{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:03:47Z","timestamp":1784099027967,"version":"3.55.0"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,6,25]],"date-time":"2021-06-25T00:00:00Z","timestamp":1624579200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,6,25]],"date-time":"2021-06-25T00:00:00Z","timestamp":1624579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004489","name":"Mitacs","doi-asserted-by":"publisher","award":["IT12446"],"award-info":[{"award-number":["IT12446"]}],"id":[{"id":"10.13039\/501100004489","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Image Video Proc."],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Recent years have witnessed a substantial increase in the deep learning (DL) architectures proposed for visual recognition tasks like person re-identification, where individuals must be recognized over multiple distributed cameras. Although these architectures have greatly improved the state-of-the-art accuracy, the computational complexity of the convolutional neural networks (CNNs) commonly used for feature extraction remains an issue, hindering their deployment on platforms with limited resources, or in applications with real-time constraints. There is an obvious advantage to accelerating and compressing DL models without significantly decreasing their accuracy. However, the source (pruning) domain differs from operational (target) domains, and the domain shift between image data captured with different non-overlapping camera viewpoints leads to lower recognition accuracy. In this paper, we investigate the prunability of these architectures under different design scenarios. This paper first revisits pruning techniques that are suitable for reducing the computational complexity of deep CNN networks applied to person re-identification. Then, these techniques are analyzed according to their pruning criteria and strategy and according to different scenarios for exploiting pruning methods to fine-tuning networks to target domains. Experimental results obtained using DL models with ResNet feature extractors, and multiple benchmarks re-identification datasets, indicate that pruning can considerably reduce network complexity while maintaining a high level of accuracy. In scenarios where pruning is performed with large pretraining or fine-tuning datasets, the number of FLOPS required by ResNet architectures is reduced by half, while maintaining a comparable rank-1 accuracy (within 1% of the original model). Pruning while training a larger CNNs can also provide a significantly better performance than fine-tuning smaller ones.<\/jats:p>","DOI":"10.1186\/s13640-021-00562-6","type":"journal-article","created":{"date-parts":[[2021,6,25]],"date-time":"2021-06-25T09:03:14Z","timestamp":1624611794000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Exploiting prunability for person re-identification"],"prefix":"10.1186","volume":"2021","author":[{"given":"Hugo","family":"Masson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2069-0753","authenticated-orcid":false,"given":"Amran","family":"Bhuiyan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le Thanh","family":"Nguyen-Meidine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehrsan","family":"Javan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parthipan","family":"Siva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ismail Ben","family":"Ayed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Granger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,6,25]]},"reference":[{"key":"562_CR1","doi-asserted-by":"crossref","unstructured":"J. Huang, V. Rathod, C. Sun, M. Zhu, A. Korattikara, A. Fathi, I. Fischer, Z. Wojna, Y. Song, S. Guadarrama, K. Murphy, in Proc. IEEE Conf. Vis. Pattern Recognit. (CVPR). Speed\/accuracy trade-offs for modern convolutional object detectors (Honolulu, 2017), pp. 7310\u20137311.","DOI":"10.1109\/CVPR.2017.351"},{"key":"562_CR2","doi-asserted-by":"crossref","unstructured":"E. Ahmed, M. Jones, T. K. Marks, in Proc. IEEE Conf. Vis. Pattern Recognit. (CVPR). An improved deep learning architecture for person re-identification (Boston, 2015), pp. 3908\u20133916.","DOI":"10.1109\/CVPR.2015.7299016"},{"key":"562_CR3","unstructured":"A. Hermans, L. Beyer, B. Leibe, In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)."