Exploiting Temporal Coherence for Self-Supervised One-Shot Video Re-identification
Author:
Publisher
Springer International Publishing
Link
https://link.springer.com/content/pdf/10.1007/978-3-030-58583-9_16
Reference38 articles.
1. Arazo, E., Ortego, D., Albert, P., O’Connor, N.E., McGuinness, K.: Pseudo-labeling and confirmation bias in deep semi-supervised learning. arXiv preprint arXiv:1908.02983 (2019)
2. Bak, S., Carr, P.: One-shot metric learning for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2990–2999 (2017)
3. Chapelle, O., Scholkopf, B., Zien, A.: Semi-supervised learning. IEEE Trans. Neural Netw. 20(3), 542 (2009)
4. Chen, D., Li, H., Xiao, T., Yi, S., Wang, X.: Video person re-identification with competitive snippet-similarity aggregation and co-attentive snippet embedding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1169–1178 (2018)
5. Chen, T., et al.: ABD-net: attentive but diverse person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8351–8361 (2019)
Cited by 6 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Pseudo-label estimation via unsupervised Identity Link Prediction for one-shot person Re-Identification;Pattern Recognition;2024-02
2. Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition;IEEE Transactions on Pattern Analysis and Machine Intelligence;2023-12
3. Context Sensing Attention Network for Video-based Person Re-identification;ACM Transactions on Multimedia Computing, Communications, and Applications;2023-02-27
4. Semantics Guided Contrastive Learning of Transformers for Zero-shot Temporal Activity Detection;2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2023-01
5. Heterogeneous Pseudo-Supervised Learning for Few-shot Person Re-Identification;Neural Networks;2022-10
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3