{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T13:39:47Z","timestamp":1762090787915,"version":"build-2065373602"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T00:00:00Z","timestamp":1693440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T00:00:00Z","timestamp":1693440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272035"],"award-info":[{"award-number":["62272035"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16574-5","type":"journal-article","created":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T09:02:23Z","timestamp":1693472543000},"page":"28057-28075","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Interactive guidance network for object detection based on radar-camera fusion"],"prefix":"10.1007","volume":"83","author":[{"given":"Jiapeng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linhua","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongxia","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zisen","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,31]]},"reference":[{"issue":"7","key":"16574_CR1","doi-asserted-by":"publisher","first-page":"2542","DOI":"10.3390\/s22072542","volume":"22","author":"Z Wei","year":"2022","unstructured":"Wei Z, Zhang F, Chang S, Liu Y, Wu H, Feng Z (2022) Mmwave radar and vision fusion for object detection in autonomous driving: a review. Sensors 22(7):2542","journal-title":"Sensors"},{"key":"16574_CR2","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905), vol 1, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"16574_CR3","doi-asserted-by":"crossref","unstructured":"Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: 2008 IEEE conference on computer vision and pattern recognition, pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"16574_CR4","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"16574_CR5","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28"},{"key":"16574_CR6","unstructured":"Michaelis C, Mitzkus B, Geirhos R, Rusak E, Bringmann O, Ecker AS, Bethge M, Brendel W (2019) Benchmarking robustness in object detection: Autonomous driving when winter is coming. arXiv preprint arXiv:1907.07484"},{"key":"16574_CR7","doi-asserted-by":"publisher","first-page":"2847","DOI":"10.1109\/ACCESS.2019.2962554","volume":"8","author":"Z Wang","year":"2019","unstructured":"Wang Z, Wu Y, Niu Q (2019) Multi-sensor fusion in automated driving: A survey. Ieee Access 8:2847\u20132868","journal-title":"Ieee Access"},{"key":"16574_CR8","doi-asserted-by":"crossref","unstructured":"Cho M-g (2019) A study on the obstacle recognition for autonomous driving rc car using lidar and thermal infrared camera. In: 2019 Eleventh international conference on ubiquitous and future networks (ICUFN), pp 544\u2013546","DOI":"10.1109\/ICUFN.2019.8806152"},{"issue":"2","key":"16574_CR9","first-page":"1","volume":"3","author":"R Zhang","year":"2018","unstructured":"Zhang R, Cao S (2018) Real-time human motion behavior detection via cnn using mmwave radar. IEEE Sensors Letters 3(2):1\u20134","journal-title":"IEEE Sensors Letters"},{"key":"16574_CR10","doi-asserted-by":"crossref","unstructured":"Yoneda K, Hashimoto N, Yanase R, Aldibaja M, Suganuma N (2018) Vehicle localization using 76ghz omnidirectional millimeter-wave radar for winter automated driving. In: 2018 IEEE intelligent vehicles symposium (IV), pp 971\u2013977","DOI":"10.1109\/IVS.2018.8500378"},{"issue":"7","key":"16574_CR11","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1109\/TITS.2016.2533542","volume":"17","author":"X Wang","year":"2016","unstructured":"Wang X, Xu L, Sun H, Xin J, Zheng N (2016) On-road vehicle detection and tracking using mmw radar and monovision fusion. IEEE Trans Intell Transp Syst 17(7):2075\u20132084","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"16574_CR12","doi-asserted-by":"crossref","unstructured":"Wang X, Xu L, Sun H, Xin J, Zheng N (2014) Bionic vision inspired on-road obstacle detection and tracking using radar and visual information. In: 17th International IEEE conference on intelligent transportation systems (ITSC), pp 39\u201344","DOI":"10.1109\/ITSC.2014.6957663"},{"key":"16574_CR13","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1016\/j.robot.2016.05.001","volume":"83","author":"J \u0106esi\u0107","year":"2016","unstructured":"\u0106esi\u0107 J, Markovi\u0107 I, Cvi\u0161i\u0107 I, Petrovi\u0107 I (2016) Radar and stereo vision fusion for multitarget tracking on the special euclidean group. Robot Auton Syst 83:338\u2013348","journal-title":"Robot Auton Syst"},{"key":"16574_CR14","first-page":"258","volume":"17","author":"Z Zhong","year":"2018","unstructured":"Zhong Z, Liu S, Mathew M (2018) Dubey A (2018) Camera radar fusion for increased reliability in adas applications. Electronic Imaging 17:258\u20131","journal-title":"Electronic Imaging"},{"key":"16574_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2019.04.002","volume":"184","author":"V Lekic","year":"2019","unstructured":"Lekic V, Babic Z (2019) Automotive radar and camera fusion using generative adversarial networks. Comput Vis Image Underst 184:1\u20138","journal-title":"Comput Vis Image Underst"},{"key":"16574_CR16","doi-asserted-by":"crossref","unstructured":"Obrvan M, \u0106esi\u0107 J, Petrovi\u0107 I (2016) Appearance based vehicle detection by radar-stereo vision integration. In: Robot 2015: second Iberian robotics conference: advances in robotics, vol 1, pp 437\u2013449","DOI":"10.1007\/978-3-319-27146-0_34"},{"key":"16574_CR17","doi-asserted-by":"crossref","unstructured":"Chadwick S, Maddern W, Newman P (2019) Distant vehicle detection using radar and vision. In: 2019 International conference on robotics and automation (ICRA), pp 8311\u20138317","DOI":"10.1109\/ICRA.2019.8794312"},{"issue":"4","key":"16574_CR18","doi-asserted-by":"publisher","first-page":"956","DOI":"10.3390\/s20040956","volume":"20","author":"S Chang","year":"2020","unstructured":"Chang