{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:28:04Z","timestamp":1760956084724,"version":"build-2065373602"},"reference-count":55,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2021,1,7]],"date-time":"2021-01-07T00:00:00Z","timestamp":1609977600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61803061, 61906026"],"award-info":[{"award-number":["61803061, 61906026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Science and Technology Research Program of Chongqing Municipal Education Commission","award":["KJQN201800603"],"award-info":[{"award-number":["KJQN201800603"]}]},{"name":"Chongqing Natural Science Foundation","award":["cstc2018j-cyjAX0167"],"award-info":[{"award-number":["cstc2018j-cyjAX0167"]}]},{"name":"the Common Key Technology Innovation Special of Key Industries of Chongqing Science and Technology Commission","award":["cstc2017z-dcy-zdyfX0067, cstc2017zdcy-zdyfX0055, cstc2018jszx-cyzd0634"],"award-info":[{"award-number":["cstc2017z-dcy-zdyfX0067, cstc2017zdcy-zdyfX0055, cstc2018jszx-cyzd0634"]}]},{"name":"the Artificial Intelligence Technology Innovation Significant Theme Special Project of Chongqing Science and Technology Commission","award":["cstc2017rgzn-zdyfX0014, cstc2017rgzn-zdyfX0035"],"award-info":[{"award-number":["cstc2017rgzn-zdyfX0014, cstc2017rgzn-zdyfX0035"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Person re-identification (Re-ID) is challenging due to host of factors: the variety of human positions, difficulties in aligning bounding boxes, and complex backgrounds, among other factors. This paper proposes a new framework called EXAM (EXtreme And Moderate feature embeddings) for Re-ID tasks. This is done using discriminative feature learning, requiring attention-based guidance during training. Here \u201cExtreme\u201d refers to salient human features and \u201cModerate\u201d refers to common human features. In this framework, these types of embeddings are calculated by global max-pooling and average-pooling operations respectively; and then, jointly supervised by multiple triplet and cross-entropy loss functions. The processes of deducing attention from learned embeddings and discriminative feature learning are incorporated, and benefit from each other in this end-to-end framework. From the comparative experiments and ablation studies, it is shown that the proposed EXAM is effective, and its learned feature representation reaches state-of-the-art performance.<\/jats:p>","DOI":"10.3390\/jimaging7010006","type":"journal-article","created":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T19:55:56Z","timestamp":1610308556000},"page":"6","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["EXAM: A Framework of Learning Extreme and Moderate Embeddings for Person Re-ID"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9562-3865","authenticated-orcid":false,"given":"Guanqiu","family":"Qi","sequence":"first","affiliation":[{"name":"Computer Information Systems Department, State University of New York at Buffalo State, Buffalo, NY 14222, USA"}]},{"given":"Gang","family":"Hu","sequence":"additional","affiliation":[{"name":"Computer Information Systems Department, State University of New York at Buffalo State, Buffalo, NY 14222, USA"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, China"}]},{"given":"Neal","family":"Mazur","sequence":"additional","affiliation":[{"name":"Computer Information Systems Department, State University of New York at Buffalo State, Buffalo, NY 14222, USA"}]},{"given":"Zhiqin","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, China"}]},{"given":"Matthew","family":"Haner","sequence":"additional","affiliation":[{"name":"Department of Mathematics &amp; Computer and Information Science, Mansfield University of Pennsylvania, Mansfield, PA 16933, USA"}]}],"member":"1968","published-online":{"date-parts":[[2021,1,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"107414","DOI":"10.1016\/j.patcog.2020.107414","article-title":"Structure alignment of attributes and visual features for cross-dataset person re-identification","volume":"106","author":"Li","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"107277","DOI":"10.1016\/j.sigpro.2019.107277","article-title":"Person re-identification by integrating metric learning and support vector machine","volume":"166","author":"Zhao","year":"2020","journal-title":"Signal Process."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1480","DOI":"10.1109\/TIFS.2020.3036800","article-title":"Attribute-Aligned Domain-Invariant Feature Learning for Unsupervised Domain Adaptation Person Re-Identification","volume":"16","author":"Li","year":"2021","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1016\/j.ins.2019.06.046","article-title":"Top distance regularized projection and dictionary learning for person re-identification","volume":"502","author":"Li","year":"2019","journal-title":"Inf. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1016\/j.neucom.2019.11.001","article-title":"Person re-identification with dictionary learning regularized by stretching regularization and label consistency constraint","volume":"379","author":"Li","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3472","DOI":"10.1109\/TCSVT.2019.2952550","article-title":"Attribute-Identity Embedding and Self-supervised Learning for Scalable Person Re-Identification","volume":"30","author":"Li","year":"2019","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2897","DOI":"10.1049\/iet-ipr.2019.0699","article-title":"HPILN: A feature learning framework for cross-modality person re-identification","volume":"13","author":"Zhao","year":"2019","journal-title":"IET Image Process."