jvcir.2021.103189","journal-title":"J. Vis. Commun. Image Repre."},{"key":"2009_CR128","doi-asserted-by":"publisher","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: Shufflenet v2: practical guidelines for efficient cnn architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer vision - ECCV 2018, PT XIV. Lecture Notes in Computer Science, vol. 11218, pp. 122\u2013138. 15th European Conference on Computer Vision (ECCV), Munich. https:\/\/doi.org\/10.1007\/978-3-030-01264-9_8 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"2009_CR129","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural networks. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems 28 (NIPS 2015). Advances in neural information processing systems, vol. 28. 29th Annual Conference on Neural Information Processing Systems (NIPS), Montreal (2015)"},{"key":"2009_CR130","doi-asserted-by":"publisher","first-page":"100762","DOI":"10.1016\/j.iot.2023.100762","volume":"22","author":"G Xue","year":"2023","unstructured":"Xue, G., Li, S., Hou, P., Gao, S., Tan, R.: Research on lightweight yolo coal gangue detection algorithm based on resnet18 backbone feature network. Int. Things 22, 100762 (2023)","journal-title":"Int. Things"},{"key":"2009_CR131","doi-asserted-by":"publisher","first-page":"108045","DOI":"10.1016\/j.compag.2023.108045","volume":"212","author":"J Cui","year":"2023","unstructured":"Cui, J., Zheng, H., Zeng, Z., Yang, Y., Ma, R., Tao, N., Tan, J.X., Feng, X., Qi, L.: Real-time missing seedling counting in paddy fields based on lightweight network and tracking-by-detection algorithm. Comput. Electron. Agric. 212, 108045 (2023)","journal-title":"Comput. Electron. Agric."},{"key":"2009_CR132","doi-asserted-by":"crossref","unstructured":"Mahaur, B., Mishra, K.K., Kumar, A.: An improved lightweight small object detection framework applied to real-time autonomous driving. Exp. Syst. Appl. (2023)","DOI":"10.1016\/j.eswa.2023.121036"},{"key":"2009_CR133","doi-asserted-by":"crossref","unstructured":"Ge, S., Luo, Z., Zhao, S., Jin, X., Zhang, X.-Y.: Compressing deep neural networks for efficient visual inference. In: 2017 IEEE International Conference on Multimedia and Expo (ICME). IEEE, Hong Kong, pp. 667\u2013672 (2017)","DOI":"10.1109\/ICME.2017.8019465"},{"key":"2009_CR134","doi-asserted-by":"crossref","unstructured":"Wang, J.: Lightweight and real-time object detection model on edge devices with model quantization. J. Phys. Conf. Ser. 1748 (2021)","DOI":"10.1088\/1742-6596\/1748\/3\/032055"},{"key":"2009_CR135","doi-asserted-by":"crossref","unstructured":"Liqun, C., Lei, H.: Clipping-based neural network post training quantization for object detection. In: 2023 IEEE International Conference on Control, Electronics and Computer Technology (ICCECT), pp 1192\u20131196 (2023)","DOI":"10.1109\/ICCECT57938.2023.10141287"},{"key":"2009_CR136","doi-asserted-by":"publisher","unstructured":"Zhang, W., Biswas, G., Zhao, Q., Zhao, H., Feng, W.: Knowledge distilling based model compression and feature learning in fault diagnosis. Appl. Soft Comput. 88 (2020). https:\/\/doi.org\/10.1016\/j.asoc.2019.105958","DOI":"10.1016\/j.asoc.2019.105958"},{"key":"2009_CR137","doi-asserted-by":"crossref","unstructured":"Wang, W., Su, C., Han, G., Zhang, H.: A lightweight crack segmentation network based on knowledge distillation. J. Building Eng. (2023)","DOI":"10.1016\/j.jobe.2023.107200"},{"key":"2009_CR138","doi-asserted-by":"publisher","first-page":"107765","DOI":"10.1016\/j.compag.2023.107765","volume":"207","author":"Y Shang","year":"2023","unstructured":"Shang, Y., Xu, X., Jiao, Y., Wang, Z., Hua, Z., Song, H.: Using lightweight deep learning algorithm for real-time detection of apple flowers in natural environments. Comput. Electron. Agric. 207, 107765 (2023)","journal-title":"Comput. Electron. Agric."