{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T14:05:27Z","timestamp":1778335527032,"version":"3.51.4"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,3,23]],"date-time":"2024-03-23T00:00:00Z","timestamp":1711152000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,23]],"date-time":"2024-03-23T00:00:00Z","timestamp":1711152000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62172212"],"award-info":[{"award-number":["62172212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s10586-024-04373-y","type":"journal-article","created":{"date-parts":[[2024,3,23]],"date-time":"2024-03-23T19:02:02Z","timestamp":1711220522000},"page":"7401-7415","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["GHA-Inst: a real-time instance segmentation model utilizing YOLO detection framework"],"prefix":"10.1007","volume":"27","author":[{"given":"Chengang","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liyan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,23]]},"reference":[{"key":"4373_CR1","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"4373_CR2","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Hermans, A., Papandreou, G., Schroff, F., Wang, P., Adam, H.: Masklab: Instance segmentation by refining object detection with semantic and direction features. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 4013\u20134022 (2018)","DOI":"10.1109\/CVPR.2018.00422"},{"key":"4373_CR3","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: Yolact: Real-time instance segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, 9157\u20139166 (2019)","DOI":"10.1109\/ICCV.2019.00925"},{"key":"4373_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120730","volume":"230","author":"G Yang","year":"2023","unstructured":"Yang, G., Li, R., Zhang, S., Wen, Y., Xu, X., Song, H.: Extracting cow point clouds from multi-view rgb images with an improved yolact++ instance segmentation. Expert Syst. Appl. 230, 120730 (2023)","journal-title":"Expert Syst. Appl."},{"key":"4373_CR5","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., Girshick, R.: Pointrend: Image segmentation as rendering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 9799\u20139808 (2020)","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"4373_CR6","doi-asserted-by":"crossref","unstructured":"Huang, H., Lin, L., Tong, R., Hu, H., Zhang, Q., Iwamoto, Y., Han, X., Chen, Y.-W., Wu, J.: Unet 3+: A full-scale connected unet for medical image segmentation. In: ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP), 1055\u20131059 (2020). IEEE","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"key":"4373_CR7","unstructured":"Han, D., Yun, S., Heo, B., Yoo, Y.: Rexnet: Diminishing representational bottleneck on convolutional neural network. arXiv preprint arXiv:2007.009926, 1 (2020)"},{"key":"4373_CR8","doi-asserted-by":"crossref","unstructured":"Koonce, B., Koonce, B.: Mobilenetv3. Convolutional neural networks with swift for Tensorflow: image recognition and dataset categorization. 125\u2013144 (2021)","DOI":"10.1007\/978-1-4842-6168-2_11"},{"key":"4373_CR9","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: Repvgg: Making vgg-style convnets great again. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 13733\u201313742 (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"4373_CR10","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/j.ins.2020.02.067","volume":"522","author":"Z Huang","year":"2020","unstructured":"Huang, Z., Wang, J., Fu, X., Yu, T., Guo, Y., Wang, R.: Dc-spp-yolo: dense connection and spatial pyramid pooling based yolo for object detection. Inf. Sci. 522, 241\u2013258 (2020)","journal-title":"Inf. Sci."},{"issue":"6","key":"4373_CR11","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1007\/s11554-022-01241-z","volume":"19","author":"H Wang","year":"2022","unstructured":"Wang, H., Jin, Y., Ke, H., Zhang, X.: Ddh-yolov5: improved yolov5 based on double iou-aware decoupled head for object detection. J. Real-Time Image Proc. 19(6), 1023\u20131033 (2022)","journal-title":"J. Real-Time Image Proc."},{"key":"4373_CR12","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. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"4373_CR13","doi-asserted-by":"crossref","unstructured":"Peng, S., Jiang, W., Pi, H., Li, X., Bao, H., Zhou, X.: Deep snake for real-time instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 8533\u20138542 (2020)","DOI":"10.1109\/CVPR42600.2020.00856"},{"key":"4373_CR14","doi-asserted-by":"crossref","unstructured":"Chen, H., Sun, K., Tian, Z., Shen, C., Huang, Y., Yan, Y.: Blendmask: Top-down meets bottom-up for instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 8573\u20138581 (2020)","DOI":"10.1109\/CVPR42600.2020.00860"},{"key":"4373_CR15","first-page":"17721","volume":"33","author":"X Wang","year":"2020","unstructured":"Wang, X., Zhang, R., Kong, T., Li, L., Shen, C.: Solov2: dynamic and fast instance segmentation. Adv. Neural. Inf. Process. Syst. 33, 17721\u201317732 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4373_CR16","doi-asserted-by":"crossref","unstructured":"He, J., Li, P., Geng, Y., Xie, X.: Fastinst: A simple query-based model for real-time instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 23663\u201323672 (2023)","DOI":"10.1109\/CVPR52729.2023.02266"},{"key":"4373_CR17","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"4373_CR18","doi-asserted-by":"crossref","unstructured":"Aboah, A., Wang, B., Bagci, U., Adu-Gyamfi, Y.: Real-time multi-class helmet violation detection using few-shot data sampling technique and yolov8. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 5349\u20135357 (2023)","DOI":"10.1109\/CVPRW59228.2023.00564"},{"key":"4373_CR19","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"4373_CR20","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et al.: Yolov6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"key":"4373_CR21","doi-asserted-by":"publisher","first-page":"1113669","DOI":"10.3389\/fmars.2023.1113669","volume":"10","author":"M Yasir","year":"2023","unstructured":"Yasir, M., Zhan, L., Liu, S., Wan, J., Hossain, M.S., Isiacik Colak, A.T., Liu, M., Islam, Q.U., Raza Mehdi, S., Yang, Q.: Instance segmentation ship detection based on improved yolov7 using complex background sar images. Front. Mar. Sci. 10, 1113669 (2023)","journal-title":"Front. Mar. Sci."