Search Results for author: Chun Yang

Found 24 papers, 10 papers with code

Transformer-based Reasoning for Learning Evolutionary Chain of Events on Temporal Knowledge Graph

1 code implementation1 May 2024 Zhiyu Fang, Shuai-Long Lei, Xiaobin Zhu, Chun Yang, Shi-Xue Zhang, Xu-Cheng Yin, Jingyan Qin

We then craft a mixed-context reasoning module based on the multi-layer perceptron (MLP) to learn the unified representations of inter-quadruples for ECE while accomplishing temporal knowledge reasoning.

Arbitrary Time Information Modeling via Polynomial Approximation for Temporal Knowledge Graph Embedding

1 code implementation1 May 2024 Zhiyu Fang, Jingyan Qin, Xiaobin Zhu, Chun Yang, Xu-Cheng Yin

Distinguished from traditional knowledge graphs (KGs), temporal knowledge graphs (TKGs) must explore and reason over temporally evolving facts adequately.

Knowledge Graph Embedding Knowledge Graphs

Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Sampling

no code implementations8 Jan 2024 Shi-Xue Zhang, Chun Yang, Xiaobin Zhu, Hongyang Zhou, Hongfa Wang, Xu-Cheng Yin

Specifically, we propose an innovative reading-order estimation module (REM) that extracts reading-order information from the initial text boundary generated by an initial boundary module (IBM).

Text Detection Text Spotting

Scene Text Recognition with Single-Point Decoding Network

no code implementations5 Sep 2022 Lei Chen, Haibo Qin, Shi-Xue Zhang, Chun Yang, XuCheng Yin

In this paper, we propose an efficient attention-free Single-Point Decoding Network (dubbed SPDN) for scene text recognition, which can replace the traditional attention-based decoding network.

Scene Text Recognition

SPR:Supervised Personalized Ranking Based on Prior Knowledge for Recommendation

no code implementations7 Jul 2022 Chun Yang, Shicai Fan

Currently, two popular loss functions are widely used to optimize recommender systems: the pointwise and the pairwise.

Recommendation Systems

Arbitrary Shape Text Detection via Boundary Transformer

2 code implementations11 May 2022 Shi-Xue Zhang, Chun Yang, Xiaobin Zhu, Xu-Cheng Yin

In our method, we explicitly model the text boundary via an innovative iterative boundary transformer in a coarse-to-fine manner.

Decoder Text Detection

Open-set Text Recognition via Character-Context Decoupling

1 code implementation CVPR 2022 Chang Liu, Chun Yang, Xu-Cheng Yin

Contextual information can be decomposed into temporal information and linguistic information.

Kernel Proposal Network for Arbitrary Shape Text Detection

1 code implementation12 Mar 2022 Shi-Xue Zhang, Xiaobin Zhu, Jie-Bo Hou, Chun Yang, Xu-Cheng Yin

In this paper, we propose an innovative Kernel Proposal Network (dubbed KPN) for arbitrary shape text detection.

Text Detection

Supervised Contrastive Learning for Recommendation

no code implementations10 Jan 2022 Chun Yang

In this work, we aim to consider the application of contrastive learning in the scenario of the recommendation system adequately, making it more suitable for recommendation task.

Collaborative Filtering Contrastive Learning +1

Learning Aligned Cross-Modal Representation for Generalized Zero-Shot Classification

no code implementations24 Dec 2021 Zhiyu Fang, Xiaobin Zhu, Chun Yang, Zheng Han, Jingyan Qin, Xu-Cheng Yin

Learning a common latent embedding by aligning the latent spaces of cross-modal autoencoders is an effective strategy for Generalized Zero-Shot Classification (GZSC).

Classification Zero-Shot Learning

A Novel Deep Parallel Time-series Relation Network for Fault Diagnosis

no code implementations3 Dec 2021 Chun Yang

Besides, BERT model applies absolute position embedding to introduce contextual information to the model, which would bring noise to the raw data and therefore cannot be applied to fault diagnosis directly.

Position Relation +3

Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection

1 code implementation ICCV 2021 Shi-Xue Zhang, Xiaobin Zhu, Chun Yang, Hongfa Wang, Xu-Cheng Yin

In this work, we propose a novel adaptive boundary proposal network for arbitrary shape text detection, which can learn to directly produce accurate boundary for arbitrary shape text without any post-processing.

Decoder Text Detection

End-to-end trainable network for degraded license plate detection via vehicle-plate relation mining

1 code implementation27 Oct 2020 Song-Lu Chen, Shu Tian, Jia-Wei Ma, Qi Liu, Chun Yang, Feng Chen, Xu-Cheng Yin

Second, we propose to predict the quadrilateral bounding box in the local region by regressing the four corners of the license plate to robustly detect oblique license plates.

License Plate Detection License Plate Recognition +1

IF-Net: An Illumination-invariant Feature Network

no code implementations10 Aug 2020 Po-Heng Chen, Zhao-Xu Luo, Zu-Kuan Huang, Chun Yang, Kuan-Wen Chen

To show the practicality, we further evaluate IF-Net on the task of visual localization under large illumination changes scenes, and achieves the best localization accuracy.

Image Retrieval Image Stitching +4

Semantic Bilinear Pooling for Fine-Grained Recognition

no code implementations3 Apr 2019 Xinjie Li, Chun Yang, Songlu Chen, Chao Zhu, Xu-Cheng Yin

Specifically, we design a generalized cross-entropy loss for the training of the proposed framework to fully exploit the semantic priors via considering the relevance between adjacent levels and enlarge the distance between samples of different coarse classes.

General Classification Multi-Label Learning

Security Event Recognition for Visual Surveillance

no code implementations26 Oct 2018 Michael Ying Yang, Wentong Liao, Chun Yang, Yanpeng Cao, Bodo Rosenhahn

The experimental results show that the proposed approach outperforms the state-of-the-art methods and effective in recognizing complex security events.

AdaDNNs: Adaptive Ensemble of Deep Neural Networks for Scene Text Recognition

no code implementations10 Oct 2017 Chun Yang, Xu-Cheng Yin, Zejun Li, Jianwei Wu, Chunchao Guo, Hongfa Wang, Lei Xiao

Recognizing text in the wild is a really challenging task because of complex backgrounds, various illuminations and diverse distortions, even with deep neural networks (convolutional neural networks and recurrent neural networks).

Diversity Scene Text Recognition

Learning to Diversify via Weighted Kernels for Classifier Ensemble

no code implementations4 Jun 2014 Xu-Cheng Yin, Chun Yang, Hong-Wei Hao

In this paper, we argue that diversity, not direct diversity on samples but adaptive diversity with data, is highly correlated to ensemble accuracy, and we propose a novel technology for classifier ensemble, learning to diversify, which learns to adaptively combine classifiers by considering both accuracy and diversity.

Diversity Ensemble Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.