},{"key":"2009_CR139","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yang, Y., Sun, J., Zhang, P.P., Ji, R., Shan, H.: Surface defect detection of wind turbine based on lightweight yolov5s model. SSRN Electron. J. (2023)","DOI":"10.2139\/ssrn.4348576"},{"key":"2009_CR140","doi-asserted-by":"publisher","first-page":"107098","DOI":"10.1016\/j.compag.2022.107098","volume":"198","author":"S Zhao","year":"2022","unstructured":"Zhao, S., Zhang, S., Lu, J., Wang, H., Feng, Y., Shi, C., Li, D., Zhao, R.: A lightweight dead fish detection method based on deformable convolution and yolov4. Comput. Electron. Agric. 198, 107098 (2022)","journal-title":"Comput. Electron. Agric."},{"key":"2009_CR141","doi-asserted-by":"publisher","first-page":"119108","DOI":"10.1016\/j.eswa.2022.119108","volume":"213","author":"M Bie","year":"2022","unstructured":"Bie, M., Liu, Y., Li, G., Hong, J., Li, J.: Real-time vehicle detection algorithm based on a lightweight you-only-look-once (yolov5n-l) approach. Expert Syst. Appl. 213, 119108 (2022)","journal-title":"Expert Syst. Appl."},{"key":"2009_CR142","unstructured":"Park, K., Jang, W., Lee, W., Nam, K., Seong, K., Chai, K., Li, W.-S.: Real-time mask detection on google edge tpu. (2020). arXiv:2010.04427"},{"issue":"12","key":"2009_CR143","doi-asserted-by":"publisher","first-page":"14096","DOI":"10.1007\/s11227-022-04415-5","volume":"78","author":"K Zeng","year":"2022","unstructured":"Zeng, K., Ma, Q., Wu, J.W., Chen, Z., Shen, T., Yan, C.: Fpga-based accelerator for object detection: a comprehensive survey. J. Supercomput. 78(12), 14096\u201314136 (2022). https:\/\/doi.org\/10.1007\/s11227-022-04415-5","journal-title":"J. Supercomput."},{"key":"2009_CR144","doi-asserted-by":"crossref","unstructured":"Zhang, F., Li, Y., Ye, Z.: Apply yolov4-tiny on an fpga-based accelerator of convolutional neural network for object detection. J. Phys. Conf. Ser. 2303 (2022)","DOI":"10.1088\/1742-6596\/2303\/1\/012032"},{"key":"2009_CR145","doi-asserted-by":"crossref","unstructured":"Li, W., Hu, H.: Fpga-based object detection acceleration architecture design. J. Phys. Conf. Ser. 2405 (2022)","DOI":"10.1088\/1742-6596\/2405\/1\/012011"},{"issue":"3","key":"2009_CR146","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1109\/TNNLS.2020.3041185","volume":"33","author":"J Xu","year":"2022","unstructured":"Xu, J., Du, W., Jin, Y., He, W., Cheng, R.: Ternary compression for communication-efficient federated learning. IEEE Trans. Neural Netw. Learn. Syst. 33(3), 1162\u20131176 (2022). https:\/\/doi.org\/10.1109\/TNNLS.2020.3041185","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2009_CR147","doi-asserted-by":"publisher","unstructured":"Liang, J., Zhang, Y., Xue, J., Hu, Y.: Lightweight image super-resolution network using involution. Mach. Vis. Appl. 33(5) (2022). https:\/\/doi.org\/10.1007\/s00138-022-01307-9","DOI":"10.1007\/s00138-022-01307-9"},{"key":"2009_CR148","doi-asserted-by":"publisher","first-page":"103719","DOI":"10.1016\/j.jvcir.2022.103719","volume":"90","author":"X Zhong","year":"2022","unstructured":"Zhong, X., Wang, M., Liu, W., Yuan, J., Huang, W.: Scpnet: self-constrained parallelism network for keypoint-based lightweight object detection. J. Vis. Commun. Image Represent. 90, 103719 (2022)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"2009_CR149","doi-asserted-by":"crossref","unstructured":"Zhang, T., Pan, Y.: Real-time detection of a camouflaged object in unstructured scenarios based on hierarchical aggregated attention lightweight network. Adv. Eng. Inf. (2023)","DOI":"10.1016\/j.aei.2023.102082"},{"key":"2009_CR150","doi-asserted-by":"publisher","first-page":"108520","DOI":"10.1016\/j.compeleceng.2022.108520","volume":"105","author":"J Huang","year":"2023","unstructured":"Huang, J., Chen, J., Wang, H.: A lightweight and efficient one-stage detection framework. Comput. Electr. Eng. 105, 108520 (2023)","journal-title":"Comput. Electr. Eng."