{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T11:54:15Z","timestamp":1790682855760,"version":"4.1.0"},"reference-count":93,"publisher":"Springer Science and Business Media LLC","issue":"6-7","license":[{"start":{"date-parts":[[2019,2,19]],"date-time":"2019-02-19T00:00:00Z","timestamp":1550534400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61473291"],"award-info":[{"award-number":["61473291"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876178"],"award-info":[{"award-number":["61876178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Plan","award":["2016YFC0801002"],"award-info":[{"award-number":["2016YFC0801002"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806196"],"award-info":[{"award-number":["61806196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1007\/s11263-019-01159-3","type":"journal-article","created":{"date-parts":[[2019,2,18]],"date-time":"2019-02-18T23:03:17Z","timestamp":1550530997000},"page":"537-559","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Single-Shot Scale-Aware Network for Real-Time Face Detection"],"prefix":"10.1007","volume":"127","author":[{"given":"Shifeng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longyin","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hailin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siwei","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stan Z.","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,2,19]]},"reference":[{"key":"1159_CR1","unstructured":"Barbu, A., Lay, N., & Gramajo, G. (2014). Face detection with a 3d model. CoRR \n                    arXiv:abs\/1404.35968\n                    \n                  ."},{"key":"1159_CR2","doi-asserted-by":"crossref","unstructured":"Bell, S., Zitnick, C. L., Bala, K., & Girshick, R. B. (2016). Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 2874\u20132883).","DOI":"10.1109\/CVPR.2016.314"},{"issue":"1\u20133","key":"1159_CR3","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s11263-007-0060-1","volume":"77","author":"SC Brubaker","year":"2008","unstructured":"Brubaker, S. C., Wu, J., Sun, J., Mullin, M. D., & Rehg, J. M. (2008). On the design of cascades of boosted ensembles for face detection. International Journal of Computer Vision, 77(1\u20133), 65\u201386.","journal-title":"International Journal of Computer Vision"},{"key":"1159_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Z., Fan, Q., Feris, R. S., & Vasconcelos, N. (2016). A unified multi-scale deep convolutional neural network for fast object detection. In Proceedings of European conference on computer vision (pp. 354\u2013370).","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"1159_CR5","doi-asserted-by":"crossref","unstructured":"Chen, D., Hua, G., Wen, F., & Sun, J. (2016). Supervised transformer network for efficient face detection. In Proceedings of European conference on computer vision (pp. 122\u2013138).","DOI":"10.1007\/978-3-319-46454-1_8"},{"key":"1159_CR6","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2015). Semantic image segmentation with deep convolutional nets and fully connected crfs. In International conference on learning representations ."},{"key":"1159_CR7","unstructured":"Chen, Y., Song, L., & He, R. (2017). Masquer hunter: Adversarial occlusion-aware face detection. CoRR \n                    arXiv:abs\/1709.05188\n                    \n                  ."},{"key":"1159_CR8","unstructured":"Dai, J., Li, Y., He, K., & Sun, J. (2016). R-FCN: Object detection via region-based fully convolutional networks. In D. D. Lee, M. Sugiyama, V. von Luxburg, I. Guyon, & R. Garnett (Eds.), Advances in neural information processing systems, Barcelona, Spain (pp. 379\u2013387)."},{"key":"1159_CR9","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 886\u2013893).","DOI":"10.1109\/CVPR.2005.177"},{"key":"1159_CR10","doi-asserted-by":"crossref","unstructured":"Erhan, D., Szegedy, C., Toshev, A., & Anguelov, D. (2014). Scalable object detection using deep neural networks. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 2155\u20132162).","DOI":"10.1109\/CVPR.2014.276"},{"key":"1159_CR11","doi-asserted-by":"crossref","unstructured":"Farfade, S. S., Saberian, M. J., & Li, L. (2015). Multi-view face detection using deep convolutional neural networks. In ACM on international conference on multimedia retrieval (pp. 643\u2013650).","DOI":"10.1145\/2671188.2749408"},{"issue":"9","key":"1159_CR12","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P. F., Girshick, R. B., McAllester, D. A., & Ramanan, D. (2010). Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(9), 1627\u20131645.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"1159_CR13","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","volume":"55","author":"Y Freund","year":"1997","unstructured":"Freund, Y., & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119\u2013139.","journal-title":"Journal of Computer and System Sciences"},{"key":"1159_CR14","unstructured":"Fu, C., Liu, W., Ranga, A., Tyagi, A., & Berg, A. C. (2017). DSSD : Deconvolutional single shot detector. CoRR \n                    arXiv:abs\/1701.06659\n                    \n                  ."},{"key":"1159_CR15","doi-asserted-by":"crossref","unstructured":"Ge, S., Li, J., Ye, Q., & Luo, Z. (2017). Detecting masked faces in the wild with lle-cnns. CVPR (pp. 426\u2013434).","DOI":"10.1109\/CVPR.2017.53"},{"key":"1159_CR16","unstructured":"Ghiasi, G., & Fowlkes, C. C. (2015). Occlusion coherence: Detecting and localizing occluded faces. CoRR \n                    arXiv:abs\/1506.08347\n                    \n                  ."},{"key":"1159_CR17","doi-asserted-by":"crossref","unstructured":"Gidaris, S., & Komodakis, N. (2015). Object detection via a multi-region and semantic segmentation-aware CNN model. In Proceedings of IEEE international conference on computer vision (pp. 1134\u20131142).","DOI":"10.1109\/ICCV.2015.135"},{"key":"1159_CR18","doi-asserted-by":"crossref","unstructured":"Girshick, R. B. (2015). Fast R-CNN. In Proceedings of IEEE international conference on computer vision (pp. 1440\u20131448).","DOI":"10.1109\/ICCV.2015.169"},{"key":"1159_CR19","doi-asserted-by":"crossref","unstructured":"Girshick, R. B., Donahue, J., Darrell, T., Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 580\u2013587).","DOI":"10.1109\/CVPR.2014.81"},{"key":"1159_CR20","unstructured":"Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In International conference on artificial intelligence and statistics (pp. 249\u2013256)."},{"key":"1159_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2014). Spatial pyramid pooling in deep convolutional networks for visual recognition. In Proceedings of European conference on computer vision (pp. 346\u2013361).","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"1159_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1159_CR23","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Chodpathumwan, Y., & Dai, Q. (2012). Diagnosing error in object detectors. In ECCV (pp. 340\u2013353).","DOI":"10.1007\/978-3-642-33712-3_25"},{"key":"1159_CR24","unstructured":"Howard, A. G. (2013). Some improvements on deep convolutional neural network based image classification. CoRR \n                    arXiv:abs\/1312.5402\n                    \n                  ."},{"key":"1159_CR25","doi-asserted-by":"crossref","unstructured":"Hu, P., & Ramanan, D. (2017). Finding tiny faces. In CVPR (pp. 1522\u20131530).","DOI":"10.1109\/CVPR.2017.166"},{"key":"1159_CR26","unstructured":"Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., et al. (2016). Speed\/accuracy trade-offs for modern convolutional object detectors. CoRR \n                    arXiv:abs\/1611.10012\n                    \n                  ."},{"key":"1159_CR27","unstructured":"Jain, V., & Learned-Miller, E. (2010). Fddb: A benchmark for face detection in unconstrained settings. Technical Report UM-CS-2010-009, University of Massachusetts, Amherst."},{"key":"1159_CR28","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R. B., et al. (2014). Caffe: Convolutional architecture for fast feature embedding. In ACM international conference on multimedia (pp. 675\u2013678).","DOI":"10.1145\/2647868.2654889"},{"key":"1159_CR29","unstructured":"Jiang, H., & Learned-Miller, E. (2016). Face detection with the faster r-cnn. CoRR \n                    arXiv:abs\/1606.03473\n                    \n                  ."