Výsledky vyhledávání - "Multiple experts"

Akademický článek

Consensus and Risk Aversion Learning in Ensemble of Multiple Experts for Long-Tailed Classification

Autor: Taegil Ha, Jin Young Choi

Publikováno v: IEEE Access, Vol 12, Pp 97883-97892 (2024)

Recent expert ensemble methods for long-tailed recognition encourage diversity by maximizing KL divergence between the predictions of experts. However, the excessive diversity using KL divergence, which has no upper bound, induces inaccurate predicti

Externí odkaz: https://doaj.org/article/05fd86bd60ce47c7bca59e4a09d5c1ed

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Multi-Model and Multi-Expert Correlation Filter for High-Speed Tracking

Autor: Mengquan Liang, Xuedong Wu, Yaonan Wang, Zhiyu Zhu, Baiheng Cao, Jie Xu

Publikováno v: IEEE Access, Vol 9, Pp 52326-52335 (2021)

Tracking algorithm based on correlation filter have been extensively investigated due to their powerful performance in benchmark datasets and competitions. However, the periodic assumption has contributed boundary effects and the complex scenarios wi

Externí odkaz: https://doaj.org/article/cb6d6947d39747aa882cb072ef850aa6

Zobrazit plný text záznamu

Akademický článek

Robust Visual Tracking via Multiple Experts With Correlation Filters

Autor: Lei Zhang, Hong Zhang, Yawei Li, Qiaochu Kang, Naixue Xiong

Publikováno v: IEEE Access, Vol 7, Pp 129504-129513 (2019)

As one of the key components in many computer vision applications, visual tracking has been widely investigated in recent years. Correlation filter-based trackers have achieved compelling performance in terms of both efficiency and accuracy by speedi

Externí odkaz: https://doaj.org/article/56a8be73e8e54e81acd56e404ef3ae37

Zobrazit plný text záznamu