},{"key":"2009_CR151","doi-asserted-by":"crossref","unstructured":"Xu, H., Li, B., Zhong, F.: Light-yolov5: a lightweight algorithm for improved yolov5 in complex fire scenarios (2022). arXiv:2208.13422","DOI":"10.3390\/app122312312"},{"key":"2009_CR152","doi-asserted-by":"crossref","unstructured":"Wang, Z., Jin, L., Wang, S., Xu, H.: Apple stem\/calyx real-time recognition using yolo-v5 algorithm for fruit automatic loading system. Postharvest Bio. Technol. (2022)","DOI":"10.1016\/j.postharvbio.2021.111808"},{"key":"2009_CR153","unstructured":"Hou, Z., Kung, S.Y.: Parameter efficient dynamic convolution via tensor decomposition. In: British Machine Vision Conference (2021). https:\/\/api.semanticscholar.org\/CorpusID:249892686"},{"key":"2009_CR154","doi-asserted-by":"publisher","first-page":"3338","DOI":"10.1109\/TASE.2021.3118635","volume":"19","author":"Y Li","year":"2022","unstructured":"Li, Y., Shi, Z., Liu, C., Tian, W., Kong, Z.J., Williams, C.B.: Augmented time regularized generative adversarial network (atr-gan) for data augmentation in online process anomaly detection. IEEE Trans. Auto. Sci. Eng. 19, 3338\u20133355 (2022)","journal-title":"IEEE Trans. Auto. Sci. Eng."},{"key":"2009_CR155","doi-asserted-by":"crossref","unstructured":"Malialis, K., Papatheodoulou, D., Filippou, S., Panayiotou, C.G., Polycarpou, M.M.: Data augmentation on-the-fly and active learning in data stream classification. In: 2022 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1408\u20131414 (2022)","DOI":"10.1109\/SSCI51031.2022.10022133"},{"key":"2009_CR156","unstructured":"Regulariza, B., Uddin, A.F.M.S., Monira, S., Shin, W., Chung, T., Bae, S.-H.: Saliencymix: a saliency guided data augmentation strategy for better regularization (2020). arXiv:2006.01791"},{"key":"2009_CR157","unstructured":"Choi, H.K., Choi, J., Kim, H.J.: Tokenmixup: efficient attention-guided token-level data augmentation for transformers (2022). arXiv:2210.07562"},{"key":"2009_CR158","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., Xu, C.: Ghostnet: more features from cheap operations. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1577\u20131586 (2019)","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"2009_CR159","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T.-Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16514\u201316524 (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"2009_CR160","doi-asserted-by":"publisher","first-page":"6893","DOI":"10.1109\/TIP.2022.3216771","volume":"31","author":"T Liang","year":"2021","unstructured":"Liang, T., Chu, X., Liu, Y., Wang, Y., Tang, Z., Chu, W., Chen, J., Ling, H.: Cbnet: a composite backbone network architecture for object detection. IEEE Trans. Image Process. 31, 6893\u20136906 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"2009_CR161","unstructured":"Jiang, Y., Tan, Z., Wang, J., Sun, X., Lin, M., Li, H.: Giraffedet: a heavy-neck paradigm for object detection (2022). arXiv:2202.04256"},{"key":"2009_CR162","doi-asserted-by":"crossref","unstructured":"Lee, Y., Kim, J., Willette, J., Hwang, S.J.: Mpvit: multi-path vision transformer for dense prediction. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7277\u20137286 (2021)","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"2009_CR163","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.-Y., Pang, R., Le, Q.V.: Nas-fpn: learning scalable feature pyramid architecture for object detection. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7029\u20137038 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"2009_CR164","doi-asserted-by":"crossref","unstructured":"Park, H.-J., Choi, Y.J., Lee, Y.-W., Kim, B.-G.: ssfpn: scale sequence (s2) feature-based feature pyramid network for object detection. Sensors (Basel, Switzerland) 23 (2022)","DOI":"10.3390\/s23094432"},{"key":"2009_CR165","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.1007\/s10044-023-01173-9","volume":"26","author":"Z Liu","year":"2023","unstructured":"Liu, Z., Cheng, J.: Cb-fpn: object detection feature pyramid network based on context information and bidirectional efficient fusion. Pattern Anal. Appl. 26, 1441\u20131452 (2023)","journal-title":"Pattern Anal. Appl."