},{"key":"1159_CR30","doi-asserted-by":"crossref","unstructured":"Jiang, H., & Learned-Miller, E. G. (2017). Face detection with the faster R-CNN. In Proceedings of IEEE international conference on automatic face and gesture recognition (pp. 650\u2013657).","DOI":"10.1109\/FG.2017.82"},{"key":"1159_CR31","doi-asserted-by":"crossref","unstructured":"Kalal, Z., Matas, J., & Mikolajczyk, K. (2008). Weighted sampling for large-scale boosting. In Proceedings of British machine vision conference (pp. 1\u201310).","DOI":"10.5244\/C.22.42"},{"key":"1159_CR32","doi-asserted-by":"crossref","unstructured":"Kong, T., Sun, F., Yao, A., Liu, H., Lu, M., & Chen, Y. (2017). RON: Reverse connection with objectness prior networks for object detection. In Proceedings of IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.557"},{"key":"1159_CR33","doi-asserted-by":"crossref","unstructured":"Kong, T., Yao, A., Chen, Y., & Sun, F. (2016). Hypernet: Towards accurate region proposal generation and joint object detection. In Proceedings of IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.98"},{"key":"1159_CR34","doi-asserted-by":"crossref","unstructured":"Kumar, V., Namboodiri, A. M., & Jawahar, C. V. (2015). Visual phrases for exemplar face detection. In Proceedings of IEEE international conference on computer vision (pp. 1994\u20132002).","DOI":"10.1109\/ICCV.2015.231"},{"key":"1159_CR35","unstructured":"Lee, H., Eum, S., & Kwon, H. (2017). ME R-CNN: Multi-expert region-based CNN for object detection. In Proceedings of IEEE international conference on computer vision."},{"key":"1159_CR36","doi-asserted-by":"crossref","unstructured":"Li, H., Lin, Z., Brandt, J., Shen, X., & Hua, G. (2014). Efficient boosted exemplar-based face detection. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 1843\u20131850).","DOI":"10.1109\/CVPR.2014.238"},{"key":"1159_CR37","doi-asserted-by":"crossref","unstructured":"Li, H., Lin, Z., Shen, X., Brandt, J., & Hua, G. (2015). A convolutional neural network cascade for face detection. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 5325\u20135334).","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"1159_CR38","doi-asserted-by":"crossref","unstructured":"Li, J., & Zhang, Y. (2013). Learning SURF cascade for fast and accurate object detection. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 3468\u20133475).","DOI":"10.1109\/CVPR.2013.445"},{"key":"1159_CR39","doi-asserted-by":"crossref","unstructured":"Li, Y., Sun, B., Wu, T., & Wang, Y. (2016). Face detection with end-to-end integration of a convnet and a 3d model. In Proceedings of European conference on computer vision (pp. 420\u2013436).","DOI":"10.1007\/978-3-319-46487-9_26"},{"issue":"2","key":"1159_CR40","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1109\/TPAMI.2015.2448075","volume":"38","author":"S Liao","year":"2016","unstructured":"Liao, S., Jain, A. K., & Li, S. Z. (2016). A fast and accurate unconstrained face detector. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(2), 211\u2013223.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1159_CR41","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R. B., He, K., Hariharan, B., & Belongie, S. J. (2017a). Feature pyramid networks for object detection. In Proceedings of IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.106"},{"key":"1159_CR42","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R. B., He, K., & Doll\u00e1r, P. (2017b). Focal loss for dense object detection. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1159_CR43","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S.E., Fu, C., et al. (2016). SSD: Single shot multibox detector. In Proceedings of European conference on computer vision (pp. 21\u201337).","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1159_CR44","unstructured":"Liu, W., Rabinovich, A., & Berg, A. C. (2015). Parsenet: Looking wider to see better. CoRR \n                    arXiv:abs\/1506.04579\n                    \n                  ."