no code implementations • 10 Mar 2023 • Jiahan Zhang, Dayong Tian
In the case of an imbalance between positive and negative samples, hard negative mining strategies have been shown to help models learn more subtle differences between positive and negative samples, thus improving recognition performance.
no code implementations • 21 Feb 2023 • Dayong Tian, Feifei Li, Yiwen Wei
We also propose a loss function to measure the similarities between binary labels in datasets and interval type-2 fuzzy memberships generated by our model.
no code implementations • 18 Apr 2019 • Dayong Tian, DaCheng Tao
In this paper, we represent point spread functions (PSFs) by the linear combination of a set of pre-defined orthogonal PSFs, and similarly, an estimated intrinsic (EI) sharp face image is represented by the linear combination of a set of pre-defined orthogonal face images.
no code implementations • 18 Apr 2019 • Dayong Tian, DaCheng Tao
Our methods are based on finding the tradeoff between the information losses in these two steps.
no code implementations • 2 Mar 2018 • Dayong Tian
As the output of sigmoid function approximates a binary code matrix, the proposed MCR can efficiently decorrelate the hashing codes.
no code implementations • 20 Feb 2018 • Jiang Bian, Dayong Tian, Yuanyan Tang, DaCheng Tao
This paper comprehensively surveys the development of trajectory clustering.
no code implementations • 9 Dec 2017 • Dayong Tian, Maoguo Gong, Deyun Zhou, Jiao Shi, Yu Lei
As unsupervised multimodal hashing methods are usually inferior to supervised ones, while the supervised ones requires too much manually labeled data, the proposed method in this paper utilizes a part of labels to design a semi-supervised multimodal hashing method.