S, Zhang Y, Zhang F, Zhao X, Huang S, Feng Z, Wei Z (2020) Spatial attention fusion for obstacle detection using mmwave radar and vision sensor. Sensors 20(4):956","journal-title":"Sensors"},{"key":"16574_CR19","doi-asserted-by":"crossref","unstructured":"Caesar H, Bankiti V, Lang AH, Vora S, Liong VE, Xu Q, Krishnan A, Pan Y, Baldan G, Beijbom O (2020) nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11621\u201311631","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"16574_CR20","doi-asserted-by":"crossref","unstructured":"Nabati R, Qi H (2019) Rrpn: radar region proposal network for object detection in autonomous vehicles. In: 2019 IEEE international conference on image processing (ICIP), pp 3093\u20133097","DOI":"10.1109\/ICIP.2019.8803392"},{"key":"16574_CR21","unstructured":"Meyer M, Kuschk G (2019) Deep learning based 3d object detection for automotive radar and camera. In: 2019 16th European radar conference (EuRAD), pp 133\u2013136"},{"key":"16574_CR22","doi-asserted-by":"crossref","unstructured":"Dong X, Zhuang B, Mao Y, Liu L (2021) Radar camera fusion via representation learning in autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1672\u20131681","DOI":"10.1109\/CVPRW53098.2021.00183"},{"key":"16574_CR23","doi-asserted-by":"crossref","unstructured":"John V, Mita S (2019) Rvnet: deep sensor fusion of monocular camera and radar for image-based obstacle detection in challenging environments. In: Pacific-rim symposium on image and video technology, pp 351\u2013364","DOI":"10.1007\/978-3-030-34879-3_27"},{"key":"16574_CR24","doi-asserted-by":"crossref","unstructured":"Nobis F, Geisslinger M, Weber M, Betz J, Lienkamp M (2019) A deep learning-based radar and camera sensor fusion architecture for object detection. In: 2019 Sensor data fusion: trends. Solutions, applications (SDF), pp 1\u20137","DOI":"10.1109\/SDF.2019.8916629"},{"key":"16574_CR25","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"16574_CR26","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"16574_CR27","doi-asserted-by":"crossref","unstructured":"Yang Z, Zhu L, Wu Y, Yang Y (2020) Gated channel transformation for visual recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11794\u201311803","DOI":"10.1109\/CVPR42600.2020.01181"},{"key":"16574_CR28","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS (2018) Cbam: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"16574_CR29","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang X, Huang L, Huang C, Wei Y, Liu W (2019) Ccnet: criss-cross attention for semantic segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 603\u2013612","DOI":"10.1109\/ICCV.2019.00069"},{"key":"16574_CR30","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, Lu H (2019) Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"},{"key":"16574_CR31","doi-asserted-by":"crossref","unstructured":"Xu G, Zhou W, Qian X, Ye L, Lei J, Yu L (2023) Ccfnet: cross-complementary fusion network for rgb-d scene parsing of clothing images. J Vis Commun Image Represent 90:103727","DOI":"10.1016\/j.jvcir.2022.103727"},{"key":"16574_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2020.102762","volume":"73","author":"B Sun","year":"2020","unstructured":"Sun B, Yao Z, Zhang Y, Yu L (2020) Local relation network with multilevel attention for visual question answering. J Vis Commun Image Represent 73:102762","journal-title":"J Vis Commun Image Represent"},{"key":"16574_CR33","doi-asserted-by":"publisher","first-page":"7216","DOI":"10.1609\/aaai.v33i01.33017216","volume":"33","author":"Y Wang","year":"2019","unstructured":"Wang Y, Shen Y, Liu Z, Liang PP, Zadeh A, Morency L-P (2019) Words can shift: Dynamically adjusting word representations using nonverbal behaviors. Proceedings of the AAAI Conference on Artificial Intelligence 33:7216\u20137223","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"16574_CR34","doi-asserted-by":"crossref","unstructured":"Wei X, Zhang T, Li Y, Zhang Y, Wu F (2020) Multi-modality cross attention network for image and sentence matching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10941\u201310950","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"16574_CR35","doi-asserted-by":"crossref","unstructured":"Song X, Guo H, Xu X, Chao H, Xu S, Turkbey B, Wood BJ, Wang G, Yan P (2021) Cross-modal attention for mri and ultrasound volume registration. In: International conference on medical image computing and computer-assisted intervention, pp 66\u201375","DOI":"10.1007\/978-3-030-87202-1_7"},{"key":"16574_CR36","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"16574_CR37","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"16574_CR38","unstructured":"Nabati R, Qi H (2020) Radar-camera sensor fusion for joint object detection and distance estimation in autonomous vehicles. arXiv preprint arXiv:2009.08428"},{"key":"16574_CR39","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"16574_CR40","unstructured":"Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W, Li Y, Zhang B, Liang Y, Zhou L, Xu X, Chu X, Wei X, Wei X (2022) Yolov6: a single-stage object detection framework for industrial applications. arXiv:2209.02976"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16574-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16574-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16574-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T10:48:43Z","timestamp":1709203723000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16574-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,31]]},"references-count":40,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["16574"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16574-5","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,8,31]]},"assertion":[{"value":"27 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 July 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}