{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T11:31:07Z","timestamp":1776425467945,"version":"3.51.2"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"R&D Program of Beijing Municipal Education Commission","award":["KM202311232002"],"award-info":[{"award-number":["KM202311232002"]}]},{"name":"Beijing Natural Science Foundation","award":["4232025"],"award-info":[{"award-number":["4232025"]}]},{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62202061;64171043"],"award-info":[{"award-number":["62202061;64171043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62202061;64171043"],"award-info":[{"award-number":["62202061;64171043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s00371-024-03629-3","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T12:02:56Z","timestamp":1729080176000},"page":"3719-3734","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Attribute correlation mask fusion network for pedestrian attribute recognition"],"prefix":"10.1007","volume":"41","author":[{"given":"Baoan","family":"Li","sequence":"first","affiliation":[]},{"given":"Long","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Shangzhi","family":"Teng","sequence":"additional","affiliation":[]},{"given":"Xueqiang","family":"Lyu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,16]]},"reference":[{"key":"3629_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108220","volume":"121","author":"X Wang","year":"2022","unstructured":"Wang, X., Zheng, S., Yang, R., Zheng, A., Chen, Z., Tang, J., Luo, B.: Pedestrian attribute recognition: a survey. Pattern Recognition 121, 108220 (2022)","journal-title":"Pattern Recognition"},{"key":"3629_CR2","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.neucom.2020.12.005","volume":"432","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Han, C., Yao, G., Zhou, W.: Mapd: an improved multi-attribute pedestrian detection in a crowd. Neurocomputing 432, 101\u2013110 (2021)","journal-title":"Neurocomputing"},{"key":"3629_CR3","doi-asserted-by":"publisher","unstructured":"Dong, Q., Zhu, X., Gong, S.: Person search by text attribute query as zero-shot learning. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3651\u20133660 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00375","DOI":"10.1109\/ICCV.2019.00375"},{"key":"3629_CR4","doi-asserted-by":"crossref","unstructured":"Li, W., Hou, S., Zhang, C., Cao, C., Liu, X., Huang, Y., Zhao, Y.: An in-depth exploration of person re-identification and gait recognition in cloth-changing conditions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13824\u201313833 (2023)","DOI":"10.1109\/CVPR52729.2023.01328"},{"key":"3629_CR5","doi-asserted-by":"publisher","unstructured":"Li, D., Chen, X., Zhang, Z., Huang, K.: Pose guided deep model for pedestrian attribute recognition in surveillance scenarios. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2018). https:\/\/doi.org\/10.1109\/ICME.2018.8486604","DOI":"10.1109\/ICME.2018.8486604"},{"key":"3629_CR6","doi-asserted-by":"crossref","unstructured":"Zhao, X., Sang, L., Ding, G., Guo, Y., Jin, X.: Grouping attribute recognition for pedestrian with joint recurrent learning. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (2018)","DOI":"10.24963\/ijcai.2018\/441"},{"key":"3629_CR7","doi-asserted-by":"publisher","unstructured":"Sudowe, P., Spitzer, H., Leibe, B.: Person attribute recognition with a jointly-trained holistic CNN model. In: 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), pp. 329\u2013337 (2015). https:\/\/doi.org\/10.1109\/ICCVW.2015.51","DOI":"10.1109\/ICCVW.2015.51"},{"key":"3629_CR8","doi-asserted-by":"crossref","unstructured":"Sarafianos, N., Xu, X., Kakadiaris, I.A.: Deep imbalanced attribute classification using visual attention aggregation. CoRR arxiv:1807.03903 (2018)","DOI":"10.1007\/978-3-030-01252-6_42"},{"key":"3629_CR9","unstructured":"Chen, X., Liu, X., Liu, W., Zhang, X., Zhang, Y., Mei, T.: Attrimeter: an attribute-guided metric interpreter for person re-identification. CoRR arxiv:2103.01451 (2021)"},{"key":"3629_CR10","doi-asserted-by":"publisher","unstructured":"Zeng, H., Ai, H., Zhuang, Z., Chen, L.: