{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T01:09:58Z","timestamp":1763341798781,"version":"3.45.0"},"reference-count":52,"publisher":"Tech Science Press","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.060783","type":"journal-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T04:14:29Z","timestamp":1743048869000},"page":"3389-3410","source":"Crossref","is-referenced-by-count":0,"title":["VPM-Net: Person Re-ID Network Based on Visual Prompt Technology and Multi-Instance Negative Pooling"],"prefix":"10.32604","volume":"83","author":[{"given":"Haitao","family":"Xie","sequence":"first","affiliation":[]},{"given":"Yuliang","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yunjie","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Lingyu","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Zhizhi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhiwei","family":"Ye","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"15013","article-title":"TransReID: transformer-based object re-identification","author":"He","year":"2021"},{"key":"ref2","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","article-title":"Bag of tricks and a strong baseline for deep person re-identification","author":"Luo","year":"2019"},{"key":"ref3","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7297","article-title":"NFormer: robust person re-identification with neighbor transformer","author":"Wang","year":"2022"},{"key":"ref4","series-title":"2020 IEEE International Joint Conference on Biometrics (IJCB)","first-page":"1","article-title":"Cross modal person re-identification with visual-textual queries","author":"Farooq","year":"2020"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"6609","DOI":"10.1109\/TMM.2024.3355644","article-title":"Cross-modal adaptive dual association for text-to-image person retrieval","volume":"26","author":"Lin","year":"2024","journal-title":"IEEE Trans Multimed"},{"key":"ref6","unstructured":"Bao L, Wei L, Qiu X, Zhou W, Li H, Tian Q. Learning transferable pedestrian representation from multimodal information supervision. arXiv:2304.05554. 2023."},{"key":"ref7","doi-asserted-by":"crossref","first-page":"4057","DOI":"10.1109\/TIP.2021.3068825","article-title":"Cross-modal knowledge adaptation for language-based person search","volume":"30","author":"Chen","year":"2021","journal-title":"IEEE Trans Image Process"},{"key":"ref8","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"686","article-title":"Deep cross-modal projection learning for image-text matching","author":"Zhang","year":"2018"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3383184","article-title":"Dual-path convolutional image-text embeddings with instance loss","volume":"16","author":"Zheng","year":"2020","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.neucom.2022.04.081","article-title":"TIPCB: a simple but effective part-based convolutional baseline for text-based person search","volume":"494","author":"Chen","year":"2022","journal-title":"Neurocomputing"},{"key":"ref11","unstructured":"Ding Z, Ding C, Shao Z, Tao D. Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv:2107.12666. 2021."},{"key":"ref12","first-page":"11189","article-title":"Pose-guided multi-granularity attention network for text-based person search","volume":"34","author":"Jing","year":"2020","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref13","series-title":"European Conference on Computer Vision","first-page":"402","article-title":"Vitaa: visual-textual attributes alignment in person search by natural language","author":"Wang","year":"2020"},{"key":"ref14","series-title":"European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"ref15","first-page":"465","article-title":"An empirical study of clip for text-based person search","volume":"38","author":"Cao","year":"2024","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref16","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1970","article-title":"Person search with natural language description","author":"Li","year":"2017"},{"key":"ref17","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2787","article-title":"Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval","author":"Jiang","year":"2023"},{"key":"ref18","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. 2014."},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"ref20","series-title":"2018 IEEE Winter Conference on Applications of Computer Vision (WACV)","first-page":"1879","article-title":"Improving text-based person search by spatial matching and adaptive threshold","author":"Chen","year":"2018"},{"key":"ref21","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1890","article-title":"Identity-aware textual-visual matching with latent co-attention","author":"Li","year":"2017"},{"key":"ref22","series-title":"European Conference on computer vision","first-page":"104","article-title":"UNITER: Universal image-text representation learning","author":"Chen","year":"2020"},{"key":"ref23","doi-asserted-by":"crossref","unstructured":"Yan S, Dong N, Zhang L, Tang J. CLIP-driven fine-grained text-image person re-identification. arXiv:2210.10276. 2022.","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref24","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805. 2018."},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"Wang Z, Zhu A, Xue J, Wan X, Liu C, Wang T, et al. CAIBC: capturing all-round information beyond color for text-based person retrieval. arXiv:2209.05773. 