},{"key":"ref_9","unstructured":"Zhang, X., Luo, H., Fan, X., Xiang, W., Sun, Y., Xiao, Q., Jiang, W., Zhang, C., and Sun, J. (2017). AlignedReID: Surpassing Human-Level Performance in Person Re-Identification. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhao, H., Tian, M., Sun, S., Shao, J., Yan, J., Yi, S., Wang, X., and Tang, X. (2017, January 21\u201326). Spindle Net: Person Re-Identification with Human Body Region Guided Feature Decomposition and Fusion. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.103"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Song, C., Huang, Y., Ouyang, W., and Wang, L. (2018, January 18\u201323). Mask-guided contrastive attention model for person re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00129"},{"key":"ref_12","unstructured":"Ning, X.B., Yuan, G., Yizhe, Z., and Christian, P. (November, January 27). Second-Order Non-Local Attention Networks for Person Re-Identification. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_13","unstructured":"Shuang, L., Slawomir, B., Peter, C., and Xiaogang, W. (2018, January 18\u201323). Diversity regularized spatiotemporal attention for video-based person re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA."},{"key":"ref_14","unstructured":"Chen, T., Ding, S., Xie, J., Yuan, Y., Chen, W., Yang, Y., Ren, Z., and Wang, Z. (November, January 27). Abd-net: Attentive but diverse person re-identification. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Li, W., Zhao, R., Xiao, T., and Wang, X. (2014, January 23\u201328). DeepReID: Deep Filter Pairing Neural Network for Person Re-Identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.27"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yi, D., Lei, Z., Liao, S., and Li, S.Z. (2014, January 24\u201328). Deep Metric Learning for Person Re-identification. Proceedings of the International Conference on Pattern Recognition, Stockholm, Sweden.","DOI":"10.1109\/ICPR.2014.16"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zheng, L., Yang, Y., Tian, Q., and Wang, S. (2018, January 8\u201314). Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline). Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2657","DOI":"10.1109\/TCSVT.2017.2726580","article-title":"Deep Multi-View Feature Learning for Person Re-Identification","volume":"28","author":"Tao","year":"2018","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3159171","article-title":"A Discriminatively Learned CNN Embedding for Person Reidentification","volume":"14","author":"Zheng","year":"2017","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Li, D., Chen, X., Zhang, Z., and Huang, K. (2017, January 21\u201326). Learning Deep Context-Aware Features Over Body and Latent Parts for Person Re-Identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.782"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Saquib Sarfraz, M., Schumann, A., Eberle, A., and Stiefelhagen, R. (2018, January 18\u201323). A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00051"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"986","DOI":"10.1109\/TMM.2018.2870522","article-title":"GLAD: Global-Local-Alignment Descriptor for Scalable Person Re-Identification","volume":"21","author":"Wei","year":"2019","journal-title":"IEEE Trans. Multimed."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2860","DOI":"10.1109\/TIP.2019.2891888","article-title":"Deep Representation Learning with Part Loss for Person Re-Identification","volume":"28","author":"Yao","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"103494","DOI":"10.1016\/j.infrared.2020.103494","article-title":"A residual neural network based method for the classification of tobacco cultivation regions using near-infrared spectroscopy sensors","volume":"111","author":"Jiang","year":"2020","journal-title":"Infrared Phys. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Li, W., Zhu, X., and Gong, S. (2018, January 18\u201323). Harmonious Attention Network for Person Re-Identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00243"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, C., Zhang, Q., Huang, C., Liu, W., and Wang, X. (2018, January 8\u201314). Mancs: A multi-task attentional network with curriculum sampling for person re-identification. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01225-0_23"},{"key":"ref_27","unstructured":"Chen, G., Lin, C., Ren, L., Lu, J., and Zhou, J. (November, January 27). Self-Critical Attention Learning for Person Re-Identification. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_28","unstructured":"Binghui, C., Weihong, D., and Jiani, H. (November, January 27). Mixed high-order attention network for person re-identification. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hou, R., Ma, B., Chang, H., Gu, X., Shan, S., and Chen, X. (2019, January 15\u201320). Interaction-And-Aggregation Network for Person Re-Identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00954"},{"key":"ref_30","unstructured":"Zhou, S., Wang, F., Huang, Z., and Wang, J. (November, January 27). Discriminative feature learning with consistent attention regularization for person re-identification. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_31","unstructured":"Hu, G., and Gao, Q. (2012, January 11\u201315). A 3D gesture recognition framework based on hierarchical visual attention and perceptual organization models. Proceedings of the IEEE 21st International Conference on Pattern Recognition (ICPR2012), Tsukuba, Japan."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"107036","DOI":"10.1016\/j.patcog.2019.107036","article-title":"Deep-Person: Learning discriminative deep features for person Re-Identification","volume":"98","author":"Bai","year":"2020","journal-title":"Pattern Recogn."