Multi-task learning via co-attentive sharing for pedestrian attribute recognition. In: 2020 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2020). https:\/\/doi.org\/10.1109\/ICME46284.2020.9102757","DOI":"10.1109\/ICME46284.2020.9102757"},{"key":"3629_CR11","doi-asserted-by":"publisher","unstructured":"Cao, J., Wei, H., Sun, Y., Zhao, Z., Wang, W., Sun, G., Wang, G.: Multi-task collaborative attention network for pedestrian attribute recognition. In: 2023 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20136 (2023). https:\/\/doi.org\/10.1109\/IJCNN54540.2023.10191574","DOI":"10.1109\/IJCNN54540.2023.10191574"},{"key":"3629_CR12","doi-asserted-by":"publisher","unstructured":"Fang, J., Zhu, B., Chen, Y., Wang, J., Tang, M.: Explicit attention modeling for pedestrian attribute recognition. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 2075\u20132080 (2023). https:\/\/doi.org\/10.1109\/ICME55011.2023.00355","DOI":"10.1109\/ICME55011.2023.00355"},{"key":"3629_CR13","first-page":"498","volume-title":"Artif. Intell. Secur.","author":"X Feng","year":"2019","unstructured":"Feng, X., Li, Y., Du, H., Wang, H.: Research on pedestrian attribute recognition based on semantic segmentation in natural scene. In: Sun, X., Pan, Z., Bertino, E. (eds.) Artif. Intell. Secur., pp. 498\u2013509. Springer, Cham (2019)"},{"key":"3629_CR14","doi-asserted-by":"crossref","unstructured":"Tang, C., Sheng, L., Zhang, Z., Hu, X.: Improving pedestrian attribute recognition with weakly-supervised multi-scale attribute-specific localization. CoRR arxiv:1910.04562 (2019)","DOI":"10.1109\/ICCV.2019.00510"},{"key":"3629_CR15","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. CoRR arxiv:1706.03762 (2017)"},{"key":"3629_CR16","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale. CoRR arxiv:2010.11929 (2020)"},{"key":"3629_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. CoRR arxiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3629_CR18","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"3629_CR19","unstructured":"Lanchantin, J., Wang, T., Ordonez, V., Qi, Y.: General multi-label image classification with transformers. CoRR arxiv:2011.14027 (2020)"},{"key":"3629_CR20","unstructured":"Liu, S., Zhang, L., Yang, X., Su, H., Zhu, J.: Query2label: a simple transformer way to multi-label classification. CoRR arxiv:2107.10834 (2021)"},{"issue":"1","key":"3629_CR21","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1109\/TCSVT.2023.3285411","volume":"34","author":"X Fan","year":"2024","unstructured":"Fan, X., Zhang, Y., Lu, Y., Wang, H.: Parformer: transformer-based multi-task network for pedestrian attribute recognition. IEEE Trans. Circuits Syst. Video Technol. 34(1), 411\u2013423 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3285411","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"4","key":"3629_CR22","first-page":"1423","volume":"39","author":"D He","year":"2023","unstructured":"He, D., He, X., Yuan, R., Li, Y., Shen, C.: Lightweight network-based multi-modal feature fusion for face anti-spoofing. Vis. Comput. 39(4), 1423\u20131435 (2023)","journal-title":"Vis. Comput."},{"key":"3629_CR23","doi-asserted-by":"crossref","unstructured":"Yan, J., Liu, Y., Sun, J., Jia, F., Li, S., Wang, T., Zhang, X.: Cross modal transformer: towards fast and robust 3D object detection (2023)","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"3629_CR24","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1007\/978-3-030-69532-3_41","volume-title":"Computer Vision - ACCV 2020","author":"Y Zhong","year":"2021","unstructured":"Zhong, Y., You, S., Neumann, U.: Modeling cross-modal interaction in a multi-detector, multi-modal tracking framework. In: Ishikawa, H., Liu, C.-L., Pajdla, T., Shi, J. (eds.) Computer Vision - ACCV 2020, pp. 683\u2013699. Springer, Cham (2021)"},{"issue":"2","key":"3629_CR25","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.3390\/rs70201798","volume":"7","author":"B Chen","year":"2015","unstructured":"Chen, B., Huang, B., Xu, B.: Comparison of spatiotemporal fusion models: a review. Remote Sens. 7(2), 1798\u20131835 (2015)","journal-title":"Remote Sens."