Robust Top- k Multiclass SVM for Visual Category Recognition
Author:
Affiliation:
1. Carnegie Mellon University, Pittsburgh, PA, USA
2. University of Waterloo, Waterloo, Canada
3. University of Technology Sydney, Sydney, Australia
Funder
Data to Decisions Cooperative Research Centre (www.d2dcrc.com.au)
NSERC
Publisher
ACM
Link
https://dl.acm.org/doi/pdf/10.1145/3097983.3097991
Reference32 articles.
1. Samy Bengio Jason Weston and David Grangier. 2010. Label Embedding Trees for Large Multi-Class Tasks. NIPS. Samy Bengio Jason Weston and David Grangier. 2010. Label Embedding Trees for Large Multi-Class Tasks. NIPS.
2. Antoine Bordes Léon Bottou Patrick Gallinari and Jason Weston 2007. Solving multiclass support vector machines with LaRank ICML. Antoine Bordes Léon Bottou Patrick Gallinari and Jason Weston 2007. Solving multiclass support vector machines with LaRank ICML.
3. On the algorithmic implementation of multiclass kernel-based vector machines;Crammer Koby;Journal of Machine Learning Research,2001
4. Jia Deng Jonathan Krause Alexander C. Berg and Fei-Fei Li 2012. Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition CVPR. Jia Deng Jonathan Krause Alexander C. Berg and Fei-Fei Li 2012. Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition CVPR.
Cited by 14 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. When Measures are Unreliable: Imperceptible Adversarial Perturbations toward Top-k Multi-Label Learning;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26
2. Rank-based Decomposable Losses in Machine Learning: A Survey;IEEE Transactions on Pattern Analysis and Machine Intelligence;2023
3. A convex multi-class model via distance metric learning based class-to-instance confidence;Knowledge-Based Systems;2022-12
4. TkTC: A framework for top-k text classification of multimedia computing in wireless networks;Wireless Networks;2022-01-19
5. Probabilistic Twin Support Vector Machine for Solving Unclassifiable Region Problem;International Journal of Engineering;2022-01
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