{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:34:18Z","timestamp":1763202858126,"version":"build-2065373602"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T00:00:00Z","timestamp":1717718400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T00:00:00Z","timestamp":1717718400000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s00530-024-01378-w","type":"journal-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T17:01:54Z","timestamp":1717779714000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A feature pyramid network with adaptive fusion strategy and enhanced semantic information"],"prefix":"10.1007","volume":"30","author":[{"given":"Longfei","family":"Qin","sequence":"first","affiliation":[]},{"given":"Wenchao","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Dexin","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"1378_CR1","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/978-3-031-19812-0_31","volume-title":"Computer Vision - ECCV 2022","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: Petr: Position embedding transformation for\u00c2 multi-view 3d object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, pp. 531\u2013548. Springer Nature Switzerland, Cham (2022)"},{"key":"1378_CR2","doi-asserted-by":"crossref","unstructured":"Feng, Z., Guo, S., Tan, X., Xu, K., Wang, M., Ma, L.: Rethinking efficient lane detection via curve modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17062\u201317070 (2022)","DOI":"10.1109\/CVPR52688.2022.01655"},{"key":"1378_CR3","unstructured":"Shi, Y., Jiang, K., Li, J., Wen, J., Qian, Z., Yang, M., Wang, K., Yang, D.: Grid-centric traffic scenario perception for autonomous driving: A comprehensive review. arXiv preprint arXiv:2303.01212 (2023)"},{"key":"1378_CR4","unstructured":"Wang, T., Xinge, Z., Pang, J., Lin, D.: Probabilistic and geometric depth: Detecting objects in perspective. In: Conference on Robot Learning, pp. 1475\u20131485. PMLR (2022)"},{"key":"1378_CR5","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: Fcos3d: Fully convolutional one-stage monocular 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 913\u2013922 (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"1378_CR6","doi-asserted-by":"crossref","unstructured":"Huang, Y., Chen, J., Huang, D.: Ufpmp-det: Toward accurate and efficient object detection on drone imagery. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 1026\u20131033 (2022)","DOI":"10.1609\/aaai.v36i1.19986"},{"key":"1378_CR7","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Doll\u00c3\u00a1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"1378_CR8","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)"},{"key":"1378_CR9","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":"1378_CR10","doi-asserted-by":"publisher","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00913","DOI":"10.1109\/CVPR.2018.00913"},{"key":"1378_CR11","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra r-cnn: Towards balanced learning for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 821\u2013830 (2019)","DOI":"10.1109\/CVPR.2019.00091"},{"key":"1378_CR12","doi-asserted-by":"crossref","unstructured":"Guo, C., Fan, B., Zhang, Q., Xiang, S., Pan, C.: Augfpn: Improving multi-scale feature learning for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 12595\u201312604 (2020)","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"1378_CR13","doi-asserted-by":"crossref","unstructured":"Yang, G., Lei, J., Zhu, Z., Cheng, S., Feng, Z., Liang, R.: Afpn: asymptotic feature pyramid network for object detection. In: 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2184\u20132189. IEEE (2023)","DOI":"10.1109\/SMC53992.2023.10394415"},{"key":"1378_CR14","doi-asserted-by":"crossref","unstructured":"Chang, J., Dai, H., Zheng, Y.: Cag-fpn: Channel self-attention guided feature pyramid network for object detection. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 9616\u20139620. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10448037"},{"issue":"21","key":"1378_CR15","doi-asserted-by":"publisher","first-page":"30685","DOI":"10.1007\/s11042-022-11940-1","volume":"81","author":"Y Luo","year":"2022","unstructured":"Luo, Y., Cao, X., Zhang, J., Guo, J., Shen, H., Wang, T., Feng, Q.: Ce-fpn: Enhancing channel information for object detection. Multimedia Tools and Applications 81(21), 30685\u201330704 (2022)","journal-title":"Multimedia Tools and Applications"},{"key":"1378_CR16","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision - ECCV 2014","author":"TY 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.) Computer Vision - ECCV 2014, pp. 740\u2013755. Springer International Publishing, Cham (2014)"},{"key":"1378_CR17","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":"1378_CR18","unstructured":"Benjumea, A., Teeti, I., Cuzzolin, F., Bradley, A.: Yolo-z: Improving small object detection in yolov5 for autonomous vehicles. arXiv preprint arXiv:2112.11798 (2021)"},{"key":"1378_CR19","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"1378_CR20","unstructured":"Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., Kwon, Y., Michael, K., Fang, J., Yifu, Z., Wong, C., Montes, D., et\u00a0al.: ultralytics\/yolov5: v7. 0-yolov5 sota realtime instance segmentation. Zenodo (2022)"},{"key":"1378_CR21","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"1378_CR22","unstructured":"Wang, C.Y., Yeh, I.H., Liao, H.Y.M.: You only learn one representation: Unified network for multiple tasks. arXiv preprint arXiv:2105.04206 (2021)"},{"issue":"6","key":"1378_CR23","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1007\/s11633-022-1339-y","volume":"19","author":"D Wu","year":"2022","unstructured":"Wu, D., Liao, M.W., Zhang, W.T., Wang, X.G., Bai, X., Cheng, W.Q., Liu, W.Y.: Yolop: You only look once for panoptic driving perception. Machine Intelligence Research 19(6), 550\u2013562 (2022)","journal-title":"Machine Intelligence Research"},{"key":"1378_CR24","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":"1378_CR25","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":"1378_CR26","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":"1378_CR27","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":"1378_CR28","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":"1378_CR29","doi-asserted-by":"publisher","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: Delving into high quality object detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00644","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1378_CR30","unstructured":"Chang, H., Yeung, D.Y., Xiong, Y.: Super-resolution through neighbor embedding. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., vol.\u00a01, pp. I\u2013I. IEEE (2004)"},{"issue":"7","key":"1378_CR31","doi-asserted-by":"publisher","first-page":"3194","DOI":"10.1109\/TIP.2012.2190080","volume":"21","author":"X Gao","year":"2012","unstructured":"Gao, X., Zhang, K., Tao, D., Li, X.: Image super-resolution with sparse neighbor embedding. IEEE Trans. Image Process. 21(7), 3194\u20133205 (2012)","journal-title":"IEEE Trans. Image Process."},{"key":"1378_CR32","doi-asserted-by":"crossref","unstructured":"Hu, X., Mu, H., Zhang, X., Wang, Z., Tan, T., Sun, J.M.S.: A magnification-arbitrary network for super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, pp. 15\u201320 (2019)","DOI":"10.1109\/CVPR.2019.00167"},{"key":"1378_CR33","doi-asserted-by":"crossref","unstructured":"Park, S., Yoo, J., Cho, D., Kim, J., Kim, T.H.: Fast adaptation to super-resolution networks via meta-learning. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXVII 16, pp. 754\u2013769. Springer (2020)","DOI":"10.1007\/978-3-030-58583-9_45"},{"key":"1378_CR34","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Husz\u00e1r, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et\u00a0al.: Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4681\u20134690 (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"1378_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Y., Change\u00a0Loy, C.: Esrgan: Enhanced super-resolution generative adversarial networks. In: Proceedings of the European conference on computer vision (ECCV) workshops, pp. 0\u20130 (2018)","DOI":"10.1007\/978-3-030-11021-5_5"},{"key":"1378_CR36","doi-asserted-by":"crossref","unstructured":"Shi, W., Caballero, J., Husz\u00e1r, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., Wang, Z.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"1378_CR37","doi-asserted-by":"crossref","unstructured":"Qiao, S., Chen, L.C., Yuille, A.: Detectors: Detecting objects with recursive feature pyramid and switchable atrous convolution. arxiv 2020. arXiv preprint arXiv:2006.02334 (2020)","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"1378_CR38","doi-asserted-by":"crossref","unstructured":"Xu, H., Yao, L., Zhang, W., Liang, X., Li, Z.: Auto-fpn: Automatic network architecture adaptation for object detection beyond classification. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 6649\u20136658 (2019)","DOI":"10.1109\/ICCV.2019.00675"},{"key":"1378_CR39","doi-asserted-by":"crossref","unstructured":"Wang, N., Gao, Y., Chen, H., Wang, P., Tian, Z., Shen, C., Zhang, Y.: Nas-fcos: Fast neural architecture search for object detection. In: proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11943\u201311951 (2020)","DOI":"10.1109\/CVPR42600.2020.01196"},{"key":"1378_CR40","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"1378_CR41","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":"1378_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, K., Xu, R., Liu, Z., Loy, C.C., Lin, D.: Carafe: Content-aware reassembly of features. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 3007\u20133016 (2019)","DOI":"10.1109\/ICCV.2019.00310"},{"key":"1378_CR43","doi-asserted-by":"publisher","first-page":"2593","DOI":"10.1109\/TIP.2023.3270801","volume":"32","author":"H Zhou","year":"2023","unstructured":"Zhou, H., Tian, C., Zhang, Z., Li, C., Ding, Y., Xie, Y., Li, Z.: Position-aware relation learning for rgb-thermal salient object detection. IEEE Trans. Image Process. 32, 2593\u20132607 (2023). https:\/\/doi.org\/10.1109\/TIP.2023.3270801","journal-title":"IEEE Trans. Image Process."},{"key":"1378_CR44","doi-asserted-by":"publisher","unstructured":"Zhou, H., Tian, C., Zhang, Z., Li, C., Xie, Y., Li, Z.: Frequency-aware feature aggregation network with dual-task consistency for rgb-t salient object detection. Pattern Recognition 146, 110043 (2024) https:\/\/doi.org\/10.1016\/j.patcog.2023.110043. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320323007409","DOI":"10.1016\/j.patcog.2023.110043"},{"key":"1378_CR45","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":"1378_CR46","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1378_CR47","unstructured":"Ma, J., Chen, B.: Dual refinement feature pyramid networks for object detection. arXiv preprint arXiv:2012.01733 (2020)"},{"key":"1378_CR48","doi-asserted-by":"crossref","unstructured":"Li, C., Zhou, H., Liu, Y., Yang, C., Xie, Y., Li, Z., Zhu, L.: Detection-friendly dehazing: Object detection in real-world hazy scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)","DOI":"10.1109\/TPAMI.2023.3234976"},{"key":"1378_CR49","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01378-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01378-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01378-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T08:13:48Z","timestamp":1724314428000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01378-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,7]]},"references-count":49,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["1378"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01378-w","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2024,6,7]]},"assertion":[{"value":"12 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 June 2024","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"171"}}