},{"key":"2009_CR166","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13708\u201313717 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"2009_CR167","doi-asserted-by":"crossref","unstructured":"Sagar, A.: Dmsanet: dual multi scale attention network (2021). arXiv:2106.08382","DOI":"10.1007\/978-3-031-06427-2_53"},{"key":"2009_CR168","unstructured":"Cao, J., Chen, Q., Guo, J., Shi, R.: Attention-guided context feature pyramid network for object detection (2020). arXiv:2005.11475"},{"key":"2009_CR169","doi-asserted-by":"publisher","first-page":"8128","DOI":"10.1109\/TCSVT.2021.3102944","volume":"32","author":"Z Li","year":"2021","unstructured":"Li, Z., Lang, C., Liang, L., Zhao, J., Feng, S., Hou, Q., Feng, J.: Dense attentive feature enhancement for salient object detection. IEEE Trans. Circ. Syst. Vid. Technol. 32, 8128\u20138141 (2021)","journal-title":"IEEE Trans. Circ. Syst. Vid. Technol."},{"key":"2009_CR170","unstructured":"Gevorgyan, Z.: Siou loss: more powerful learning for bounding box regression (2022). arXiv:2205.12740"},{"key":"2009_CR171","doi-asserted-by":"crossref","unstructured":"Oksuz, K., Cam, B.C., Akbas, E., Kalkan, S.: Rank & sort loss for object detection and instance segmentation. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2989\u20132998 (2021)","DOI":"10.1109\/ICCV48922.2021.00300"},{"key":"2009_CR172","unstructured":"Wang, J., Xu, C., Yang, W., Yu, L.: A normalized gaussian wasserstein distance for tiny object detection (2021). arXiv:2110.13389"},{"key":"2009_CR173","unstructured":"He, J., Erfani, S.M., Ma, X., Bailey, J., Chi, Y., Hua, X.: Alpha-iou: a family of power intersection over union losses for bounding box regression (2021). arXiv:2110.13675"},{"key":"2009_CR174","unstructured":"Chen, D., Miao, D.: Control distance iou and control distance iou loss function for better bounding box regression (2021). arXiv:2103.11696"},{"key":"2009_CR175","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. 2017 IEEE International Conference on Computer Vision (ICCV), pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"2009_CR176","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions (2015). arXiv:1511.07122"},{"key":"2009_CR177","doi-asserted-by":"crossref","unstructured":"Chen, J., Kao, S.-h., He, H., Zhuo, W., Wen, S., Lee, C.-H., Chan, S.-H.G.: Run, don\u2019t walk: chasing higher flops for faster neural networks. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12021\u201312031 (2023)","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"2009_CR178","doi-asserted-by":"crossref","unstructured":"Park, H.-J., Choi, Y.J., Lee, Y.-W., Kim, B.-G.: ssfpn: scale sequence (s2) feature-based feature pyramid network for object detection. Sensors (Basel, Switzerland) 23 (2022)","DOI":"10.3390\/s23094432"},{"key":"2009_CR179","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J.-J., Ni, L.M.-s., Shum, H.-y.: Dino: Detr with improved denoising anchor boxes for end-to-end object detection (2022). arXiv:2203.03605"},{"key":"2009_CR180","doi-asserted-by":"crossref","unstructured":"Zand, M., Etemad, A., Greenspan, M.A.: Objectbox: From centers to boxes for anchor-free object detection. In: European Conference on Computer Vision (2022). https:\/\/api.semanticscholar.org\/CorpusID:250526817","DOI":"10.1007\/978-3-031-20080-9_23"},{"key":"2009_CR181","doi-asserted-by":"crossref","unstructured":"Kim, K.-j., Lee, H.S.: Probabilistic anchor assignment with iou prediction for object detection (2020). arXiv:2007.08103","DOI":"10.1007\/978-3-030-58595-2_22"},{"key":"2009_CR182","doi-asserted-by":"crossref","unstructured":"Liu, Y.-C., Ma, C.-Y., Kira, Z.: Unbiased teacher v2: semi-supervised object detection for anchor-free and anchor-based detectors. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9809\u20139818 (2022)","DOI":"10.1109\/CVPR52688.2022.00959"},{"key":"2009_CR183","doi-asserted-by":"crossref","unstructured":"Dai, X., Chen, Y., Xiao, B., Chen, D., Liu, M., Yuan, L., Zhang, L.: Dynamic head: unifying object detection heads with attentions. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7369\u20137378 (2021)","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"2009_CR184","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. 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 2778\u20132788 (2021)","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"2009_CR185","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, Y., Yuan, L., Liu, Z., Wang, L., Li, H., Fu, Y.R.: Rethinking classification and localization for object detection. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10183\u201310192 (2019)","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"2009_CR186","doi-asserted-by":"crossref","unstructured":"Baidya, R., Jeong, H.-J.: Yolov5 with convmixer prediction heads for precise object detection in drone imagery. Sensors (Basel, Switzerland) 22 (2022)","DOI":"10.3390\/s22218424"},{"key":"2009_CR187","doi-asserted-by":"publisher","first-page":"104117","DOI":"10.1016\/j.imavis.2021.104117","volume":"107","author":"RA Solovyev","year":"2021","unstructured":"Solovyev, R.A., Wang, W., Gabruseva, T.: Weighted boxes fusion: ensembling boxes from different object detection models. Image Vis. Comput. 107, 104117 (2021)","journal-title":"Image Vis. Comput."},{"key":"2009_CR188","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-nms - improving object detection with one line of code. 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5562\u20135570 (2017)","DOI":"10.1109\/ICCV.2017.593"},{"key":"2009_CR189","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/j.neucom.2022.09.080","volume":"512","author":"H Zhao","year":"2022","unstructured":"Zhao, H., Wang, J.-K., Dai, D., Lin, S., Chen, Z.: D-nms: a dynamic nms network for general object detection. Neurocomput. 512, 225\u2013234 (2022)","journal-title":"Neurocomput."},{"key":"2009_CR190","doi-asserted-by":"crossref","unstructured":"Liu, L., Hirakawa, T., Yamashita, T., Fujiyoshi, H.: Class-wise fm-nms for knowledge distillation of object detection. 2022 IEEE International Conference on Image Processing (ICIP), pp. 1641\u20131645 (2022)","DOI":"10.1109\/ICIP46576.2022.9897257"},{"key":"2009_CR191","unstructured":"Mantovani, R.G., Horv\u00e1th, T., Cerri, R., Junior, S.B., Vanschoren, J., Carvalho, A.C.P.: An empirical study on hyperparameter tuning of decision trees (2018). arXiv:1812.02207"},{"key":"2009_CR192","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.patrec.2017.01.007","volume":"88","author":"E Duarte","year":"2017","unstructured":"Duarte, E., Wainer, J.: Empirical comparison of cross-validation and internal metrics for tuning svm hyperparameters. Pattern Recognit. Lett. 88, 6\u201311 (2017)","journal-title":"Pattern Recognit. Lett."},{"issue":"3","key":"2009_CR193","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1021\/acs.jcim.8b00671","volume":"59","author":"Y Zhou","year":"2018","unstructured":"Zhou, Y., Cahya, S., Combs, S.A., Nicolaou, C.A., Wang, J.-B., Desai, P.V., Shen, J.: Exploring tunable hyperparameters for deep neural networks with industrial adme data sets. J. Chem. Inf. Model 59(3), 1005\u20131016 (2018)","journal-title":"J. Chem. Inf. Model"},{"key":"2009_CR194","doi-asserted-by":"crossref","unstructured":"Probst, P.: Hyperparameters, tuning and meta-learning for random forest and other machine learning algorithms. (2019). https:\/\/api.semanticscholar.org\/CorpusID:201710457","DOI":"10.1002\/widm.1301"},{"key":"2009_CR195","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R.B., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., He, K.: Accurate, large minibatch sgd: training imagenet in 1 hour (2017). arXiv:1706.02677"},{"key":"2009_CR196","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). arXiv:1412.6980"},{"key":"2009_CR197","unstructured":"Zhuang, J., Tang, T.M., Ding, Y., Tatikonda, S.C., Dvornek, N.C., Papademetris, X., Duncan, J.S.: Adabelief optimizer: adapting stepsizes by the belief in observed gradients (2020). arXiv:2010.07468"},{"key":"2009_CR198","doi-asserted-by":"publisher","first-page":"52818","DOI":"10.1109\/ACCESS.2022.3174583","volume":"10","author":"IS Isa","year":"2022","unstructured":"Isa, I.S., Rosli, M.S.A., Yusof, U.K., Maruzuki, M.I.F., Sulaiman, S.N.: Optimizing the hyperparameter tuning of yolov5 for underwater detection. IEEE Access 10, 52818\u201352831 (2022)","journal-title":"IEEE Access"},{"key":"2009_CR199","unstructured":"Kingma, D.P., Salimans, T., Welling, M.: Variational dropout and the local reparameterization trick. In: NIPS (2015). https:\/\/api.semanticscholar.org\/CorpusID:46343823"},{"key":"2009_CR200","doi-asserted-by":"crossref","unstructured":"Mobiny, A., Nguyen, H.V., Moulik, S., Garg, N., Wu, C.C.: Dropconnect is effective in modeling uncertainty of bayesian deep networks. Scientific Reports 11 (2019)","DOI":"10.1038\/s41598-021-84854-x"},{"key":"2009_CR201","unstructured":"Bouthillier, X., Delaunay, P., Bronzi, M., Trofimov, A., Nichyporuk, B., Szeto, J., Sepah, N., Raff, E., Madan, K., Voleti, V.S., Kahou, S.E., Michalski, V., Serdyuk, D., Arbel, T., Pal, C., Varoquaux, G., Vincent, P.: Accounting for variance in machine learning benchmarks (2021). arXiv:2103.03098"},{"key":"2009_CR202","doi-asserted-by":"crossref","unstructured":"Takenaga, S., Watanabe, S., Nomura, M., Ozaki, Y., Onishi, M., Habe, H.: Evaluating initialization of nelder-mead method for hyperparameter optimization in deep learning. 2020 25th International Conference on Pattern Recognition (ICPR), pp. 3372\u20133379 (2021)","DOI":"10.1109\/ICPR48806.2021.9412240"},{"key":"2009_CR203","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1504\/IJWMC.2022.122489","volume":"22","author":"Y Yin","year":"2022","unstructured":"Yin, Y., Zhang, G.: Object detection based on multiple trick feature pyramid networks and dynamic balanced l1 loss. Int. J. Wirel. Mob. Comput. 22, 93\u2013103 (2022)","journal-title":"Int. J. Wirel. Mob. Comput."},{"key":"2009_CR204","doi-asserted-by":"crossref","unstructured":"Li, T., Shu, X., Chen, G., Wang, Y.: Size-sensitive optimization of loss function on vision-based object detection. Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering (2021)","DOI":"10.1145\/3501409.3501689"},{"key":"2009_CR205","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1016\/j.neunet.2021.04.028","volume":"142","author":"YY Zhang","year":"2021","unstructured":"Zhang, Y.Y., Wang, H., Lv, X., Zhang, P.: Capturing the grouping and compactness of high-level semantic feature for saliency detection. Neural Netw. 142, 351\u2013362 (2021). https:\/\/doi.org\/10.1016\/j.neunet.2021.04.028","journal-title":"Neural Netw."},{"key":"2009_CR206","doi-asserted-by":"publisher","unstructured":"Rao, Y., Mu, H., Yang, Z., Zheng, W., Wang, F., Pu, J., Zeng, S.: B-pesnet: smoothly propagating semantics for robust and reliable multi-scale object detection for secure systems. CMES-Comput. Model. Eng. Sci. 132(3), 1039\u20131054 (2022). https:\/\/doi.org\/10.32604\/cmes.2022.020331","DOI":"10.32604\/cmes.2022.020331"},{"key":"2009_CR207","doi-asserted-by":"publisher","unstructured":"Rao, Y., Mu, H., Yang, Z., Zheng, W., Wang, F., Pu, J., Zeng, S.: B-pesnet: smoothly propagating semantics for robust and reliable multi-scale object detection for secure systems. CMES-Comput. Model. Eng. Sci. 132(3), 1039\u20131054 (2022). https:\/\/doi.org\/10.32604\/cmes.2022.020331","DOI":"10.32604\/cmes.2022.020331"},{"key":"2009_CR208","doi-asserted-by":"publisher","unstructured":"Li, J., Zhu, Z., Liu, H., Su, Y., Deng, L.: Strawberry r-cnn: Recognition and counting model of strawberry based on improved faster r-cnn. Eco. Inf. 77 (2023). https:\/\/doi.org\/10.1016\/j.ecoinf.2023.102210","DOI":"10.1016\/j.ecoinf.2023.102210"},{"key":"2009_CR209","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Sung, Y.: Traffic accident detection using background subtraction and cnn encoder-transformer decoder in video frames. Math. 11(13) (2023). https:\/\/doi.org\/10.3390\/math11132884","DOI":"10.3390\/math11132884"},{"key":"2009_CR210","doi-asserted-by":"publisher","unstructured":"Li, C.