},{"key":"562_CR4","first-page":"791","volume-title":"Proc. European Conf. Comput. Vis. (ECCV)","author":"R. R. Varior","year":"2016","unstructured":"R. R. Varior, M. Haloi, G. Wang, in Proc. European Conf. Comput. Vis. (ECCV). Gated siamese convolutional neural network architecture for human reidentification (SpringerAmsterdam, 2016), pp. 791\u2013808."},{"key":"562_CR5","doi-asserted-by":"crossref","unstructured":"W. Chen, X. Chen, J. Zhang, K. Huang, in Proc. IEEE Conf. Vis. Pattern Recognit. (CVPR). Beyond triplet loss: a deep quadruplet network for person reidentification (Honolulu, 2017), pp. 403\u2013412.","DOI":"10.1109\/CVPR.2017.145"},{"key":"562_CR6","unstructured":"M. Geng, Y. Wang, Y. Shi, K. Yan, M. Geng, Y. Tian, T. Xiang, in Proc. IEEE Conf. on Multimedia Big Data (BigMM). Deep transfer learning for person reidentification (Xi\u2019an, 2018), pp. 1\u20135."},{"key":"562_CR7","doi-asserted-by":"crossref","unstructured":"D. Cheng, Y. Gong, S. Zhou, J. Wang, N. Zheng, in Proc. IEEE Conf. Vis. Pattern Recognit. (CVPR). Person re-identification by multi-channel parts-based cnn with improved triplet loss function (Las Vegas, 2016), pp. 1335\u20131344.","DOI":"10.1109\/CVPR.2016.149"},{"issue":"7","key":"562_CR8","first-page":"3492","volume":"26","author":"H. Liu","year":"2017","unstructured":"H. Liu, J. Feng, M. Qi, J. Jiang, S. Yan, End-to-end comparative attention networks for person re-identification. IEEE Trans. on TIP. 26(7), 3492\u20133506 (2017).","journal-title":"IEEE Trans. on TIP"},{"key":"562_CR9","doi-asserted-by":"crossref","unstructured":"A. Bhuiyan, Y. Liu, P. Siva, M. Javan, I. B. Ayed, E. Granger, in Proc. IEEE\/CVF Winter Conf. on Applications of Computer Vision. Pose guided gated fusion for person reidentification (Aspen, 2020), pp. 2675\u20132684.","DOI":"10.1109\/WACV45572.2020.9093370"},{"key":"562_CR10","first-page":"147","volume-title":"Proc. European Conf. Comput. Vis. (ECCV)","author":"A. Bhuiyan","year":"2016","unstructured":"A. Bhuiyan, A. Perina, V. Murino, in Proc. European Conf. Comput. Vis. (ECCV). Person re-identification by discriminatively selecting parts and features (SpringerZurich, 2016), pp. 147\u2013161."},{"key":"562_CR11","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, in Proc. IEEE Conf. Vis. Pattern Recognit. (CVPR). Deep residual learning for image recognition (Las Vegas, 2016), pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"562_CR12","unstructured":"S. Han, H. Mao, W. J. Dally, in International Conference on Learning Representations (ICLR). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding (San Juan, 2016). Conference Track Proceedings."},{"key":"562_CR13","unstructured":"S. Han, J. Pool, J. Tran, W. Dally, in Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS), vol. 1. Learning both weights and connections for efficient neural network (Montreal, 2015), pp. 1135\u20131143."},{"key":"562_CR14","doi-asserted-by":"crossref","unstructured":"Y. Lu, A. Kumar, S. Zhai, Y. Cheng, T. Javidi, R. Feris, in Proc. IEEE Conf. Vis. Pattern Recognit. (CVPR). Fully-adaptive feature sharing in multi-task networks with applications in person attribute classification (Honolulu, 2017), pp. 5334\u20135343.","DOI":"10.1109\/CVPR.2017.126"},{"key":"562_CR15","doi-asserted-by":"crossref","unstructured":"R. Rigamonti, A. Sironi, V. Lepetit, P. Fua, in Proc. IEEE Conf. Vis. Pattern Recognit. (CVPR). Learning separable filters (Portland, 2013), pp. 2754\u20132761.","DOI":"10.1109\/CVPR.2013.355"},{"key":"562_CR16","unstructured":"E. L. Denton, W. Zaremba, J. Bruna, Y. LeCun, R. Fergus, in Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS), vol. 1. Exploiting linear structure within convolutional networks for efficient evaluation (Montreal, 2015), pp. 1269\u20131277."