},{"key":"4373_CR22","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, 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"4373_CR23","doi-asserted-by":"crossref","unstructured":"Lu, C., Xia, Z., Przystupa, K., Kochan, O., Su, J.: Dcelanm-net: medical image segmentation based on dual channel efficient layer aggregation network with learner. arXiv preprint arXiv:2304.09620 (2023)","DOI":"10.1002\/ima.22960"},{"key":"4373_CR24","doi-asserted-by":"crossref","unstructured":"Chowdhury, P.N., Sain, A., Bhunia, A.K., Xiang, T., Gryaditskaya, Y., Song, Y.-Z.: Fs-coco: Towards understanding of freehand sketches of common objects in context. In: European conference on computer vision, 253\u2013270 (2022). Springer","DOI":"10.1007\/978-3-031-20074-8_15"},{"key":"4373_CR25","doi-asserted-by":"crossref","unstructured":"Qi, L., Jiang, L., Liu, S., Shen, X., Jia, J.: Amodal instance segmentation with kins dataset. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, 3014\u20133023 (2019)","DOI":"10.1109\/CVPR.2019.00313"},{"key":"4373_CR26","unstructured":"Lv, W., Xu, S., Zhao, Y., Wang, G., Wei, J., Cui, C., Du, Y., Dang, Q., Liu, Y.: Detrs beat yolos on real-time object detection. arXiv preprint arXiv:2304.08069 (2023)"},{"key":"4373_CR27","doi-asserted-by":"crossref","unstructured":"Chen, K., Pang, J., Wang, J., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Shi, J., Ouyang, W., : Hybrid task cascade for instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 4974\u20134983 (2019)","DOI":"10.1109\/CVPR.2019.00511"},{"key":"4373_CR28","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International conference on computer vision. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"4373_CR29","doi-asserted-by":"crossref","unstructured":"Li, R., He, C., Li, S., Zhang, Y., Zhang, L.: Dynamask: Dynamic mask selection for instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11279\u201311288 (2023)","DOI":"10.1109\/CVPR52729.2023.01085"},{"key":"4373_CR30","doi-asserted-by":"crossref","unstructured":"Fang, Y., Yang, S., Wang, X., Li, Y., Fang, C., Shan, Y., Feng, B., Liu, W.: Instances as queries. In: Proceedings of the IEEE\/CVF international conference on computer vision, 6910\u20136919 (2021)","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"4373_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, T., Wei, S., Ji, S.: E2ec: An end-to-end contour-based method for high-quality high-speed instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 4443\u20134452 (2022)","DOI":"10.1109\/CVPR52688.2022.00440"},{"key":"4373_CR32","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"4373_CR33","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"4373_CR34","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"4373_CR35","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"4373_CR36","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops, 0\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"4373_CR37","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.-Y., Le, Q.V.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"4373_CR38","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"4373_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: Eca-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"4373_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2022.104215","volume":"50","author":"Q Li","year":"2022","unstructured":"Li, Q., Li, D., Zhao, K., Wang, L., Wang, K.: State of health estimation of lithium-ion battery based on improved ant lion optimization and support vector regression. J. Energy Storage 50, 104215 (2022)","journal-title":"J. Energy Storage"},{"key":"4373_CR41","doi-asserted-by":"crossref","unstructured":"Lee, Y., Park, J.: Centermask: Real-time anchor-free instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 13906\u201313915 (2020)","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"4373_CR42","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H.: Conditional convolutions for instance segmentation. In: Computer Vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16, 282\u2013298 (2020). Springer","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"4373_CR43","doi-asserted-by":"crossref","unstructured":"Zhu, X., Lyu, S., Wang, X., Zhao, Q.: Tph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios. In: Proceedings of the IEEE\/CVF international conference on computer vision, 2778\u20132788 (2021)","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"4373_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhang, H., Zhao, Y.: Yolov7-sea: Object detection of maritime uav images based on improved yolov7. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, 233\u2013238 (2023)","DOI":"10.1109\/WACVW58289.2023.00029"},{"key":"4373_CR45","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2359\u20132367 (2017)","DOI":"10.1109\/CVPR.2017.472"},{"key":"4373_CR46","doi-asserted-by":"crossref","unstructured":"Ke, L., Tai, Y.-W., Tang, C.-K.: Deep occlusion-aware instance segmentation with overlapping bilayers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 4019\u20134028 (2021)","DOI":"10.1109\/CVPR46437.2021.00401"},{"issue":"8","key":"4373_CR47","doi-asserted-by":"publisher","first-page":"4061","DOI":"10.3390\/app12084061","volume":"12","author":"X Zeng","year":"2022","unstructured":"Zeng, X., Liu, X., Yin, J.: Amodal segmentation just like doing a jigsaw. Appl. Sci. 12(8), 4061 (2022)","journal-title":"Appl. Sci."},{"key":"4373_CR48","doi-asserted-by":"crossref","unstructured":"Chattopadhay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. In: 2018 IEEE winter conference on applications of computer vision (WACV), 839\u2013847 (2018). IEEE","DOI":"10.1109\/WACV.2018.00097"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-024-04373-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-024-04373-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-024-04373-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T12:43:51Z","timestamp":1725453831000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-024-04373-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,23]]},"references-count":48,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["4373"],"URL":"https:\/\/doi.org\/10.1007\/s10586-024-04373-y","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,23]]},"assertion":[{"value":"7 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We have conducted a thorough assessment of both financial and non-financial affiliations that could potentially create a Conflict of interest with the research presented. We unequivocally declare that no Conflict of interest have been identified that could in any way introduce bias or influence the outcomes of our study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}