no code implementations • 28 Oct 2023 • Jiatai Wang, Zhiwei Xu, Xuewen Yang, Xin Wang
Multi-view clustering (MVC) can explore common semantics from unsupervised views generated by different sources, and thus has been extensively used in applications of practical computer vision.
no code implementations • 18 Sep 2023 • Jiatai Wang, Zhiwei Xu, Xuewen Yang, Hailong Li, Bo Li, Xuying Meng
However, as contrastive learning continues to evolve within the field of computer vision, self-supervised learning has also made substantial research progress and is progressively becoming dominant in MVC methods.
no code implementations • 27 Jan 2023 • Xuewen Yang
We apply this methodology to different AI tasks, including machine translation and image captioning and improve the original state-of-the-art models by a large margin.
no code implementations • 24 Sep 2022 • Jiatai Wang, Zhiwei Xu, Xuewen Yang, Dongjin Guo, Limin Liu
Incomplete Multi-View Clustering aims to enhance clustering performance by using data from multiple modalities.
1 code implementation • EMNLP 2021 • Xuewen Yang, Svebor Karaman, Joel Tetreault, Alex Jaimes
The task of news article image captioning aims to generate descriptive and informative captions for news article images.
no code implementations • 29 Jul 2021 • Xuewen Yang, Yingru Liu, Xin Wang
To improve the quality of image captioning, we propose a novel architecture ReFormer -- a RElational transFORMER to generate features with relation information embedded and to explicitly express the pair-wise relationships between objects in the image.
no code implementations • 27 Aug 2020 • Xuewen Yang, Dongliang Xie, Xin Wang
In this work, we propose a general framework for unsupervised image-to-image translation across multiple domains, which can translate images from domain X to any a domain without requiring direct training between the two domains involved in image translation.
no code implementations • 18 Aug 2020 • Xuewen Yang, Dongliang Xie, Xin Wang, Jiangbo Yuan, Wanying Ding, Pengyun Yan
Our contributions include: 1) Designing a Mixed Category Attention Net (MCAN) which integrates both fine-grained and coarse category information into recommendation and learns the compatibility among fashion tuples.
Cultural Vocal Bursts Intensity Prediction Recommendation Systems
2 code implementations • ECCV 2020 • Xuewen Yang, Heming Zhang, Di Jin, Yingru Liu, Chi-Hao Wu, Jianchao Tan, Dongliang Xie, Jue Wang, Xin Wang
The goal of this work is to develop a novel learning framework for accurate and expressive fashion captioning.
no code implementations • 5 Jul 2020 • Heming Zhang, Xuewen Yang, Jianchao Tan, Chi-Hao Wu, Jue Wang, C. -C. Jay Kuo
Color compatibility is important for evaluating the compatibility of a fashion outfit, yet it was neglected in previous studies.
no code implementations • 11 Jun 2020 • Yingru Liu, Yucheng Xing, Xuewen Yang, Xin Wang, Jing Shi, Di Jin, Zhaoyue Chen
Learning continuous-time stochastic dynamics is a fundamental and essential problem in modeling sporadic time series, whose observations are irregular and sparse in both time and dimension.
no code implementations • 19 Nov 2019 • Yingru Liu, Xuewen Yang, Dongliang Xie, Xin Wang, Li Shen, Hao-Zhi Huang, Niranjan Balasubramanian
In this paper, we propose a novel deep learning model called Task Adaptive Activation Network (TAAN) that can automatically learn the optimal network architecture for MTL.
no code implementations • IJCNLP 2019 • Xuewen Yang, Yingru Liu, Dongliang Xie, Xin Wang, Niranjan Balasubramanian
In this work, we introduce a new latent variable model, LaSyn, that captures the co-dependence between syntax and semantics, while allowing for effective and efficient inference over the latent space.
no code implementations • 11 Jun 2019 • Xuewen Yang, Xin Wang
To enable real-time and accurate license plate recognition, in this work, we propose a set of techniques: 1) a contour reconstruction method along with edge-detection to quickly detect the candidate plates; 2) a simple zero-one-alternation scheme to effectively remove the fake top and bottom borders around plates to facilitate more accurate segmentation of characters on plates; 3) a set of techniques to augment the training data, incorporate SIFT features into the CNN network, and exploit transfer learning to obtain the initial parameters for more effective training; and 4) a two-phase verification procedure to determine the correct plate at low cost, a statistical filtering in the plate detection stage to quickly remove unwanted candidates, and the accurate CR results after the CR process to perform further plate verification without additional processing.