},{"key":"562_CR17","volume-title":"Proceedings of the British Machine Vision Conference","author":"M. Jaderberg","year":"2014","unstructured":"M. Jaderberg, A. Vedaldi, A. Zisserman, in Proceedings of the British Machine Vision Conference. Speeding up Convolutional Neural Networks with Low Rank Expansions (BMVA PressNottingham, 2014)."},{"key":"562_CR18","unstructured":"V. Lebedev, Y. Ganin, M. Rakhuba, I. Oseledets, V. Lempitsky, in 3rd International Conference on Learning Representations, ICLR. Speeding-up convolutional neural networks using fine-tuned CP-decomposition (San Diego, 2015). Conference Track Proceedings 2015."},{"key":"562_CR19","unstructured":"C. Tai, T. Xiao, Y. Zhang, X. Wang, E. Weinan, in 4th International Conference on Learning Representations, ICLR. Convolutional neural networks with low-rank regularization (San Juan, 2016). Conference Track Proceedings 2016."},{"key":"562_CR20","first-page":"2990","volume-title":"International conference on machine learning (ICML)","author":"T. Cohen","year":"2016","unstructured":"T. Cohen, M. Welling, in International conference on machine learning (ICML). Group equivariant convolutional networks (PMLRNew York City, 2016), pp. 2990\u20132999."},{"key":"562_CR21","doi-asserted-by":"crossref","unstructured":"H. Van Hasselt, A. Guez, D. Silver, in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 30, No. 1. Deep reinforcement learning with double q-learning (Phoenix, 2016).","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"562_CR22","first-page":"2217","volume-title":"international conference on machine learning (ICML)","author":"W. Shang","year":"2016","unstructured":"W. Shang, K. Sohn, D. Almeida, H. Lee, in international conference on machine learning (ICML). Understanding and improving convolutional neural networks via concatenated rectified linear units (PMLRNew York City, 2016), pp. 2217\u20132225."},{"key":"562_CR23","first-page":"1889","volume-title":"International conference on machine learning (ICML)","author":"S. Dieleman","year":"2016","unstructured":"S. Dieleman, J. De Fauw, K. Kavukcuoglu, in International conference on machine learning (ICML). Exploiting cyclic symmetry in convolutional neural networks (PMLRNew York City, 2016), pp. 1889\u20131898."},{"key":"562_CR24","doi-asserted-by":"crossref","unstructured":"C. Bucilua\u030c, R. Caruana, A. Niculescu-Mizil, in Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Model compression, (2006), pp. 535\u2013541.","DOI":"10.1145\/1150402.1150464"},{"key":"562_CR25","unstructured":"G. Hinton, O. Vinyals, J. Dean, Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"562_CR26","unstructured":"P. Luo, Z. Zhu, Z. Liu, X. Wang, X. Tang, et al, in AAAI. Face model compression by distilling knowledge from neurons, (2016), pp. 3560\u20133566."},{"key":"562_CR27","unstructured":"T. Chen, I. Goodfellow, J. Shlens, Net2net: accelerating learning via knowledge transfer. arXiv preprint arXiv:1511.05641 (2015)."},{"key":"562_CR28","unstructured":"Y. Gong, L. Liu, M. Yang, L. Bourdev, in 6th International Conference on Learning Representations, ICLR. Compressing deep convolutional networks using vector quantization (Vancouver, 2018). Conference Track Proceedings 2018."