},{"issue":"8","key":"3629_CR26","doi-asserted-by":"publisher","first-page":"4499","DOI":"10.1109\/TNNLS.2021.3116209","volume":"34","author":"Z Xie","year":"2021","unstructured":"Xie, Z., Zhang, W., Sheng, B., Li, P., Chen, C.P.: BaGFN: broad attentive graph fusion network for high-order feature interactions. IEEE Trans. Neural Netw. Learn. Syst. 34(8), 4499\u20134513 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3629_CR27","doi-asserted-by":"crossref","unstructured":"Fu, Y., Wu, X.-J.: A dual-branch network for infrared and visible image fusion. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 10675\u201310680 (2021). IEEE","DOI":"10.1109\/ICPR48806.2021.9412293"},{"key":"3629_CR28","doi-asserted-by":"crossref","unstructured":"Jia, J., Chen, X., Huang, K.: Spatial and semantic consistency regularizations for pedestrian attribute recognition. CoRR arxiv:2109.05686 (2021)","DOI":"10.1109\/ICCV48922.2021.00100"},{"key":"3629_CR29","unstructured":"Jia, J., Huang, H., Chen, X., Huang, K.: Rethinking of pedestrian attribute recognition: a reliable evaluation under zero-shot pedestrian identity setting. CoRR arxiv:2107.03576 (2021)"},{"key":"3629_CR30","doi-asserted-by":"crossref","unstructured":"Li, D., Chen, X., Huang, K.: Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 111\u2013115 (2015). IEEE","DOI":"10.1109\/ACPR.2015.7486476"},{"key":"3629_CR31","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"3629_CR32","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhao, H., Tian, M., Sheng, L., Shao, J., Yi, S., Yan, J., Wang, X.: Hydraplus-net: attentive deep features for pedestrian analysis. CoRR arxiv:1709.09930 (2017)","DOI":"10.1109\/ICCV.2017.46"},{"key":"3629_CR33","doi-asserted-by":"publisher","unstructured":"DENG, Y., Luo, P., Loy, C.C., Tang, X.: Pedestrian attribute recognition at far distance. In: Proceedings of the 22nd ACM International Conference on Multimedia. MM \u201914, pp. 789\u2013792. Association for Computing Machinery, New York, NY, USA (2014). https:\/\/doi.org\/10.1145\/2647868.2654966","DOI":"10.1145\/2647868.2654966"},{"key":"3629_CR34","doi-asserted-by":"crossref","unstructured":"Li, T., Liu, J., Zhang, W., Ni, Y., Wang, W., Li, Z.: Uav-human: a large benchmark for human behavior understanding with unmanned aerial vehicles. CoRR arxiv:2104.00946 (2021)","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"3629_CR35","unstructured":"Loshchilov, I., Hutter, F., et al.: Fixing weight decay regularization in adam. arXiv preprint arXiv:1711.051015 (2017)"},{"key":"3629_CR36","doi-asserted-by":"publisher","first-page":"82656","DOI":"10.1109\/ACCESS.2022.3196650","volume":"10","author":"G Lee","year":"2022","unstructured":"Lee, G., Cho, J.: Stdp-net: improved pedestrian attribute recognition using Swin transformer and semantic self-attention. IEEE Access 10, 82656\u201382667 (2022)","journal-title":"IEEE Access"},{"key":"3629_CR37","doi-asserted-by":"crossref","unstructured":"Yan, S., Yang, Z., Ma, C., Huang, H., Vouga, E., Huang, Q.: Hpnet: Deep primitive segmentation using hybrid representations. CoRR arxiv:2105.10620 (2021)","DOI":"10.1109\/ICCV48922.2021.00275"},{"key":"3629_CR38","unstructured":"Sarfraz, M.S., Schumann, A., Wang, Y., Stiefelhagen, R.: Deep view-sensitive pedestrian attribute inference in an end-to-end model (2017)"},{"key":"3629_CR39","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.patrec.2022.10.003","volume":"163","author":"Z Liu","year":"2022","unstructured":"Liu, Z., Zhang, Z., Li, D., Zhang, P., Shan, C.: Dual-branch self-attention network for pedestrian attribute recognition. Pattern Recognit. Lett. 163, 112\u2013120 (2022). https:\/\/doi.org\/10.1016\/j.patrec.2022.10.003","journal-title":"Pattern Recognit. Lett."