{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T10:34:23Z","timestamp":1770460463560,"version":"3.49.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"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 Real-Time Image Proc"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s11554-025-01796-7","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T17:48:16Z","timestamp":1763056096000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Auto-accel: a SW\/HW co-design framework with adaptive unified buffer mapping and power-of-two quantization for FPGA-based object detection accelerators"],"prefix":"10.1007","volume":"23","author":[{"given":"Junha","family":"Ko","sequence":"first","affiliation":[]},{"given":"Dongjun","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Youngchan","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Hyun","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,13]]},"reference":[{"key":"1796_CR1","doi-asserted-by":"crossref","unstructured":"Anupreetham, A., Ibrahim, M., Hall, M., Boutros, A., Kuzhively, A., Mohanty, A., Nurvitadhi, E., Betz, V., Cao, Y., Seo, J.S.: End-to-end FPGA-based object detection using pipelined CNN and non-maximum suppression. In: 2021 31st International Conference on Field-Programmable Logic and Applications (FPL), pp. 76\u201382. IEEE (2021)","DOI":"10.1109\/FPL53798.2021.00021"},{"key":"1796_CR2","doi-asserted-by":"crossref","unstructured":"Bae, S.H., Lee, H.J., Kim, H.: MCM-SR: multiple constant multiplication-based CNN streaming hardware architecture for super-resolution. In: IEEE Transactions on Very Large Scale Integration (VLSI) Systems (2024)","DOI":"10.1109\/TVLSI.2024.3504513"},{"key":"1796_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Chen, D., Liu, M., Dong, X., Yuan, L., Liu, Z.: Mobile-former: bridging mobilenet and transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5270\u20135279 (2022)","DOI":"10.1109\/CVPR52688.2022.00520"},{"issue":"15","key":"1796_CR4","doi-asserted-by":"publisher","first-page":"16019","DOI":"10.1609\/aaai.v39i15.33759","volume":"39","author":"D Choi","year":"2025","unstructured":"Choi, D., Kim, H.: GradQ-VIT: Robust and efficient gradient quantization for vision transformers. Proc. AAAI Confer. Artif. Intell. 39(15), 16019\u201316027 (2025). https:\/\/doi.org\/10.1609\/aaai.v39i15.33759","journal-title":"Proc. AAAI Confer. Artif. Intell."},{"key":"1796_CR5","doi-asserted-by":"publisher","first-page":"159611","DOI":"10.1109\/ACCESS.2024.3488093","volume":"12","author":"D Choi","year":"2024","unstructured":"Choi, D., Park, J., Kim, H.: HLQ: hardware-friendly logarithmic quantization aware training for power-efficient low-precision CNN models. IEEE Access. 12, 159611\u2013159621 (2024)","journal-title":"IEEE Access"},{"key":"1796_CR6","doi-asserted-by":"crossref","unstructured":"Choi, J., Chun, D., Kim, H., Lee, H.J.: Gaussian yolov3: an accurate and fast object detector using localization uncertainty for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 502\u2013511 (2019)","DOI":"10.1109\/ICCV.2019.00059"},{"key":"1796_CR7","doi-asserted-by":"crossref","unstructured":"Colbert, I., Pappalardo, A., Petri-Koenig, J.: A2Q: accumulator-aware quantization with guaranteed overflow avoidance. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16989\u201316998 (2023)","DOI":"10.1109\/ICCV51070.2023.01558"},{"key":"1796_CR8","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"1796_CR9","doi-asserted-by":"crossref","unstructured":"Fan, H., Liu, S., Ferianc, M., Ng, H.C., Que, Z., Liu, S., Niu, X., Luk, W.: A real-time object detection accelerator with compressed SSDLite on FPGA. In: 2018 International Conference on Field-programmable Technology (FPT), pp. 14\u201321. IEEE (2018)","DOI":"10.1109\/FPT.2018.00014"},{"key":"1796_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1796_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1796_CR12","doi-asserted-by":"crossref","unstructured":"Hettiarachchi, D.L.N., Davuluru, V.S.P., Balster, E.J.: Integer vs. floating-point processing on modern FPGA technology. In: 2020 10th Annual Computing and Communication Workshop and Conference (CCWC), pp. 0606\u20130612. IEEE (2020)","DOI":"10.1109\/CCWC47524.2020.9031118"},{"key":"1796_CR13","doi-asserted-by":"crossref","unstructured":"Hong, H., Choi, D., Kim, N., Kim, H.: Mobile-X: dedicated FPGA implementation of the mobilenet accelerator optimizing depthwise separable convolution. In: IEEE Transactions on Circuits and Systems II: Express Briefs (2024)","DOI":"10.1109\/TCSII.2024.3440884"},{"key":"1796_CR14","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. Preprint at arXiv:1704.04861 (2017)"},{"key":"1796_CR15","doi-asserted-by":"crossref","unstructured":"Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., et\u00a0al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7310\u20137311 (2017)","DOI":"10.1109\/CVPR.2017.351"},{"key":"1796_CR16","doi-asserted-by":"crossref","unstructured":"Jeong, S., Lee, S., Kim, H.: LowgradQ: adaptive gradient quantization for low-bit CNN training via kernel density estimation-guided thresholding and hardware-efficient stochastic rounding unit. In: 2025 Design, Automation & Test in Europe Conference (DATE), pp. 1\u20132. IEEE (2025)","DOI":"10.23919\/DATE64628.2025.10992985"},{"key":"1796_CR17","doi-asserted-by":"publisher","first-page":"5279","DOI":"10.1109\/TMM.2022.3189496","volume":"25","author":"NJ Kim","year":"2022","unstructured":"Kim, N.J., Kim, H.: FP-AGL: filter pruning with adaptive gradient learning for accelerating deep convolutional neural networks. IEEE Trans. Multimed. 