},{"key":"562_CR29","first-page":"2285","volume-title":"International conference on machine learning (ICML)","author":"W. Chen","year":"2015","unstructured":"W. Chen, J. Wilson, S. Tyree, K. Weinberger, Y. Chen, in International conference on machine learning (ICML). Compressing neural networks with the hashing trick (PMLRLille, 2015), pp. 2285\u20132294."},{"key":"562_CR30","first-page":"598","volume-title":"Proceedings of the 2nd International Conference on Neural Information Processing Systems (NIPS)","author":"Y. Le Cun","year":"1989","unstructured":"Y. Le Cun, J. S. Denker, S. A. Solla, in Proceedings of the 2nd International Conference on Neural Information Processing Systems (NIPS). Optimal brain damage (MIT PressCambridge, 1989), pp. 598\u2013605."},{"key":"562_CR31","unstructured":"B. Hassibi, D. G. Stork, in Proceedings of the 5th International Conference on Neural Information Processing Systems (NIPS). Second order derivatives for network pruning: optimal brain surgeon (Denver, 1992), pp. 164\u2013171."},{"key":"562_CR32","unstructured":"P. Molchanov, S. Tyree, T. Karras, T. Aila, J. Kautz, Pruning Convolutional Neural Networks for Resource Efficient Transfer Learning. CoRR abs\/1611.06440 (2016)."},{"key":"562_CR33","unstructured":"H. Li, A. Kadav, I. Durdanovic, H. Samet, H. P. Graf, Pruning Filters for Efficient ConvNets. CoRR abs\/1608.08710 (2016)."},{"key":"562_CR34","unstructured":"J. -H. Luo, J. Wu, An Entropy-based Pruning Method for CNN Compression. CoRR abs\/1706.05791 (2017)."},{"key":"562_CR35","doi-asserted-by":"crossref","unstructured":"Y. He, X. Zhang, J. Sun, in Proceedings of the IEEE International Conference on Computer Vision. Channel pruning for accelerating very deep neural networks, (2017), pp. 1389\u20131397.","DOI":"10.1109\/ICCV.2017.155"},{"key":"562_CR36","doi-asserted-by":"crossref","unstructured":"Y. He, X. Dong, G. Kang, Y. Fu, Y. Yang, in Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI). Progressive deep neural networks acceleration via soft filter pruning (Stockholm, 2018), pp. 2234\u20132240.","DOI":"10.24963\/ijcai.2018\/309"},{"key":"562_CR37","doi-asserted-by":"crossref","unstructured":"L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, Q. Tian, in Proceedings of the IEEE international conference on computer vision. Scalable person re-identification: A benchmark (Santiago, 2015), pp. 1116\u20131124.","DOI":"10.1109\/ICCV.2015.133"},{"key":"562_CR38","doi-asserted-by":"crossref","unstructured":"W. Li, R. Zhao, T. Xiao, X. Wang, in Proceedings of the IEEE conference on computer vision and pattern recognition. Deepreid: Deep filter pairing neural network for person re-identification (Columbus, 2014), pp. 152\u2013159.","DOI":"10.1109\/CVPR.2014.27"},{"key":"562_CR39","first-page":"17","volume-title":"Proc. European Conf. Comput. Vis. (ECCV)","author":"E. Ristani","year":"2016","unstructured":"E. Ristani, F. Solera, R. Zou, R. Cucchiara, C. Tomasi, in Proc. European Conf. Comput. Vis. (ECCV). Performance measures and a data set for multi-target, multi-camera tracking (SpringerAmsterdam, 2016), pp. 17\u201335."},{"key":"562_CR40","doi-asserted-by":"crossref","unstructured":"D. Yi, Z. Lei, S. Liao, S. Z. Li, in IEEE 22nd International Conference on Pattern Recognition. Deep metric learning for person re-identification (Columbus, 2014), pp. 34\u201339.","DOI":"10.1109\/ICPR.2014.16"},{"key":"562_CR41","unstructured":"A. Hermans, L. Beyer, B. Leibe, In Defense of the Triplet Loss for Person Re-Identification. arXiv e-prints arXiv-1703 (2017)."},{"key":"562_CR42","unstructured":"L. Zheng, Y. Yang, A. G. Hauptmann, Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984 (2016)."},{"key":"562_CR43","doi-asserted-by":"crossref","unstructured":"Y. Sun, L. Zheng, Y. Yang, Q. Tian, S. Wang, in Proceedings of the European conference on computer vision (ECCV). Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline) (Munich, 2018), pp. 480\u2013496.","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"562_CR44","doi-asserted-by":"crossref","unstructured":"C. Su, J. Li, S. Zhang, J. Xing, W. Gao, Q. Tian, in Proceedings of the IEEE international conference on computer vision. Pose-driven deep convolutional model for person reidentification (Venice, 2017), pp. 3960\u20133969.","DOI":"10.1109\/ICCV.2017.427"},{"issue":"6","key":"562_CR45","doi-asserted-by":"publisher","first-page":"2860","DOI":"10.1109\/TIP.2019.2891888","volume":"28","author":"H. Yao","year":"2019","unstructured":"H. Yao, S. Zhang, R. Hong, Y. Zhang, C. Xu, Q. Tian, Deep representation learning with part loss for person re-identification. IEEE Trans. Image Process.28(6), 2860\u20132871 (2019).","journal-title":"IEEE Trans. Image Process."},{"key":"562_CR46","doi-asserted-by":"crossref","unstructured":"L. Zhao, X. Li, Y. Zhuang, J. Wang, in Proceedings of the IEEE international conference on computer vision, (CVPR). Deeply-learned part-aligned representations for person re-identification (Honolulu, 2017), pp. 3219\u20133228.","DOI":"10.1109\/ICCV.2017.349"},{"issue":"10","key":"562_CR47","doi-asserted-by":"publisher","first-page":"2993","DOI":"10.1016\/j.patcog.2015.04.005","volume":"48","author":"S. Ding","year":"2015","unstructured":"S. Ding, L. Lin, G. Wang, H. Chao, Deep feature learning with relative distance comparison for person re-identification. Pattern Recog.48(10), 2993\u20133003 (2015).","journal-title":"Pattern Recog."},{"key":"562_CR48","doi-asserted-by":"crossref","unstructured":"R. Yu, Z. Dou, S. Bai, Z. Zhang, Y. Xu, X. Bai, in Proceedings of the European conference on computer vision (ECCV). Hard-aware point-to-set deep metric for person reidentification (Munich, 2018), pp. 188\u2013204.","DOI":"10.1007\/978-3-030-01270-0_12"},{"key":"562_CR49","doi-asserted-by":"crossref","unstructured":"N. Wojke, A. Bewley, in 2018 IEEE winter conference on applications of computer vision (WACV). Deep cosine metric learning for person re-identification (Lake Tahoe, 2018), pp. 748\u2013756.","DOI":"10.1109\/WACV.2018.00087"},{"key":"562_CR50","unstructured":"L. Wu, C. Shen, An entropy-based pruning method for cnn compression. arXiv preprint arXiv:1706.05791 (2017)."},{"key":"562_CR51","unstructured":"J. Bromley, I. Guyon, Y. LeCun, E. S\u00e4ckinger, R. Shah, in Advances in neural information processing systems (NIPS), vol. 6. Signature verification using a \u201cSiamese\u201d time delay neural network (Denver, 1992), pp. 737\u201344."},{"key":"562_CR52","first-page":"135","volume-title":"European Conference on Computer Vision","author":"R. R. Varior","year":"2016","unstructured":"R. R. Varior, B. Shuai, J. Lu, D. Xu, G. Wang, in European Conference on Computer Vision. A siamese long short-term memory architecture for human re-identification (SpringerAmsterdam, 2016), pp. 135\u2013153."},{"key":"562_CR53","doi-asserted-by":"crossref","unstructured":"F. Wang, W. Zuo, L. Lin, D. Zhang, L. Zhang, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Joint learning of single-image and cross-image representations for person re-identification (Las Vegas, 2016), pp. 1288\u20131296.","DOI":"10.1109\/CVPR.2016.144"},{"key":"562_CR54","doi-asserted-by":"crossref","unstructured":"K. Zhou, Y. Yang, A. Cavallaro, T. Xiang, in Proceedings of the IEEE International Conference on Computer Vision (ICCV). Omni-scale feature learning for person re-identification (Seoul, 2019), pp. 3702\u20133712.","DOI":"10.1109\/ICCV.2019.00380"},{"key":"562_CR55","doi-asserted-by":"crossref","unstructured":"H. Luo, Y. Gu, X. Liao, S. Lai, W. Jiang, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. Bag of tricks and a strong baseline for deep person reidentification (Seoul, 2019).","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"562_CR56","doi-asserted-by":"crossref","unstructured":"Z. Dai, M. Chen, X. Gu, S. Zhu, P. Tan, in Proceedings of