{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:07:02Z","timestamp":1767182822634},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2022,2,20]],"date-time":"2022-02-20T00:00:00Z","timestamp":1645315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,2,20]],"date-time":"2022-02-20T00:00:00Z","timestamp":1645315200000},"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":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s00521-022-06938-7","type":"journal-article","created":{"date-parts":[[2022,2,20]],"date-time":"2022-02-20T11:11:20Z","timestamp":1645355480000},"page":"10097-10108","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["PointDet++: an object detection framework based on human local features with transformer encoder"],"prefix":"10.1007","volume":"35","author":[{"given":"Yudi","family":"Tang","sequence":"first","affiliation":[]},{"given":"Bing","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wangli","family":"He","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Qian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,20]]},"reference":[{"key":"6938_CR1","unstructured":"Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning. PMLR, pp 6105\u20136114"},{"key":"6938_CR2","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":"6938_CR3","doi-asserted-by":"crossref","unstructured":"Tang Y, Wang B, He W, Qian F (2021) Pointdet: an object detection framework based on human local features in the task of identifying violations. In: 2021 11th international conference on information science and technology (ICIST). IEEE, pp 673\u2013680","DOI":"10.1109\/ICIST52614.2021.9440553"},{"key":"6938_CR4","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907"},{"key":"6938_CR5","doi-asserted-by":"crossref","unstructured":"Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: a benchmark. In: Proceedings of the IEEE international conference on computer vision, pp 1116\u20131124","DOI":"10.1109\/ICCV.2015.133"},{"key":"6938_CR6","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"6938_CR7","unstructured":"Han K, Xiao A, Wu E, Guo J, Xu C, Wang Y (2021) Transformer in transformer. arXiv preprint arXiv:2103.00112"},{"key":"6938_CR8","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934"},{"key":"6938_CR9","unstructured":"(Format ) Dosovitskiy A, Beyer L, Kolesnikov A et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"6938_CR10","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"6938_CR11","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L, Weinberger KQ (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":"6938_CR12","doi-asserted-by":"crossref","unstructured":"Huang R, Pedoeem J, Chen C (2018) Yolo-lite: a real-time object detection algorithm optimized for non-gpu computers. In: 2018 I33EEE international conference on big data (Big Data). IEEE, pp 2503\u20132510","DOI":"10.1109\/BigData.2018.8621865"},{"key":"6938_CR13","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"6938_CR14","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (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":"6938_CR15","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (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":"6938_CR16","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (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":"6938_CR17","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"6938_CR18","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":"6938_CR19","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (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":"6938_CR20","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":"6938_CR21","doi-asserted-by":"crossref","unstructured":"Pang J, Chen K, Shi J, Feng H, Ouyang W, Lin D (2019) 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","DOI":"10.1109\/CVPR.2019.00091"},{"key":"6938_CR22","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"},{"issue":"6","key":"6938_CR23","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren S, He K, Girshick R, Sun J (2016) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6938_CR24","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"6938_CR25","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: European conference on computer vision. Springer, pp 483\u2013499","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"6938_CR26","doi-asserted-by":"crossref","unstructured":"Park H, Ham B (2020) Relation network for person re-identification. In: Proceedings of the AAAI conference on artificial intelligence, vol \u00a034, no \u00a007, pp 11839\u201311847","DOI":"10.1609\/aaai.v34i07.6857"},{"key":"6938_CR27","doi-asserted-by":"crossref","unstructured":"Wang G, Yang S, Liu H, Wang Z, Yang Y, Wang S, Yu G, Zhou E, Sun J (2020) High-order information matters: learning relation and topology for occluded person re-identification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6449\u20136458","DOI":"10.1109\/CVPR42600.2020.00648"},{"key":"6938_CR28","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European conference on computer vision. Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"6938_CR29","unstructured":"Chen M, Radford A, Child R, Wu J, Jun H, Luan D, Sutskever I (2020) Generative pretraining from pixels. In: International conference on machine learning. PMLR, pp 1691\u20131703"},{"key":"6938_CR30","doi-asserted-by":"crossref","unstructured":"Nagrani A, Sun C, Ross D, Sukthankar R, Schmid C, Zisserman A (2020) Speech2action: cross-modal supervision for action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10317\u201310326","DOI":"10.1109\/CVPR42600.2020.01033"},{"key":"6938_CR31","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":"6938_CR32","doi-asserted-by":"crossref","unstructured":"Sun K, Xiao B, Liu D, Wang J (2019) Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5693\u20135703","DOI":"10.1109\/CVPR.2019.00584"},{"key":"6938_CR33","doi-asserted-by":"crossref","unstructured":"Wang C, Samari B, Siddiqi K (2018) Local spectral graph convolution for point set feature learning. In: Proceedings of the European conference on computer vision (ECCV), pp 52\u201366","DOI":"10.1007\/978-3-030-01225-0_4"},{"key":"6938_CR34","doi-asserted-by":"crossref","unstructured":"Ye M, Shen J, Lin G, Xiang T, Shao L, Hoi SC (2021) Deep learning for person re-identification: a survey and outlook. In: IEEE transactions on pattern analysis and machine intelligence","DOI":"10.1109\/TPAMI.2021.3054775"},{"issue":"2","key":"6938_CR35","first-page":"179","volume":"37","author":"SWO Driscoll","year":"2000","unstructured":"Driscoll SWO, Giori NJ (2000) Continuous passive motion (CPM): theory and principles of clinical application. J Rehabil Res Dev 37(2):179\u2013188","journal-title":"J Rehabil Res Dev"},{"issue":"1","key":"6938_CR36","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","volume":"43","author":"Z Cao","year":"2019","unstructured":"Cao Z, Hidalgo G, Simon T, Wei S-E, Sheikh Y (2019) Openpose: realtime multi-person 2d pose estimation using part affinity fields. IEEE Trans Pattern Anal Mach Intell 43(1):172\u2013186","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6938_CR37","unstructured":"Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao A, Xu C, Xu Y et\u00a0al. (2020) A survey on visual transformer. arXiv preprint arXiv:2012.12556"},{"key":"6938_CR38","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol\u00a032, no\u00a01","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"6938_CR39","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"6938_CR40","doi-asserted-by":"crossref","unstructured":"Yun S, Han D, Oh SJ et al (2019) Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6023\u20136032","DOI":"10.1109\/ICCV.2019.00612"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-06938-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-06938-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-06938-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T17:12:12Z","timestamp":1682356332000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-06938-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,20]]},"references-count":40,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["6938"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-06938-7","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,20]]},"assertion":[{"value":"26 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2022","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}