},{"key":"1159_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, H., Yan, J., Wei, F., Wang, X., & Tang, X. (2017). Recurrent scale approximation for object detection in CNN. In ICCV.","DOI":"10.1109\/ICCV.2017.69"},{"issue":"2","key":"1159_CR46","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"key":"1159_CR47","unstructured":"Luo, W., Li, Y., Urtasun, R., & Zemel, R. S. (2016). Understanding the effective receptive field in deep convolutional neural networks. In Advances in neural information processing systems (pp. 4898\u20134906)."},{"key":"1159_CR48","doi-asserted-by":"crossref","unstructured":"Mathias, M., Benenson, R., Pedersoli, M., & Gool, L. J. V. (2014). Face detection without bells and whistles. In Proceedings of European conference on computer vision.","DOI":"10.1007\/978-3-319-10593-2_47"},{"key":"1159_CR49","doi-asserted-by":"crossref","unstructured":"Najibi, M., Samangouei, P., Chellappa, R., & Davis, L. S. (2017). SSH: Single stage headless face detector. In ICCV.","DOI":"10.1109\/ICCV.2017.522"},{"key":"1159_CR50","doi-asserted-by":"crossref","unstructured":"Ohn-Bar, E., & Trivedi, M. M. (2016). To boost or not to boost? On the limits of boosted trees for object detection. In International conference on pattern recognition.","DOI":"10.1109\/ICPR.2016.7900151"},{"key":"1159_CR51","doi-asserted-by":"crossref","unstructured":"Pham, M., & Cham, T. (2007). Fast training and selection of haar features using statistics in boosting-based face detection. In Proceedings of IEEE international conference on computer vision (pp. 1\u20137).","DOI":"10.1109\/ICCV.2007.4409038"},{"key":"1159_CR52","doi-asserted-by":"crossref","unstructured":"Qin, H., Yan, J., Li, X., & Hu, X. (2016). Joint training of cascaded CNN for face detection. In Proceedings of IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.376"},{"key":"1159_CR53","unstructured":"Ranjan, R., Patel, V. M., & Chellappa, R. (2015). A deep pyramid deformable part model for face detection. In: IEEE International conference on biometrics theory, applications and systems (pp. 1\u20138)."},{"key":"1159_CR54","unstructured":"Ranjan, R., Patel, V. M., & Chellappa, R. (2016). Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. CoRR \n                    arXiv:abs\/1603.01249\n                    \n                  ."},{"key":"1159_CR55","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S. K., Girshick, R. B., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 779\u2013788).","DOI":"10.1109\/CVPR.2016.91"},{"key":"1159_CR56","unstructured":"Redmon, J., & Farhadi, A. (2016). YOLO9000: Better, faster, stronger. CoRR \n                    arXiv:abs\/1612.08242\n                    \n                  ."},{"issue":"6","key":"1159_CR57","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R. B., & Sun, J. (2017). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137\u20131149.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"1159_CR58","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"1159_CR59","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2014). Overfeat: Integrated recognition, localization and detection using convolutional networks. In International conference on learning representations."},{"key":"1159_CR60","doi-asserted-by":"crossref","unstructured":"Shen, X., Lin, Z., Brandt, J., & Wu, Y. (2013). Detecting and aligning faces by image retrieval. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 3460\u20133467).","DOI":"10.1109\/CVPR.2013.444"},{"key":"1159_CR61","doi-asserted-by":"crossref","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y., Chen, Y., & Xue, X. (2017). DSOD: Learning deeply supervised object detectors from scratch. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2017.212"},{"key":"1159_CR62","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., & Gupta, A. (2016). Contextual priming and feedback for faster R-CNN. In Proceedings of European conference on computer vision (pp. 330\u2013348).","DOI":"10.1007\/978-3-319-46448-0_20"},{"key":"1159_CR63","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., & Girshick, R. B. (2016a). Training region-based object detectors with online hard example mining. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 761\u2013769).","DOI":"10.1109\/CVPR.2016.89"},{"key":"1159_CR64","unstructured":"Shrivastava, A., Sukthankar, R., Malik, J., & Gupta, A. (2016b). Beyond skip connections: Top-down modulation for object detection. CoRR \n                    arXiv:abs\/1612.06851\n                    \n                  ."