the IEEE International Conference on Computer Vision (ICCV). Batch dropblock network for person re-identification and beyond (Seoul, 2019), pp. 3691\u20133701.","DOI":"10.1109\/ICCV.2019.00379"},{"key":"562_CR57","doi-asserted-by":"crossref","unstructured":"Y. Shen, T. Xiao, H. Li, S. Yi, X. Wang, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). End-to-end deep kronecker-product matching for person reidentification (Salt Lake City, 2018), pp. 6886\u20136895.","DOI":"10.1109\/CVPR.2018.00720"},{"key":"562_CR58","doi-asserted-by":"publisher","first-page":"7306","DOI":"10.1109\/TIP.2020.3000904","volume":"29","author":"N. Martinel","year":"2020","unstructured":"N. Martinel, G. L. Foresti, C. Micheloni, Deep pyramidal pooling with attention for person re-identification. IEEE Trans. Image Process.29:, 7306\u20137316 (2020).","journal-title":"IEEE Trans. Image Process."},{"key":"562_CR59","doi-asserted-by":"crossref","unstructured":"M. Zheng, S. Karanam, Z. Wu, R. J. Radke, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Re-identification with consistent attentive siamese networks (Long Beach, 2019), pp. 5735\u20135744.","DOI":"10.1109\/CVPR.2019.00588"},{"key":"562_CR60","doi-asserted-by":"crossref","unstructured":"G. Chen, C. Lin, L. Ren, J. Lu, J. Zhou, in Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). Self-critical attention learning for person re-identification (Seoul, 2019), pp. 9637\u20139646.","DOI":"10.1109\/ICCV.2019.00973"},{"key":"562_CR61","doi-asserted-by":"crossref","unstructured":"A. Wu, W. -S. Zheng, X. Guo, J. -H. Lai, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Distilled person re-identification: towards a more scalable system (Long Beach, 2019), pp. 1187\u20131196.","DOI":"10.1109\/CVPR.2019.00128"},{"key":"562_CR62","unstructured":"F. Hafner, A. Bhuiyan, J. F. Kooij, E. Granger, A cross-modal distillation network for person re-identification in rgb-depth. arXiv preprint arXiv:1810.11641 (2018)."},{"key":"562_CR63","doi-asserted-by":"crossref","unstructured":"Z. Liu, J. Qin, A. Li, Y. Wang, L. Van Gool, in 2019 IEEE International Conference on Multimedia and Expo (ICME). Adversarial binary coding for efficient person re-identification (Shanghai, 2019), pp. 700\u2013705.","DOI":"10.1109\/ICME.2019.00126"},{"key":"562_CR64","doi-asserted-by":"crossref","unstructured":"D. Mekhazni, A. Bhuiyan, G. Ekladious, E. Granger, in European Conference on Computer Vision, Online. Unsupervised domain adaptation in the dissimilarity space for person re-identification (Springer, 2020), pp. 159\u2013174.","DOI":"10.1007\/978-3-030-58583-9_10"},{"key":"562_CR65","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.neucom.2017.07.019","volume":"272","author":"W. Fang","year":"2018","unstructured":"W. Fang, H. -M. Hu, Z. Hu, S. Liao, B. Li, Perceptual hash-based feature description for person re-identification. Neurocomputing. 272:, 520\u2013531 (2018).","journal-title":"Neurocomputing"},{"key":"562_CR66","doi-asserted-by":"crossref","unstructured":"S. Gong, J. Cheng, Z. Hou, et al., in European Conference on Computer Vision, Online. Faster person re-identification (Springer, 2020), pp. 275\u2013292.","DOI":"10.1007\/978-3-030-58598-3_17"},{"key":"562_CR67","unstructured":"B. O. Ayinde, J. M. Zurada, Building efficient convnets using redundant feature pruning. arXiv, 2018 (2018)."