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Hu, G., Dixit, C., Luong, D., Gao, Q., and Cheng, L. (2019, January 22\u201325). Salience Guided Pooling in Deep Convolutional Networks. Proceedings of the IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan.","DOI":"10.1109\/ICIP.2019.8802973"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_35","unstructured":"Hermans, A., Beyer, L., and Leibe, B. (2017). In Defense of the Triplet Loss for Person Re-Identification. arXiv."},{"key":"ref_36","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., and Yang, Y. (2017). Random Erasing Data Augmentation. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., and Ramanan, D. (2008, January 23\u201328). A discriminatively trained, multiscale, deformable part model. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"ref_38","unstructured":"Zhou, K., Yang, Y., Cavallaro, A., and Xiang, T. (November, January 27). Omni-Scale Feature Learning for Person Re-Identification. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zheng, L., Deng, W., and Wang, S. (2017, January 22\u201329). Svdnet for pedestrian retrieval. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.410"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Huang, H., Li, D., Zhang, Z., Chen, X., and Huang, K. (2018, January 18\u201323). Adversarially occluded samples for person re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00535"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Du, Y., Yuan, C., Li, B., Zhao, L., Li, Y., and Hu, W. (2018, January 8\u201314). Interaction-aware spatio-temporal pyramid attention networks for action classification. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01270-0_23"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yang, W., Huang, H., Zhang, Z., Chen, X., Huang, K., and Zhang, S. (2019, January 15\u201320). Towards Rich Feature Discovery with Class Activation Maps Augmentation for Person Re-Identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00148"},{"key":"ref_43","unstructured":"Ustinova, E., Ganin, Y., and Lempitsky, V. (September, January 29). Multi-region bilinear convolutional neural networks for person re-identification. Proceedings of the IEEE International Conference on Advanced Video and Signal Based Surveillance, Lecce, Italy."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhao, L., Li, X., Zhuang, Y., and Wang, J. (2017, January 22\u201329). Deeply-Learned Part-Aligned Representations for Person Re-Identification. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.349"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Su, C., Li, J., Zhang, S., Xing, J., Gao, W., and Tian, Q. (2017, January 22\u201329). Pose-Driven Deep Convolutional Model for Person Re-Identification. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.427"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Xu, J., Zhao, R., Zhu, F., Wang, H., and Ouyang, W. (2018, January 18\u201323). Attention-Aware Compositional Network for Person Re-Identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00226"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Tay, C.P., Roy, S., and Yap, K.H. (2019, January 15\u201320). AANet: Attribute Attention Network for Person Re-Identifications. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00730"},{"key":"ref_48","unstructured":"Quan, R., Dong, X., Wu, Y., Zhu, L., and Yang, Y. (November, January 27). Auto-ReID: Searching for a Part-Aware ConvNet for Person Re-Identification. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Chang, X., Hospedales, T.M., and Xiang, T. (2018, January 18\u201323). Multi-Level Factorisation Net for Person Re-Identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00225"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Si, J., Zhang, H., Li, C.G., Kuen, J., Kong, X., Kot, A.C., and Wang, G. (2018, January 18\u201323). Dual attention matching network for context-aware feature sequence based person re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00562"},{"key":"ref_51","unstructured":"Xiong, F., Xiao, Y., Cao, Z., Gong, K., Fang, Z., and Zhou, J.T. (2018). Towards good practices on building effective cnn baseline model for person re-identification. arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"3037","DOI":"10.1109\/TCSVT.2018.2873599","article-title":"Pedestrian Alignment Network for Large-scale Person Re-Identification","volume":"29","author":"Zheng","year":"2019","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhu, X., and Gong, S. (2017, January 22\u201329). Person re-identification by deep learning multi-scale representations. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCVW.2017.304"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, L., You, Y., Zou, X., Chen, V., Li, S., Huang, G., Hariharan, B., and Weinberger, K.Q. (2018, January 18\u201323). Resource aware person re-identification across multiple resolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00839"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Yang, X., Yu, Z., Zheng, L., Yang, Y., and Kautz, J. (2019, January 15\u201320). Joint discriminative and generative learning for person re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00224"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/7\/1\/6\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:08:06Z","timestamp":1760159286000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/7\/1\/6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,7]]},"references-count":55,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,1]]}},"alternative-id":["jimaging7010006"],"URL":"https:\/\/doi.org\/10.3390\/jimaging7010006","relation":{},"ISSN":["2313-433X"],"issn-type":[{"type":"electronic","value":"2313-433X"}],"subject":[],"published":{"date-parts":[[2021,1,7]]}}}