},{"key":"3629_CR40","unstructured":"Zhang, J., Ren, P., Li, J.: Deep template matching for pedestrian attribute recognition with the auxiliary supervision of attribute-wise keypoints. CoRR arxiv:2011.06798 (2020)"},{"key":"3629_CR41","doi-asserted-by":"crossref","unstructured":"Tan, Z., Yang, Y., Wan, J., Guo, G., Li, S.: Relation-aware pedestrian attribute recognition with graph convolutional networks. In: AAAI Conference on Artificial Intelligence (2020). https:\/\/api.semanticscholar.org\/CorpusID:212856067","DOI":"10.1609\/aaai.v34i07.6883"},{"key":"3629_CR42","doi-asserted-by":"crossref","unstructured":"Li, W., Cao, Z., Feng, J., Zhou, J., Lu, J.: Label2Label: a language modeling framework for multi-attribute learning (2022)","DOI":"10.1007\/978-3-031-19775-8_33"},{"key":"3629_CR43","doi-asserted-by":"crossref","unstructured":"Jia, J., Gao, N., He, F., Chen, X., Huang, K.: Learning disentangled attribute representations for robust pedestrian attribute recognition. In: AAAI Conference on Artificial Intelligence (2022). https:\/\/api.semanticscholar.org\/CorpusID:250290850","DOI":"10.1609\/aaai.v36i1.19991"},{"key":"3629_CR44","doi-asserted-by":"publisher","first-page":"5623","DOI":"10.1109\/TIFS.2023.3311584","volume":"18","author":"J Wu","year":"2023","unstructured":"Wu, J., Huang, Y., Gao, M., Gao, Z., Zhao, J., Shi, J., Zhang, A.: Exponential information bottleneck theory against intra-attribute variations for pedestrian attribute recognition. IEEE Trans. Inf. Forensics Secur. 18, 5623 (2023)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"3629_CR45","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.neucom.2023.02.019","volume":"531","author":"D Weng","year":"2023","unstructured":"Weng, D., Tan, Z., Fang, L., Guo, G.: Exploring attribute localization and correlation for pedestrian attribute recognition. Neurocomputing 531, 140\u2013150 (2023)","journal-title":"Neurocomputing"},{"issue":"10","key":"3629_CR46","doi-asserted-by":"publisher","first-page":"6994","DOI":"10.1109\/TCSVT.2022.3178144","volume":"32","author":"X Cheng","year":"2022","unstructured":"Cheng, X., Jia, M., Wang, Q., Zhang, J.: A simple visual-textual baseline for pedestrian attribute recognition. IEEE Trans. Circuits Syst. Video Technol. 32(10), 6994\u20137004 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3629_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110194","volume":"148","author":"J Shen","year":"2024","unstructured":"Shen, J., Guo, T., Zuo, X., Fan, H., Yang, W.: Sspnet: scale and spatial priors guided generalizable and interpretable pedestrian attribute recognition. Pattern Recognit. 148, 110194 (2024)","journal-title":"Pattern Recognit."},{"key":"3629_CR48","doi-asserted-by":"crossref","unstructured":"Thakare, K.V., Dogra, D.P., Choi, H., Kim, H., Kim, I.-J.: Let\u2019s observe them over time: an improved pedestrian attribute recognition approach. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 708\u2013717 (2024)","DOI":"10.1109\/WACV57701.2024.00076"},{"key":"3629_CR49","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part VIII 14, pp. 483\u2013499 (2016). Springer","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"3629_CR50","doi-asserted-by":"crossref","unstructured":"Fang, H.-S., Xie, S., Tai, Y.-W., Lu, C.: Rmpe: Regional multi-person pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2334\u20132343 (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"3629_CR51","doi-asserted-by":"publisher","unstructured":"Zhang, L.: ACMFNet. https:\/\/doi.org\/10.5281\/zenodo.1234 . https:\/\/github.com\/luffy-op\/ACMFNet","DOI":"10.5281\/zenodo.1234"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03629-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03629-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03629-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T06:21:30Z","timestamp":1744784490000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03629-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":51,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["3629"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03629-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4292609\/v1","asserted-by":"object"}]},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]},"assertion":[{"value":"1 September 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There are no conflict of interest in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}