-j., Qu, Z., Wang, S.-y.: A method of knowledge distillation based on feature fusion and attention mechanism for complex traffic scenes. Eng. Appl. Artif. Intelli. 124 (2023). https:\/\/doi.org\/10.1016\/j.engappai.2023.106533","DOI":"10.1016\/j.engappai.2023.106533"},{"key":"2009_CR211","doi-asserted-by":"publisher","unstructured":"Zeng, Y., Zhang, T., He, W., Zhang, Z.: Yolov7-uav: an unmanned aerial vehicle image object detection algorithm based on improved yolov7. Electronics 12(14) (2023). https:\/\/doi.org\/10.3390\/electronics12143141","DOI":"10.3390\/electronics12143141"},{"key":"2009_CR212","doi-asserted-by":"publisher","unstructured":"Wang, T., Wang, J., Wang, R.: Camouflaged object detection with a feature lateral connection network. Electronics 12(12) (2023). https:\/\/doi.org\/10.3390\/electronics12122570","DOI":"10.3390\/electronics12122570"},{"key":"2009_CR213","doi-asserted-by":"publisher","unstructured":"Yi, C., Liu, J., Huang, T., Xiao, H., Guan, H.: An efficient method of pavement distress detection based on improved yolov7. Meas. Sci. Technol. 34(11) (2023). https:\/\/doi.org\/10.1088\/1361-6501\/ace929","DOI":"10.1088\/1361-6501\/ace929"},{"key":"2009_CR214","doi-asserted-by":"publisher","unstructured":"Shen, J., Zhou, Y.: Accurate and real-time object detection in crowded indoor spaces based on the fusion of dbscan algorithm and improved yolov4-tiny network. J. Intell. Syste. 32(1) (2023). https:\/\/doi.org\/10.1515\/jisys-2022-0268","DOI":"10.1515\/jisys-2022-0268"},{"key":"2009_CR215","doi-asserted-by":"publisher","unstructured":"Nag, S., Bhattacharyya, M., Mukherjee, A., Kundu, R.: Serf: towards better training of deep neural networks using log-softplus error activation function. In: 2023 23rd IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE; CVF; IEEE Comp Soc, Waikoloa, pp. 5313\u20135322. https:\/\/doi.org\/10.1109\/WACV56688.2023.00529 (2023)","DOI":"10.1109\/WACV56688.2023.00529"},{"key":"2009_CR216","unstructured":"Devries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout (2017). arXiv:1708.04552"}],"updated-by":[{"DOI":"10.1007\/s10846-024-02130-2","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000}}],"container-title":["Journal of Intelligent & Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-023-02009-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10846-023-02009-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-023-02009-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T05:51:24Z","timestamp":1730699484000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10846-023-02009-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,29]]},"references-count":216,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["2009"],"URL":"https:\/\/doi.org\/10.1007\/s10846-023-02009-8","relation":{"correction":[{"id-type":"doi","id":"10.1007\/s10846-024-02130-2","asserted-by":"object"}]},"ISSN":["0921-0296","1573-0409"],"issn-type":[{"value":"0921-0296","type":"print"},{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,29]]},"assertion":[{"value":"24 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2024","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s10846-024-02130-2","URL":"https:\/\/doi.org\/10.1007\/s10846-024-02130-2","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Approval was obtained from the ethics committee of the Qilu University of Technology.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Informed consent was obtained from all individual participants included in the study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"The participant has consented to the submission of the research manuscript to the journal.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors have no conflicts of interest to declare that are relevant to the content of this article.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}],"article-number":"82"}}