},{"key":"562_CR68","doi-asserted-by":"crossref","unstructured":"Y. He, P. Liu, Z. Wang, Y. Yang, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Filter pruning via geometric median for deep convolutional neural networks acceleration (Long Beach, 2019).","DOI":"10.1109\/CVPR.2019.00447"},{"key":"562_CR69","doi-asserted-by":"crossref","unstructured":"P. Singh, V. K. Verma, P. Rai, V. P. Namboodiri, in 28th International Joint Conference on Artificial Intelligence (IJCAI). Play and Prune: Adaptive filter pruning for deep model compression (Macao, 2019), pp. 3460\u20133466.","DOI":"10.24963\/ijcai.2019\/480"},{"key":"562_CR70","doi-asserted-by":"crossref","unstructured":"X. Ding, G. Ding, J. Han, S. Tang, in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, No. 1. Auto-balanced filter pruning for efficient convolutional neural networks (New Orleans, 2018).","DOI":"10.1609\/aaai.v32i1.12262"},{"key":"562_CR71","unstructured":"J. -H. Luo, H. Zhang, H. -Y. Zhou, C. -W. Xie, J. Wu, W. Lin, Thinet: pruning CNN filters for a thinner net. TPAMI, 2018 (2018)."},{"key":"562_CR72","doi-asserted-by":"crossref","unstructured":"R. Yu, A. Li, C. -F. Chen, J. -H. Lai, V. I. Morariu, X. Han, M. Gao, C. -Y. Lin, L. S. Davis, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Nisp: Pruning networks using neuron importance score propagation (Salt Lake City, 2018), pp. 9194\u20139203.","DOI":"10.1109\/CVPR.2018.00958"},{"key":"562_CR73","doi-asserted-by":"crossref","unstructured":"B. Chu, V. Madhavan, O. Beijbom, J. Hoffman, T. Darrell, Best practices for fine-tuning visual classifiers to new domains. Proc. European Conf. Comput. Vis. (ECCV), 435\u2013442 (2016).","DOI":"10.1007\/978-3-319-49409-8_34"},{"issue":"3","key":"562_CR74","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O. Russakovsky","year":"2015","unstructured":"O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, Imagenet large scale visual recognition challenge. Int. J. Comput. Vis.115(3), 211\u2013252 (2015).","journal-title":"Int. J. Comput. Vis."},{"key":"562_CR75","doi-asserted-by":"crossref","unstructured":"Z. Zhong, L. Zheng, D. Cao, S. Li, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Re-ranking person re-identification with k-reciprocal encoding (Honolulu, 2017), pp. 1318\u20131327.","DOI":"10.1109\/CVPR.2017.389"},{"key":"562_CR76","doi-asserted-by":"crossref","unstructured":"Z. Zheng, L. Zheng, Y. Yang, in Proceedings of the IEEE International Conference on Computer Vision (CVPR). Unlabeled samples generated by gan improve the person re-identification baseline in vitro (Honolulu, 2017), pp. 3754\u20133762.","DOI":"10.1109\/ICCV.2017.405"},{"key":"562_CR77","doi-asserted-by":"crossref","unstructured":"J. Deng, W. Dong, R. Socher, L. -J. Li, K. Li, L. Fei-Fei, in 2009 IEEE conference on computer vision and pattern recognition (CVPR). Imagenet: A large-scale hierarchical image database (Miami, 2009), pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"562_CR78","doi-asserted-by":"crossref","unstructured":"J. Hu, L. Shen, G. Sun, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Squeeze-and-excitation networks (Salt Lake City, 2018), pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"}],"container-title":["EURASIP Journal on Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13640-021-00562-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13640-021-00562-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13640-021-00562-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T13:23:35Z","timestamp":1725283415000},"score":1,"resource":{"primary":{"URL":"https:\/\/jivp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13640-021-00562-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,25]]},"references-count":78,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["562"],"URL":"https:\/\/doi.org\/10.1186\/s13640-021-00562-6","relation":{"is-basis-for":[{"id-type":"doi","id":"10.52843\/cassyni.3drvy1","asserted-by":"object"}],"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-84743\/v1","asserted-by":"object"}]},"ISSN":["1687-5281"],"issn-type":[{"value":"1687-5281","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,25]]},"assertion":[{"value":"26 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2021","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"22"}}