no code implementations • 26 Mar 2024 • Dian Chao, Xin Song, Shupeng Zhong, Boyuan Wang, Xiangyu Wu, Chen Zhu, Yang Yang
In this paper, we propose a solution for improving the quality of captions generated for figures in papers.
1 code implementation • 15 Jan 2024 • Wenjuan Xi, Xin Song, Weili Guo, Yang Yang
Existing semi-supervised learning (SSL) methods assume that labeled and unlabeled data share the same class space.
1 code implementation • 8 Nov 2023 • Feng Xie, Xin Song, Xiang Zeng, Xuechen Zhao, Lei Tian, Bin Zhou, Yusong Tan
More importantly, in pseudo mapping learning, we propose a bi-directional voting (BDV) strategy that fuses the alignment decisions in different directions to estimate the uncertainty via the joint matching confidence score.
no code implementations • 4 Jun 2022 • Xiaochen Li, Xin Song, Pengjia Yuan, Xialong Liu, Yu Zhang
In this paper, we focus on a new type of user interest, i. e., user retargeting interest.
no code implementations • 14 Aug 2019 • Mingyuan Bai, S. T. Boris Choy, Xin Song, Junbin Gao
Thus, we propose a tensor-train parameterization for ultra dimensionality reduction (TTPUDR) in which the traditional LPP mapping is tensorized in terms of tensor-trains and the LPP objective is replaced with the Frobenius norm to increase the robustness of the model.