2022.","DOI":"10.1145\/3503161.3548057"},{"key":"ref26","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1624","article-title":"Language-guided person search via color reasoning","author":"Wu","year":"2021"},{"key":"ref27","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"209","article-title":"DSSL: deep surroundings-person separation learning for text-based person retrieval","author":"Zhu","year":"2021"},{"key":"ref28","series-title":"Proc AAAI Conf Artif Intell","first-page":"4477","article-title":"AXM-Net: implicit cross-modal feature alignment for person re-identification","volume":"36","author":"Farooq","year":"2022"},{"key":"ref29","doi-asserted-by":"crossref","unstructured":"Shao Z, Zhang X, Fang M, Lin Z, Wang J, Ding C. Learning granularity-unified representations for text-to-image person re-identification. arXiv:2207.07802. 2022.","DOI":"10.1145\/3503161.3548028"},{"key":"ref30","unstructured":"Yan S, Tang H, Zhang L, Tang J. Image-specific information suppression and implicit local alignment for text-based person search. arXiv:2208.14365. 2022."},{"key":"ref31","first-page":"3164","article-title":"3D person re-identification based on global semantic guidance and local feature aggregation","volume":"32","author":"Wang","year":"2023","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"5589","DOI":"10.1109\/TCSVT.2024.3358850","article-title":"Pedestrian 3D shape understanding for person re-identification via multi-view learning","volume":"34","author":"Yu","year":"2024","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref33","doi-asserted-by":"crossref","unstructured":"Han X, He S, Zhang L, Xiang T. Text-based person search with limited data. arXiv:211010807. 2021.","DOI":"10.5244\/C.35.10"},{"key":"ref34","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"ref35","doi-asserted-by":"crossref","unstructured":"Li X, Yin X, Li C, Zhang P, Hu X, Zhang L, et al. Oscar: object-semantics aligned pre-training for vision-language tasks. 2020. doi:10.48550\/arXiv.2004.06165.","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref36","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11162","article-title":"VirTex: learning visual representations from textual annotations","author":"Desai","year":"2021"},{"key":"ref37","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9826","article-title":"Thinking fast and slow: efficient text-to-visual retrieval with transformers","author":"Miech","year":"2021"},{"key":"ref38","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref39","doi-asserted-by":"crossref","unstructured":"Sennrich R, Haddow B, Birch A. Neural machine translation of rare words with subword units. arXiv:1508.07909. 2015.","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref40","unstructured":"Liu Z, Wang Y, Vaidya S, Ruehle F, Halverson J, Soljacic M, et al. KAN: kolmogorov-arnold networks. arXiv:2404.19756. 2024."},{"key":"ref41","doi-asserted-by":"crossref","unstructured":"Li C, Liu X, Li W, Wang C, Liu H, Yuan Y. U-KAN makes strong backbone for medical image segmentation and generation. arXiv:2406.02918. 2024.","DOI":"10.1609\/aaai.v39i5.32491"},{"key":"ref42","series-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"ref43","series-title":"Advances in Neural Information Processing Systems 29","first-page":"1849","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"Sohn","year":"2016"},{"key":"ref44","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2840","article-title":"Sampling matters in deep embedding learning","author":"Wu","year":"2017"},{"key":"ref45","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5382","article-title":"Deep metric learning via facility location","author":"Oh Song","year":"2017"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"2872","DOI":"10.1109\/TPAMI.2021.3054775","article-title":"Deep learning for person re-identification: a survey and outlook","volume":"44","author":"Ye","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"4252","DOI":"10.1007\/s00034-023-02314-5","article-title":"Efficient attention branch network with combined loss function for automatic speaker verification spoof detection","volume":"42","author":"Rostami","year":"2023","journal-title":"Circuits Syst Signal Process"},{"key":"ref48","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"5814","article-title":"Adversarial representation learning for text-to-image matching","author":"Sarafianos","year":"2019"},{"key":"ref49","unstructured":"Gao C, Cai G, Jiang X, Zheng F, Zhang J, Gong Y, et al. Contextual non-local alignment over full-scale representation for text-based person search. arXiv:2101.03036. 2021."},{"key":"ref50","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"1984","article-title":"Look before you leap: improving text-based person retrieval by learning a consistent cross-modal common manifold","author":"Wang","year":"2022"},{"key":"ref51","series-title":"ICASSP 2022\u20142022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"2724","article-title":"Learning semantic-aligned feature representation for text-based person search","author":"Li","year":"2022"},{"key":"ref52","doi-asserted-by":"crossref","unstructured":"Shu X, Wen W, Wu H, Chen K, Song Y, Qiao R, et al. See finer, see more: implicit modality alignment for text-based person retrieval. arXiv:2208.08608. 2022.","DOI":"10.1007\/978-3-031-25072-9_42"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-83-2\/TSP_CMC_60783\/TSP_CMC_60783.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T01:05:17Z","timestamp":1763341517000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v83n2\/60538"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":52,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.060783","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2025]]}}}