{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:16:25Z","timestamp":1743074185130,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031476648"},{"type":"electronic","value":"9783031476655"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-47665-5_25","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T20:01:39Z","timestamp":1699128099000},"page":"307-321","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Q-YOLO: Efficient Inference for\u00a0Real-Time Object Detection"],"prefix":"10.1007","author":[{"given":"Mingze","family":"Wang","sequence":"first","affiliation":[]},{"given":"Huixin","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Xuhui","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xianbin","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Luping","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Baochang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"key":"25_CR1","unstructured":"NVIDIA TensorRT. https:\/\/developer.nvidia.com\/tensorrt. Accessed 03 Sep 2022"},{"key":"25_CR2","unstructured":"OpenVINO Toolkit. https:\/\/docs.openvinotoolkit.org\/latest\/index.html. Accessed 03 Sept 2022"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Y., Yao, Z., Dong, Z., Gholami, A., Mahoney, M.W., Keutzer, K.: Zeroq: a novel zero shot quantization framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13169\u201313178 (2020)","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"25_CR5","unstructured":"Denil, M., Shakibi, B., Dinh, L., Ranzato, M., De Freitas, N.: Predicting parameters in deep learning. In: Advances in Neural Information Processing Systems 26 (2013)"},{"key":"25_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-030-58536-5_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Fang","year":"2020","unstructured":"Fang, J., Shafiee, A., Abdel-Aziz, H., Thorsley, D., Georgiadis, G., Hassoun, J.H.: Post-training piecewise linear quantization for deep neural networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 69\u201386. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_5"},{"issue":"3","key":"25_CR7","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2020","unstructured":"Feng, D., et al.: Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Trans. Intell. Transp. Syst. 22(3), 1341\u20131360 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"25_CR8","unstructured":"Guo, Y., Yao, A., Chen, Y.: Dynamic network surgery for efficient dnns. In: Advances in neural information processing systems 29 (2016)"},{"key":"25_CR9","unstructured":"Han, S., Mao, H., Dally, W.: Compressing deep neural networks with pruning, trained quantization and huffman coding. arxiv 2015. arXiv preprint arXiv:1510.00149 305 (2015)"},{"key":"25_CR10","unstructured":"Howard, A.G., etal.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Jung, S., et al.: Learning to quantize deep networks by optimizing quantization intervals with task loss. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4350\u20134359 (2019)","DOI":"10.1109\/CVPR.2019.00448"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Karaoguz, H., Jensfelt, P.: Object detection approach for robot grasp detection. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 4953\u20134959. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793751"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Koonce, B., Koonce, B.: Mobilenetv3. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, pp. 125\u2013144 (2021)","DOI":"10.1007\/978-1-4842-6168-2_11"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Li, B., Ouyang, W., Sheng, L., Zeng, X., Wang, X.: Gs3d: an efficient 3d object detection framework for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1019\u20131028 (2019)","DOI":"10.1109\/CVPR.2019.00111"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Li, R., Wang, Y., Liang, F., Qin, H., Yan, J., Fan, R.: Fully quantized network for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2810\u20132819 (2019)","DOI":"10.1109\/CVPR.2019.00292"},{"key":"25_CR17","unstructured":"Li, Z., Yang, T., Wang, P., Cheng, J.: Q-vit: fully differentiable quantization for vision transformer. arXiv preprint arXiv:2201.07703 (2022)"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"25_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"25_CR20","unstructured":"Lin, Y., Zhang, T., Sun, P., Li, Z., Zhou, S.: Fq-vit: fully quantized vision transformer without retraining. arXiv preprint arXiv:2111.13824 (2021)"},{"key":"25_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., Sun, J.: Shufflenet v2: practical guidelines for efficient cnn architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"25_CR24","unstructured":"NVIDIA: Nvidia corporation (2022). https:\/\/www.nvidia.com\/"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Paul, S.K., Chowdhury, M.T., Nicolescu, M., Nicolescu, M., Feil-Seifer, D.: Object detection and pose estimation from rgb and depth data for real-time, adaptive robotic grasping. In: Advances in Computer Vision and Computational Biology: Proceedings from IPCV\u201920, HIMS\u201920, BIOCOMP\u201920, and BIOENG\u201920, pp. 121\u2013142. Springer (2021)","DOI":"10.1007\/978-3-030-71051-4_10"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Qin, H., Gong, R., Liu, X., Shen, M., Wei, Z., Yu, F., Song, J.: Forward and backward information retention for accurate binary neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2250\u20132259 (2020)","DOI":"10.1109\/CVPR42600.2020.00232"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"25_CR29","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"25_CR30","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems 28 (2015)"},{"key":"25_CR31","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"25_CR33","unstructured":"Ultralytics: YOLOv5: PyTorch implementation of YOLOv5 real-time object detection (2021). https:\/\/github.com\/ultralytics\/yolov5"},{"key":"25_CR34","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, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"25_CR35","unstructured":"Wang, R.J., Li, X., Ling, C.X.: Pelee: a real-time object detection system on mobile devices. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I.S., Xie, S.: Convnext v2: co-designing and scaling convnets with masked autoencoders. arXiv preprint arXiv:2301.00808 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Wu, B., et al.: Shift: a zero flop, zero parameter alternative to spatial convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9127\u20139135 (2018)","DOI":"10.1109\/CVPR.2018.00951"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Xu, S., et al.: Q-detr: an efficient low-bit quantized detection transformer. arXiv preprint arXiv:2304.00253 (2023)","DOI":"10.1109\/CVPR52729.2023.00374"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Xu, S., Li, Y., Wang, T., Ma, T., Zhang, B., Gao, P., Qiao, Y., L\u00fc, J., Guo, G.: Recurrent bilinear optimization for binary neural networks. In: Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXIV. pp. 19\u201335. Springer (2022)","DOI":"10.1007\/978-3-031-20053-3_2"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, B., Wang, R., Wang, X., Han, J., Ji, R.: Modulated convolutional networks. IEEE Trans. Neural Networks Learn. Syst. (2021)","DOI":"10.1109\/TNNLS.2021.3060830"},{"key":"25_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., Wang, X.: Bytetrack: Multi-object tracking by associating every detection box. In: Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII. pp. 1\u201321. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"25_CR43","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","volume":"129","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Wang, C., Wang, X., Zeng, W., Liu, W.: Fairmot: on the fairness of detection and re-identification in multiple object tracking. Int. J. Comput. Vision 129, 3069\u20133087 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"25_CR44","unstructured":"Zhu, C., Han, S., Mao, H., Dally, W.J.: Trained ternary quantization. ICLR (2016)"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Shen, C., Tan, M., Liu, L., Reid, I.: Towards effective low-bitwidth convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7920\u20137928 (2018)","DOI":"10.1109\/CVPR.2018.00826"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697\u20138710 (2018)","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47665-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T20:13:48Z","timestamp":1699128828000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47665-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031476648","9783031476655"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47665-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kitakyushu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ericlab.org\/acpr2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"164","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"93","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"57% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}