{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T01:53:02Z","timestamp":1768096382629,"version":"3.49.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,3,16]],"date-time":"2024-03-16T00:00:00Z","timestamp":1710547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,16]],"date-time":"2024-03-16T00:00:00Z","timestamp":1710547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 62273248"],"award-info":[{"award-number":["No. 62273248"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Computer Vision Joint Training Demonstration Base of Taiyuan University of Science and Technology","award":["JD2022005"],"award-info":[{"award-number":["JD2022005"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-18865-x","type":"journal-article","created":{"date-parts":[[2024,3,16]],"date-time":"2024-03-16T05:02:16Z","timestamp":1710565336000},"page":"4093-4113","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Context feature fusion and enhanced non-maximum suppression for pedestrian detection in crowded scenes"],"prefix":"10.1007","volume":"84","author":[{"given":"Yu","family":"Shao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2212-7187","authenticated-orcid":false,"given":"Lihua","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jifu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinbo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,16]]},"reference":[{"key":"18865_CR1","doi-asserted-by":"crossref","unstructured":"Alfred\u00a0Daniel J, Chandru\u00a0Vignesh C, Muthu BA et\u00a0al (2023) Fully convolutional neural networks for lidar\u2013camera fusion for pedestrian detection in autonomous vehicle. Multimedia Tools and Applications pp 1\u201324","DOI":"10.1007\/s11042-023-14417-x"},{"key":"18865_CR2","doi-asserted-by":"publisher","first-page":"8759","DOI":"10.1007\/s11042-020-10103-4","volume":"80","author":"MA Ansari","year":"2021","unstructured":"Ansari MA, Singh DK (2021) Human detection techniques for real time surveillance: a comprehensive survey. Multimed Tools Appl 80:8759\u20138808","journal-title":"Multimed Tools Appl"},{"key":"18865_CR3","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv:2004.10934"},{"key":"18865_CR4","doi-asserted-by":"crossref","unstructured":"Bodla N, Singh B, Chellappa R, et\u00a0al (2017) Soft-nms\u2013improving object detection with one line of code. In: Proceedings of the IEEE international conference on computer vision, pp 5561\u20135569","DOI":"10.1109\/ICCV.2017.593"},{"key":"18865_CR5","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade r-cnn: Delving into high quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"18865_CR6","unstructured":"Cao J, Chen Q, Guo J et\u00a0al (2020) Attention-guided context feature pyramid network for object detection. arXiv:2005.11475"},{"key":"18865_CR7","doi-asserted-by":"crossref","unstructured":"Chi C, Zhang S, Xing J et\u00a0al (2020) Relational learning for joint head and human detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 10647\u201310654","DOI":"10.1609\/aaai.v34i07.6691"},{"key":"18865_CR8","doi-asserted-by":"crossref","unstructured":"Chu X, Zheng A, Zhang X et\u00a0al (2020) Detection in crowded scenes: one proposal, multiple predictions. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12214\u201312223","DOI":"10.1109\/CVPR42600.2020.01223"},{"key":"18865_CR9","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), Ieee, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"issue":"4","key":"18865_CR10","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 et al (2011) Pedestrian detection: an evaluation of the state of the art. IEEE Trans Pattern Anal Mach Intell 34(4):743\u2013761","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"18865_CR11","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L et\u00a0al (2019) Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6569\u20136578","DOI":"10.1109\/ICCV.2019.00667"},{"key":"18865_CR12","unstructured":"Ge Z, Liu S, Wang F et\u00a0al (2021) Yolox: exceeding yolo series in 2021. arXiv:2107.08430"},{"key":"18865_CR13","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"18865_CR14","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T et\u00a0al (2014) 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","DOI":"10.1109\/CVPR.2014.81"},{"key":"18865_CR15","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et\u00a0al (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":"18865_CR16","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P et\u00a0al (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"18865_CR17","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L et\u00a0al (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"18865_CR18","doi-asserted-by":"crossref","unstructured":"Huang X, Ge Z, Jie Z et\u00a0al (2020) 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","DOI":"10.1109\/CVPR42600.2020.01076"},{"key":"18865_CR19","doi-asserted-by":"crossref","unstructured":"Jiang B, Luo R, Mao J et\u00a0al (2018) Acquisition of localization confidence for accurate object detection. In: Proceedings of the European conference on computer vision (ECCV), pp 784\u2013799","DOI":"10.1007\/978-3-030-01264-9_48"},{"issue":"27","key":"18865_CR20","doi-asserted-by":"publisher","first-page":"39275","DOI":"10.1007\/s11042-022-13026-4","volume":"81","author":"R Lahmyed","year":"2022","unstructured":"Lahmyed R, El Ansari M, Kerkaou Z (2022) A novel visible spectrum images-based pedestrian detection and tracking system for surveillance in non-controlled environments. Multimed Tools Appl 81(27):39275\u201339309","journal-title":"Multimed Tools Appl"},{"key":"18865_CR21","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"18865_CR22","doi-asserted-by":"crossref","unstructured":"Li X, Wang W, Hu X et\u00a0al (2019) Selective kernel networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 510\u2013519","DOI":"10.1109\/CVPR.2019.00060"},{"issue":"2","key":"18865_CR23","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TPAMI.2022.3164083","volume":"45","author":"Y Li","year":"2022","unstructured":"Li Y, Yao T, Pan Y et al (2022) Contextual transformer networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 45(2):1489\u20131500","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"18865_CR24","unstructured":"Lienhart R, Maydt J (2002) An extended set of haar-like features for rapid object detection. In: Proceedings. international conference on image processing, IEEE, pp I\u2013I"},{"key":"18865_CR25","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R et\u00a0al (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"18865_CR26","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R et\u00a0al (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"18865_CR27","doi-asserted-by":"crossref","unstructured":"Liu S, Huang D, Wang Y (2019) Adaptive nms: refining pedestrian detection in a crowd. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6459\u20136468","DOI":"10.1109\/CVPR.2019.00662"},{"key":"18865_CR28","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D et\u00a0al (2016) Ssd: single shot multibox detector. In: Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"18865_CR29","doi-asserted-by":"crossref","unstructured":"Lowe DG (1999) Object recognition from local scale-invariant features. In: Proceedings of the seventh IEEE international conference on computer vision, Ieee, pp 1150\u20131157","DOI":"10.1109\/ICCV.1999.790410"},{"key":"18865_CR30","doi-asserted-by":"crossref","unstructured":"Neubeck A, Van\u00a0Gool L (2006) Efficient non-maximum suppression. In: 18th international conference on pattern recognition (ICPR\u201906), IEEE, pp 850\u2013855","DOI":"10.1109\/ICPR.2006.479"},{"issue":"7","key":"18865_CR31","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971\u2013987","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"18865_CR32","unstructured":"Ren S, He K, Girshick R et\u00a0al (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inf Process 28"},{"key":"18865_CR33","doi-asserted-by":"crossref","unstructured":"Rukhovich D, Sofiiuk K, Galeev D et\u00a0al (2021) Iterdet: iterative scheme for object detection in crowded environments. In: Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshops, S+ SSPR 2020, Padua, Italy, January 21\u201322, 2021, Proceedings, Springer, pp 344\u2013354","DOI":"10.1007\/978-3-030-73973-7_33"},{"key":"18865_CR34","unstructured":"Shang M, Xiang D, Wang Z et\u00a0al (2021) V2f-net: explicit decomposition of occluded pedestrian detection. arXiv:2104.03106"},{"key":"18865_CR35","unstructured":"Shao S, Zhao Z, Li B et\u00a0al (2018) Crowdhuman: a benchmark for detecting human in a crowd. arXiv:1805.00123"},{"key":"18865_CR36","doi-asserted-by":"crossref","unstructured":"Shao X, Wang Q, Yang W et\u00a0al (2021) Multi-scale feature pyramid network: a heavily occluded pedestrian detection network based on resnet. Sensors 21(5):1820","DOI":"10.3390\/s21051820"},{"key":"18865_CR37","doi-asserted-by":"crossref","unstructured":"Tian Y, Luo P, Wang X et\u00a0al (2015) Deep learning strong parts for pedestrian detection. In: Proceedings of the IEEE international conference on computer vision, pp 1904\u20131912","DOI":"10.1109\/ICCV.2015.221"},{"key":"18865_CR38","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H et\u00a0al (2019) Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"18865_CR39","doi-asserted-by":"crossref","unstructured":"Wang CY, Bochkovskiy A, Liao HYM (2023) Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"18865_CR40","doi-asserted-by":"crossref","unstructured":"Wang J, Song L, Li Z et\u00a0al (2021) End-to-end object detection with fully convolutional network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15849\u201315858","DOI":"10.1109\/CVPR46437.2021.01559"},{"key":"18865_CR41","doi-asserted-by":"crossref","unstructured":"Wang X, Xiao T, Jiang Y et\u00a0al (2018) Repulsion loss: detecting pedestrians in a crowd. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7774\u20137783","DOI":"10.1109\/CVPR.2018.00811"},{"key":"18865_CR42","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122"},{"key":"18865_CR43","doi-asserted-by":"crossref","unstructured":"Zheng Z, Wang P, Liu W et\u00a0al (2020) Distance-iou loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI conference on artificial intelligence, pp 12993\u201313000","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"18865_CR44","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.patcog.2018.08.018","volume":"86","author":"C Zhou","year":"2019","unstructured":"Zhou C, Yuan J (2019) Multi-label learning of part detectors for occluded pedestrian detection. Pattern Recognit 86:99\u2013111","journal-title":"Pattern Recognit"},{"key":"18865_CR45","doi-asserted-by":"crossref","unstructured":"Zhou P, Zhou C, Peng P et\u00a0al (2020) Noh-nms: improving pedestrian detection by nearby objects hallucination. In: Proceedings of the 28th ACM International Conference on Multimedia, pp 1967\u20131975","DOI":"10.1145\/3394171.3413617"},{"key":"18865_CR46","doi-asserted-by":"crossref","unstructured":"Zou M, Yu J, Lu B et\u00a0al (2022) Active pedestrian detection for excavator robots based on multi-sensor fusion. In: 2022 IEEE International Conference on Real-time Computing and Robotics (RCAR), IEEE, pp 255\u2013260","DOI":"10.1109\/RCAR54675.2022.9872286"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18865-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-18865-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18865-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T00:17:30Z","timestamp":1742689050000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-18865-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,16]]},"references-count":46,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["18865"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-18865-x","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,16]]},"assertion":[{"value":"30 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 February 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2024","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 declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}