},{"key":"1159_CR65","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. CoRR \n                    arXiv:abs\/1409.1556\n                    \n                  ."},{"key":"1159_CR66","unstructured":"Sun, X., Wu, P., & Hoi, S. C. H. (2017). Face detection using deep learning: An improved faster RCNN approach. CoRR \n                    arXiv:abs\/1701.08289\n                    \n                  ."},{"key":"1159_CR67","unstructured":"Triantafyllidou, D., & Tefas, A. (2016). A fast deep convolutional neural network for face detection in big visual data. In INNS conference on big data (pp. 61\u201370)."},{"issue":"2","key":"1159_CR68","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JRR Uijlings","year":"2013","unstructured":"Uijlings, J. R. R., van de Sande, K. E. A., Gevers, T., & Smeulders, A. W. M. (2013). Selective search for object recognition. International Journal of Computer Vision, 104(2), 154\u2013171.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"1159_CR69","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"PA Viola","year":"2004","unstructured":"Viola, P. A., & Jones, M. J. (2004). Robust real-time face detection. International Journal of Computer Vision, 57(2), 137\u2013154.","journal-title":"International Journal of Computer Vision"},{"key":"1159_CR70","unstructured":"Wan, S., Chen, Z., Zhang, T., Zhang, B., & Wong, K. (2016). Bootstrapping face detection with hard negative examples. CoRR \n                    arXiv:abs\/1608.02236\n                    \n                  ."},{"key":"1159_CR71","unstructured":"Wang, H., Li, Z., Ji, X., & Wang, Y. (2017a). Face R-CNN. CoRR \n                    arXiv:abs\/1706.01061\n                    \n                  ."},{"key":"1159_CR72","unstructured":"Wang, J., Yuan, Y., & Yu, G. (2017b). Face attention network: An effective face detector for the occluded faces. CoRR \n                    arXiv:abs\/1711.07246\n                    \n                  ."},{"key":"1159_CR73","doi-asserted-by":"crossref","unstructured":"Wang, X., Shrivastava, A., & Gupta, A. (2017c). A-fast-rcnn: Hard positive generation via adversary for object detection. In Proceedings of IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.324"},{"key":"1159_CR74","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, S., Lei, Z., Liu, S., Guo, X., & Li, S. Z. (2018). Ensemble soft-margin softmax loss for image classification. In IJCAI (pp. 992\u2013998).","DOI":"10.24963\/ijcai.2018\/138"},{"key":"1159_CR75","unstructured":"Wang, Y., Ji, X., Zhou, Z., Wang, H., & Li, Z. (2017d). Detecting faces using region-based fully convolutional networks. CoRR \n                    arXiv:abs\/1709.05256\n                    \n                  ."},{"key":"1159_CR76","doi-asserted-by":"crossref","unstructured":"Yan, J., Lei, Z., Wen, L. & Li, S. Z. (2014a). The fastest deformable part model for object detection. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 2497\u20132504).","DOI":"10.1109\/CVPR.2014.320"},{"issue":"10","key":"1159_CR77","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1016\/j.imavis.2013.12.004","volume":"32","author":"J Yan","year":"2014","unstructured":"Yan, J., Zhang, X., Lei, Z., & Li, S. Z. (2014b). Face detection by structural models. Image Vision Computing, 32(10), 790\u2013799.","journal-title":"Image Vision Computing"},{"key":"1159_CR78","doi-asserted-by":"crossref","unstructured":"Yang, B., Yan, J., Lei, Z., & Li, S. Z. (2014). Aggregate channel features for multi-view face detection. In International joint conference on biometrics (pp. 1\u20138).","DOI":"10.1109\/BTAS.2014.6996284"},{"key":"1159_CR79","doi-asserted-by":"crossref","unstructured":"Yang, B., Yan, J., Lei, Z., & Li, S. Z. (2015a). Convolutional channel features. In Proceedings of IEEE international conference on computer vision (pp. 82\u201390).","DOI":"10.1109\/ICCV.2015.18"},{"key":"1159_CR80","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, P., Loy, C. C., & Tang, X. (2015b). From facial parts responses to face detection: A deep learning approach. In Proceedings of IEEE international conference on computer vision (pp. 3676\u20133684).","DOI":"10.1109\/ICCV.2015.419"},{"key":"1159_CR81","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, P., Loy, C. C., & Tang, X. (2016). WIDER FACE: A face detection benchmark. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 5525\u20135533).","DOI":"10.1109\/CVPR.2016.596"},{"key":"1159_CR82","unstructured":"Yang, S., Xiong, Y., Loy, C. C., & Tang, X. (2017). Face detection through scale-friendly deep convolutional networks. CoRR \n                    arXiv:abs\/1706.02863\n                    \n                  ."},{"key":"1159_CR83","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., & Huang, T. S. (2016). Unitbox: An advanced object detection network. In ACM conference on multimedia conference (pp. 516\u2013520).","DOI":"10.1145\/2964284.2967274"},{"key":"1159_CR84","doi-asserted-by":"crossref","unstructured":"Zeng, X., Ouyang, W., Yang, B., Yan, J., & Wang, X. (2016). Gated bi-directional CNN for object detection. In Proceedings of European conference on computer vision (pp. 354\u2013369).","DOI":"10.1007\/978-3-319-46478-7_22"},{"issue":"10","key":"1159_CR85","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 23(10), 1499\u20131503.","journal-title":"IEEE Signal Processing Letters"},{"key":"1159_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhang, Z., Wang, H., Li, Z., Qiao, Y., & Liu, W. (2017a). Detecting faces using inside cascaded contextual cnn. In ICCV.","DOI":"10.1109\/ICCV.2017.344"},{"key":"1159_CR87","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., & Li, S. Z. (2017b). Single-shot refinement neural network for object detection. CoRR \n                    arXiv:abs\/1711.06897\n                    \n                  .","DOI":"10.1109\/CVPR.2018.00442"},{"key":"1159_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhu, X., Lei, Z., Shi, H., Wang, X., & Li, S. Z. (2017c). Faceboxes: A CPU real-time face detector with high accuracy. In International joint conference on biometrics.","DOI":"10.1109\/BTAS.2017.8272675"},{"key":"1159_CR89","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhu, X., Lei, Z., Shi, H., Wang, X., & Li, S. Z.(2017d). S\n                    \n                      \n                    \n                    $${}^{{3}}$$\n                    \n                      \n                        \n                          \n                          3\n                        \n                      \n                    \n                  FD: Single shot scale-invariant face detector. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2017.30"},{"key":"1159_CR90","unstructured":"Zhu, C., Zheng, Y., Luu, K., & Savvides, M. (2016). CMS-RCNN: Contextual multi-scale region-based CNN for unconstrained face detection. CoRR \n                    arXiv:abs\/1606.05413\n                    \n                  ."},{"key":"1159_CR91","unstructured":"Zhu, X., & Ramanan, D. (2012). Face detection, pose estimation, and landmark localization in the wild. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 2879\u20132886)."},{"key":"1159_CR92","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhao, C., Wang, J., Zhao, X., Wu, Y., & Lu, H. (2017). Couplenet: Coupling global structure with local parts for object detection. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2017.444"},{"key":"1159_CR93","doi-asserted-by":"crossref","unstructured":"Zitnick, C. L., & Doll\u00e1r, P. (2014). Edge boxes: Locating object proposals from edges. In Proceedings of European conference on computer vision (pp. 391\u2013405).","DOI":"10.1007\/978-3-319-10602-1_26"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-019-01159-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01159-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01159-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T19:17:18Z","timestamp":1582053438000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-019-01159-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,19]]},"references-count":93,"journal-issue":{"issue":"6-7","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["1159"],"URL":"https:\/\/doi.org\/10.1007\/s11263-019-01159-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,19]]},"assertion":[{"value":"16 January 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}