25, 5279\u20135290 (2022)","journal-title":"IEEE Trans. Multimed."},{"key":"1796_CR18","unstructured":"Kim, N.J., Lee, J., Kim, H.: HYQ: hardware-friendly post-training quantization for CNN-transformer hybrid networks. In: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, pp. 4291\u20134299 (2024)"},{"issue":"6","key":"1796_CR19","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.1109\/TVLSI.2021.3064639","volume":"29","author":"S Kim","year":"2021","unstructured":"Kim, S., Na, S., Kong, B.Y., Choi, J., Park, I.C.: Real-time SSDLite object detection on FPGA. IEEE Trans. Very Large Scale Integr. VLSI Syst 29(6), 1192\u20131205 (2021)","journal-title":"IEEE Trans. Very Large Scale Integr. VLSI Syst"},{"key":"1796_CR20","doi-asserted-by":"publisher","first-page":"118547","DOI":"10.1109\/ACCESS.2023.3326534","volume":"11","author":"K Koo","year":"2023","unstructured":"Koo, K., Kim, H.: V-SKP: vectorized kernel-based structured kernel pruning for accelerating deep convolutional neural networks. IEEE Access 11, 118547\u2013118557 (2023)","journal-title":"IEEE Access"},{"key":"1796_CR21","doi-asserted-by":"crossref","unstructured":"Li, F., Mo, Z., Wang, P., Liu, Z., Zhang, J., Li, G., Hu, Q., He, X., Leng, C., Zhang, Y., et\u00a0al.: A system-level solution for low-power object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00301"},{"issue":"5","key":"1796_CR22","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.1109\/TCAD.2021.3082868","volume":"41","author":"G Li","year":"2021","unstructured":"Li, G., Liu, Z., Li, F., Cheng, J.: Block convolution: toward memory-efficient inference of large-scale CNNs on FPGA. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 41(5), 1436\u20131447 (2021)","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"1796_CR23","unstructured":"Li, Y., Dong, X., Wang, W.: Additive powers-of-two quantization: an efficient non-uniform discretization for neural networks. Preprint at arXiv:1909.13144 (2019)"},{"key":"1796_CR24","doi-asserted-by":"crossref","unstructured":"Liao, J., Cai, L., Xu, Y., He, M.: Design of accelerator for mobilenet convolutional neural network based on FPGA. In: 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), vol. 1, pp. 1392\u20131396. IEEE (2019)","DOI":"10.1109\/IAEAC47372.2019.8997842"},{"key":"1796_CR25","doi-asserted-by":"publisher","unstructured":"Liu, S., Deng, W.: Very deep convolutional neural network based image classification using small training sample size. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 730\u2013734 (2015). https:\/\/doi.org\/10.1109\/ACPR.2015.7486599","DOI":"10.1109\/ACPR.2015.7486599"},{"key":"1796_CR26","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: SSD: single shot multibox detector. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1796_CR27","doi-asserted-by":"crossref","unstructured":"Liu, W., Li, Y., Yang, Y., Zhu, J., Liu, L.: Design an efficient DNN inference framework with PS-PL synergies in FPGA for edge computing. In: 2022 China Automation Congress (CAC), pp. 4186\u20134190. IEEE (2022)","DOI":"10.1109\/CAC57257.2022.10055526"},{"key":"1796_CR28","doi-asserted-by":"crossref","unstructured":"Ma, Y., Cao, Y., Vrudhula, S., Seo, J.S.: Optimizing loop operation and dataflow in FPGA acceleration of deep convolutional neural networks. In: Proceedings of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 45\u201354 (2017)","DOI":"10.1145\/3020078.3021736"},{"key":"1796_CR29","unstructured":"Mehta, S., Rastegari, M.: Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=vh-0sUt8HlG"},{"key":"1796_CR30","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.neucom.2020.12.035","volume":"432","author":"P Peng","year":"2021","unstructured":"Peng, P., You, M., Xu, W., Li, J.: Fully integer-based quantization for mobile convolutional neural network inference. Neurocomputing 432, 194\u2013205 (2021)","journal-title":"Neurocomputing"},{"key":"1796_CR31","doi-asserted-by":"crossref","unstructured":"Podili, A., Zhang, C., Prasanna, V.: Fast and efficient implementation of convolutional neural networks on FPGA. In: 2017 IEEE 28Th International Conference on Application-specific Systems, Architectures and Processors (ASAP), pp. 11\u201318. IEEE (2017)","DOI":"10.1109\/ASAP.2017.7995253"},{"key":"1796_CR32","doi-asserted-by":"crossref","unstructured":"Talebi, H., Milanfar, P.: Learning to resize images for computer vision tasks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 497\u2013506 (2021)","DOI":"10.1109\/ICCV48922.2021.00055"},{"key":"1796_CR33","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"1796_CR34","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, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1796_CR35","doi-asserted-by":"crossref","unstructured":"Tu, Z., Milanfar, P., Talebi, H.: Muller: multilayer Laplacian resizer for vision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6877\u20136887 (2023)","DOI":"10.1109\/ICCV51070.2023.00633"},{"issue":"1","key":"1796_CR36","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s10489-024-05898-w","volume":"55","author":"Y Wan","year":"2025","unstructured":"Wan, Y., Chen, J., Yang, X., Zhang, H., Huang, C., Xie, X.: DSA-CNN: an FPGA-integrated deformable systolic array for convolutional neural network acceleration. Appl. Intell. 55(1), 65 (2025)","journal-title":"Appl. Intell."},{"key":"1796_CR37","doi-asserted-by":"crossref","unstructured":"Wu, D., Zhang, Y., Jia, X., Tian, L., Li, T., Sui, L., Xie, D., Shan, Y.: A high-performance CNN processor based on FPGA for mobilenets. In: 2019 29th International Conference on Field Programmable Logic and Applications (FPL), pp. 136\u2013143. IEEE (2019)","DOI":"10.1109\/FPL.2019.00030"},{"issue":"3","key":"1796_CR38","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1109\/TCSI.2021.3131581","volume":"69","author":"X Wu","year":"2021","unstructured":"Wu, X., Ma, Y., Wang, M., Wang, Z.: A flexible and efficient FPGA accelerator for various large-scale and lightweight CNNs. IEEE Trans. Circuits Syst. I Regul. Pap. 69(3), 1185\u20131198 (2021)","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"1796_CR39","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Liu, H., Gupta, S., Akin, B., Bender, G., Wang, Y., Kindermans, P.J., Tan, M., Singh, V., Chen, B.: Mobiledets: searching for object detection architectures for mobile accelerators. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3825\u20133834 (2021)","DOI":"10.1109\/CVPR46437.2021.00382"},{"key":"1796_CR40","doi-asserted-by":"crossref","unstructured":"Yu, Y., Zhao, T., Wang, K., He, L.: Light-OPU: an FPGA-based overlay processor for lightweight convolutional neural networks. In: Proceedings of the 2020 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 122\u2013132 (2020)","DOI":"10.1145\/3373087.3375311"},{"key":"1796_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., Cong, J.: Optimizing FPGA-based accelerator design for deep convolutional neural networks. In: Proceedings of the 2015 ACM\/SIGDA International Symposium on Field-programmable Gate Arrays, pp. 161\u2013170 (2015)","DOI":"10.1145\/2684746.2689060"},{"issue":"11","key":"1796_CR42","doi-asserted-by":"publisher","first-page":"2072","DOI":"10.1109\/TCAD.2017.2785257","volume":"38","author":"C Zhang","year":"2018","unstructured":"Zhang, C., Sun, G., Fang, Z., Zhou, P., Pan, P., Cong, J.: Caffeine: toward uniformed representation and acceleration for deep convolutional neural networks. IEEE Trans. Comput. Aided Des. Integr. Circ. Syst. 38(11), 2072\u20132085 (2018)","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circ. Syst."},{"issue":"4","key":"1796_CR43","first-page":"2316","volume":"69","author":"Y Zheng","year":"2022","unstructured":"Zheng, Y., Yang, H., Shu, Y., Jia, Y., Huang, Z.: Optimizing off-chip memory access for deep neural network accelerator. IEEE Trans. Circ. Syst. II Express Briefs 69(4), 2316\u20132320 (2022)","journal-title":"IEEE Trans. Circ. Syst. II Express Briefs"},{"issue":"11","key":"1796_CR44","doi-asserted-by":"publisher","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","volume":"44","author":"P Zhu","year":"2021","unstructured":"Zhu, P., Wen, L., Du, D., Bian, X., Fan, H., Hu, Q., Ling, H.: Detection and tracking meet drones challenge. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7380\u20137399 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"1796_CR45","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/JPROC.2023.3238524","volume":"111","author":"Z Zou","year":"2023","unstructured":"Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey. Proc. IEEE 111(3), 257\u2013276 (2023)","journal-title":"Proc. IEEE"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01796-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-025-01796-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01796-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T16:48:16Z","timestamp":1770396496000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-025-01796-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,13]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["1796"],"URL":"https:\/\/doi.org\/10.1007\/s11554-025-01796-7","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,13]]},"assertion":[{"value":"9 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"7"}}