{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T17:14:32Z","timestamp":1743095672954,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031189159"},{"type":"electronic","value":"9783031189166"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-18916-6_29","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"351-365","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Object Detection Based on Embedding Internal and External Knowledge"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7291-5635","authenticated-orcid":false,"given":"Qian","family":"Liu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3481-7820","authenticated-orcid":false,"given":"Xiaoyu","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Xu, H., Jiang, C., Liang, X., et al.: Spatial-aware graph relation network for large-scale object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9298\u20139307 (2019)","key":"29_CR1","DOI":"10.1109\/CVPR.2019.00952"},{"doi-asserted-by":"crossref","unstructured":"Xu, H., Jiang, C.H., Liang, X., et al.: Reasoning-rcnn: unifying adaptive global reasoning into large-scale object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6419\u20136428 (2019)","key":"29_CR2","DOI":"10.1109\/CVPR.2019.00658"},{"unstructured":"Jiang, C., Xu, H., Liang, X., et al.: Hybrid knowledge routed modules for large-scale object detection. Adv. Neural Inf. Process. Syst. 31 (2018)","key":"29_CR3"},{"unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)","key":"29_CR4"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","key":"29_CR5","DOI":"10.1109\/ICCV48922.2021.00986"},{"doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","key":"29_CR6","DOI":"10.1109\/CVPR.2017.106"},{"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)","key":"29_CR7","DOI":"10.1007\/978-3-030-01264-9_45"},{"doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., et al.: Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6569\u20136578 (2019)","key":"29_CR8","DOI":"10.1109\/ICCV.2019.00667"},{"doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., et al.: 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)","key":"29_CR9","DOI":"10.1109\/CVPR.2016.91"},{"unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection (2020). arXiv preprint arXiv:2004.10934","key":"29_CR10"},{"doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., et al.: 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)","key":"29_CR11","DOI":"10.1109\/CVPR.2014.81"},{"unstructured":"Beal, J., Kim, E., Tzeng, E., et al.: Toward transformer-based object detection (2020). arXiv preprint arXiv:2012.09958","key":"29_CR12"},{"doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., et al.: Deep clustering for unsupervised learning of visual features. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 132\u2013149 (2018)","key":"29_CR13","DOI":"10.1007\/978-3-030-01264-9_9"},{"doi-asserted-by":"crossref","unstructured":"Ahsan, U., Madhok, R., Essa, I.: Video jigsaw: unsupervised learning of spatiotemporal context for video action recognition. In: Proceedings of the 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 179\u2013189. IEEE (2019)","key":"29_CR14","DOI":"10.1109\/WACV.2019.00025"},{"issue":"07","key":"29_CR15","first-page":"12492","volume":"34","author":"H Xu","year":"2020","unstructured":"Xu, H., Fang, L., Liang, X., et al.: Universal-rcnn: universal object detector via transferable graph r-cnn. Proc. AAAI Conf. Artif. Intell. 34(07), 12492\u201312499 (2020)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"1","key":"29_CR16","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2008","unstructured":"Scarselli, F., Gori, M., Tsoi, A.C., et al.: The graph neural network model. IEEE Trans. Neural Networks 20(1), 61\u201380 (2008)","journal-title":"IEEE Trans. Neural Networks"},{"unstructured":"Atwood, J., Towsley, D.: Diffusion-convolutional neural networks. In: Proceedings of NIPS, pp. 1993\u20132001 (2016)","key":"29_CR17"},{"doi-asserted-by":"crossref","unstructured":"Zhuang, C., Ma, Q.: Dual graph convolutional networks for graph based semi-supervised classification. In: WWW, pp. 499\u2013508 (2018)","key":"29_CR18","DOI":"10.1145\/3178876.3186116"},{"doi-asserted-by":"crossref","unstructured":"Monti, F., Boscaini, D., Masci, J., et al.: Geometric deep learning on graphs and manifolds using mixture model cnns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5115\u20135124 (2017)","key":"29_CR19","DOI":"10.1109\/CVPR.2017.576"},{"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)","key":"29_CR20","DOI":"10.1109\/CVPR.2018.00745"},{"doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., et al.: Up-detr: unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1601\u20131610 (2021)","key":"29_CR21","DOI":"10.1109\/CVPR46437.2021.00165"},{"unstructured":"Zhu, X., Su, W., Lu, L., et al.: Deformable detr: deformable transformers for end-to-end object detection (2020). arXiv preprint arXiv:2010.04159","key":"29_CR22"},{"doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., et al.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","key":"29_CR23","DOI":"10.1109\/ICCV.2019.00972"},{"doi-asserted-by":"crossref","unstructured":"Sun, Z., Cao, S., Yang, Y., et al.: Rethinking transformer-based set prediction for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3611\u20133620 (2021)","key":"29_CR24","DOI":"10.1109\/ICCV48922.2021.00359"},{"doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., 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)","key":"29_CR25","DOI":"10.1109\/CVPR46437.2021.01422"},{"doi-asserted-by":"crossref","unstructured":"Li, J., Cheng, B., Feris, R., et al.: Pseudo-IoU: improving label assignment in anchor-free object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2378\u20132387 (2021)","key":"29_CR26","DOI":"10.1109\/CVPRW53098.2021.00270"},{"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)","key":"29_CR27","DOI":"10.1109\/CVPR.2018.00644"},{"key":"29_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1007\/978-3-030-58558-7_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W Ma","year":"2020","unstructured":"Ma, W., Tian, T., Xu, H., Huang, Y., Li, Z.: Aabo: adaptive anchor box optimization for object detection via bayesian sub-sampling. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 560\u2013575. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_33"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wu, X., Zhu, R.: Adaptive word embedding module for semantic reasoning in large-scale detection. In: Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), pp. 2103\u20132109. IEEE (2021)","key":"29_CR29","DOI":"10.1109\/ICPR48806.2021.9412094"},{"doi-asserted-by":"crossref","unstructured":"Zhang, H., Fromont, E., Lef\u00e8vre, S., et al.: Localize to classify and classify to localize: mutual guidance in object detection. In: Proceedings of the Asian Conference on Computer Vision (2020)","key":"29_CR30","DOI":"10.1007\/978-3-030-69538-5_7"},{"key":"29_CR31","doi-asserted-by":"publisher","first-page":"2058","DOI":"10.1109\/TMM.2021.3075323","volume":"24","author":"S Wu","year":"2021","unstructured":"Wu, S., Xu, Y., Zhang, B., et al.: Deformable template network (dtn) for object detection. IEEE Trans. Multimedia 24, 2058\u20132068 (2021)","journal-title":"IEEE Trans. Multimedia"},{"doi-asserted-by":"crossref","unstructured":"Wang, K., Zhang, L.: Reconcile prediction consistency for balanced object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3631\u20133640 (2021)","key":"29_CR32","DOI":"10.1109\/ICCV48922.2021.00361"},{"issue":"1","key":"29_CR33","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18916-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T16:36:23Z","timestamp":1728232583000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18916-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189159","9783031189166"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18916-6_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","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":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.cn\/","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":"microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","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":"233","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":"41% - 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":"3.03","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":"3.35","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)"}}]}}