{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:33:05Z","timestamp":1743154385484,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031441943"},{"type":"electronic","value":"9783031441950"}],"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\/978-3-031-44195-0_11","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T12:04:08Z","timestamp":1695297848000},"page":"124-135","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LGF$$^2$$: Local and\u00a0Global Feature Fusion for\u00a0Text-Guided Object Detection"],"prefix":"10.1007","author":[{"given":"Shuyu","family":"Miao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hexiang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"11_CR1","first-page":"1","volume":"70","author":"Y Cai","year":"2021","unstructured":"Cai, Y., et al.: Yolov4-5d: an effective and efficient object detector for autonomous driving. IEEE Trans. Instrum. Meas. 70, 1\u201313 (2021)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"11_CR2","unstructured":"Chen, K., et al.: Mmdetection: Open mmlab detection toolbox and benchmark. arXiv (2019)"},{"key":"11_CR3","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.1109\/LSP.2020.3025128","volume":"27","author":"S Chen","year":"2020","unstructured":"Chen, S., Li, Z., Tang, Z.: Relation R-CNN: a graph based relation-aware network for object detection. IEEE Signal Process. Lett. 27, 1680\u20131684 (2020)","journal-title":"IEEE Signal Process. Lett."},{"key":"11_CR4","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":"11_CR5","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF International Conference On Computer Vision, pp. 6569\u20136578 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Fabbri, M., et al.: Motsynth: How can synthetic data help pedestrian detection and tracking? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10849\u201310859 (2021)","DOI":"10.1109\/ICCV48922.2021.01067"},{"key":"11_CR7","doi-asserted-by":"publisher","unstructured":"Feng, C., et al.: Promptdet: Towards open-vocabulary detection using uncurated images. In: Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part IX. pp. 701\u2013717. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_41","DOI":"10.1007\/978-3-031-20077-9_41"},{"issue":"3","key":"11_CR8","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":"11_CR9","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: CVPR, pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"11_CR11","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: CVPR, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"11_CR13","unstructured":"Jaeger, P.F., et al.: Retina u-net: Embarrassingly simple exploitation of segmentation supervision for medical object detection. In: Machine Learning for Health Workshop, pp. 171\u2013183. PMLR (2020)"},{"key":"11_CR14","doi-asserted-by":"publisher","first-page":"7389","DOI":"10.1109\/TIP.2020.3002345","volume":"29","author":"T Kong","year":"2020","unstructured":"Kong, T., Sun, F., Liu, H., Jiang, Y., Li, L., Shi, J.: Foveabox: beyound anchor-based object detection. IEEE Trans. Image Process. 29, 7389\u20137398 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"11_CR15","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":"11_CR16","doi-asserted-by":"crossref","unstructured":"Li, H., Miao, S., Feng, R.: Dg-fpn: Learning dynamic feature fusion based on graph convolution network for object detection. In: ICME, pp. 1\u20136 (2020)","DOI":"10.1109\/ICME46284.2020.9102838"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Li, L.H., et al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"11_CR18","doi-asserted-by":"publisher","first-page":"194228","DOI":"10.1109\/ACCESS.2020.3033289","volume":"8","author":"Y Li","year":"2020","unstructured":"Li, Y., et al.: A deep learning-based hybrid framework for object detection and recognition in autonomous driving. IEEE Access 8, 194228\u2013194239 (2020)","journal-title":"IEEE Access"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: ICCV, pp. 6054\u20136063 (2019)","DOI":"10.1109\/ICCV.2019.00615"},{"key":"11_CR20","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.neucom.2019.04.028","volume":"350","author":"Z Li","year":"2019","unstructured":"Li, Z., Dong, M., Wen, S., Hu, X., Zhou, P., Zeng, Z.: Clu-CNNs: object detection for medical images. Neurocomputing 350, 53\u201359 (2019)","journal-title":"Neurocomputing"},{"key":"11_CR21","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: CVPR, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"11_CR23","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":"11_CR24","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: D. 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":"11_CR25","doi-asserted-by":"crossref","unstructured":"Liu, W., Liao, S., Ren, W., Hu, W., Yu, Y.: High-level semantic feature detection: a new perspective for pedestrian detection. In: CVPR, pp. 5187\u20135196 (2019)","DOI":"10.1109\/CVPR.2019.00533"},{"key":"11_CR26","volume":"65","author":"M Loey","year":"2021","unstructured":"Loey, M., Manogaran, G., Taha, M.H.N., Khalifa, N.E.M.: Fighting against Covid-19: a novel deep learning model based on yolo-v2 with Resnet-50 for medical face mask detection. Sustain. Urban Areas 65, 102600 (2021)","journal-title":"Sustain. Urban Areas"},{"key":"11_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108258","volume":"122","author":"S Miao","year":"2022","unstructured":"Miao, S., et al.: Balanced single-shot object detection using cross-context attention-guided network. Pattern Recogn. 122, 108258 (2022)","journal-title":"Pattern Recogn."},{"key":"11_CR28","unstructured":"Miao, S., Feng, R., Zhang, Y., Fan, W.: Learning class-based graph representation for object detection. In: AAAI, pp. 2752\u20132759 (2020)"},{"key":"11_CR29","doi-asserted-by":"publisher","unstructured":"Miao, S., Zheng, L., Jin, H., Feng, R.: Dynamically connected graph representation for object detection. In: International Conference on Neural Information Processing, pp. 347\u2013358. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-30111-7_30","DOI":"10.1007\/978-3-031-30111-7_30"},{"key":"11_CR30","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"11_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. Arxiv (2015)"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Singh, B., Davis, L.S.: An analysis of scale invariance in object detection snip. In: CVPR, pp. 3578\u20133587 (2018)","DOI":"10.1109\/CVPR.2018.00377"},{"key":"11_CR34","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":"11_CR35","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"11_CR37","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"issue":"9","key":"11_CR38","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, P., Ni, B., Geng, C., Hu, J., Xu, Y.: Scale-transferrable object detection. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 528\u2013537 (2018)","DOI":"10.1109\/CVPR.2018.00062"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhuo, J., Krahenbuhl, P.: Bottom-up object detection by grouping extreme and center points. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 850\u2013859 (2019)","DOI":"10.1109\/CVPR.2019.00094"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. In: Proceedings of the IEEE\/CVF Conference On Computer Vision and Pattern Recognition, pp. 840\u2013849 (2019)","DOI":"10.1109\/CVPR.2019.00093"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44195-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T12:05:49Z","timestamp":1695297949000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44195-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031441943","9783031441950"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44195-0_11","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":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","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":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"4","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)"}},{"value":"type of other papers accepted  : 9 Abstract","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)"}}]}}