{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T08:48:53Z","timestamp":1742978933314,"version":"3.40.3"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031263477"},{"type":"electronic","value":"9783031263484"}],"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\/978-3-031-26348-4_8","type":"book-chapter","created":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T07:03:47Z","timestamp":1678259027000},"page":"124-141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["IoU-Enhanced Attention for\u00a0End-to-End Task Specific Object Detection"],"prefix":"10.1007","author":[{"given":"Jing","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjian","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingli","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,9]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-nms-improving object detection with one line of code. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5561\u20135569 (2017)","DOI":"10.1109\/ICCV.2017.593"},{"key":"8_CR2","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":"8_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"8_CR4","unstructured":"Chen, K., et al.: Mmdetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"8_CR5","unstructured":"Chen, Y., et al.: Reppoints v2: verification meets regression for object detection. Adv. Neural Inf. Process. Syst. 33 (2020)"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 886\u2013893. IEEE (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"4","key":"8_CR9","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","volume":"34","author":"P Dollar","year":"2011","unstructured":"Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intelli. 34(4), 743\u2013761 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intelli."},{"key":"8_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Gao, P., Zheng, M., Wang, X., Dai, J., Li, H.: Fast convergence of detr with spatially modulated co-attention. arXiv preprint arXiv:2101.07448 (2021)","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Ge, Z., Liu, S., Li, Z., Yoshie, O., Sun, J.: Ota: optimal transport assignment for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 303\u2013312 (2021)","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"8_CR15","unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., He, K.: Detectron (2018). https:\/\/github.com\/facebookresearch\/detectron"},{"key":"8_CR16","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256. JMLR Workshop and Conference Proceedings (2010)"},{"key":"8_CR17","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":"8_CR18","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":"8_CR19","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"8_CR20","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, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Huang, X., Ge, Z., Jie, Z., Yoshie, O.: NMS by representative region: towards crowded pedestrian detection by proposal pairing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10750\u201310759 (2020)","DOI":"10.1109\/CVPR42600.2020.01076"},{"key":"8_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/978-3-030-58595-2_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Kim","year":"2020","unstructured":"Kim, K., Lee, H.S.: Probabilistic anchor assignment with IoU prediction for object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 355\u2013371. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_22"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 734\u2013750 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"8_CR24","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":"8_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"8_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Liu, S., Huang, D., Wang, Y.: Adaptive NMS: refining pedestrian detection in a crowd. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6459\u20136468 (2019)","DOI":"10.1109\/CVPR.2019.00662"},{"key":"8_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"8_CR30","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"8_CR31","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":"8_CR32","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":"8_CR33","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"8_CR35","unstructured":"Shao, S., et al.: Crowdhuman: a benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123 (2018)"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Song, G., Liu, Y., Wang, X.: Revisiting the sibling head in object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11563\u201311572 (2020)","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Stewart, R., Andriluka, M., Ng, A.Y.: End-to-end people detection in crowded scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2325\u20132333 (2016)","DOI":"10.1109\/CVPR.2016.255"},{"key":"8_CR38","unstructured":"Sun, P., Jiang, Y., Xie, E., Yuan, Z., Wang, C., Luo, P.: Onenet: towards end-to-end one-stage object detection. arXiv preprint arXiv:2012.05780 (2020)"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Sparse r-cnn: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Sun, Z., Cao, S., Yang, Y., Kitani, K.: Rethinking transformer-based set prediction for object detection. arXiv preprint arXiv:2011.10881 (2020)","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"8_CR41","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, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"8_CR42","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst., 5998\u20136008 (2017)"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Viola, P., Jones, M.: 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. IEEE (2001)","DOI":"10.1109\/CVPR.2001.990517"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. arXiv preprint arXiv:2102.12122 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: Reppoints: point set representation for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9657\u20139666 (2019)","DOI":"10.1109\/ICCV.2019.00975"},{"key":"8_CR46","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759\u20139768 (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"issue":"11","key":"8_CR47","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","volume":"30","author":"ZQ Zhao","year":"2019","unstructured":"Zhao, Z.Q., Zheng, P., Xu, S.T., Wu, X.: Object detection with deep learning: a review. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3212\u20133232 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"8_CR48","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: more deformable, better results. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9308\u20139316 (2019)","DOI":"10.1109\/CVPR.2019.00953"},{"key":"8_CR50","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26348-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T23:35:30Z","timestamp":1729035330000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26348-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263477","9783031263484"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26348-4_8","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":"9 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"33% - 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":"3.3","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":"2.6","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}