no code implementations • CCL 2020 • Shengsheng Zhang, Guina Pang, Liner Yang, Chencheng Wang, Yongping Du, Erhong Yang, Yaping Huang
语法纠错任务旨在通过自然语言处理技术自动检测并纠正文本中的语序、拼写等语法错误。当前许多针对汉语的语法纠错方法已取得较好的效果, 但往往忽略了学习者的个性化特征, 如二语等级、母语背景等。因此, 本文面向汉语作为第二语言的学习者, 提出个性化语法纠错, 对不同特征的学习者所犯的错误分别进行纠正, 并构建了不同领域汉语学习者的数据集进行实验。实验结果表明, 将语法纠错模型适应到学习者的各个领域后, 性能得到明显提升。
no code implementations • 21 Feb 2024 • Luming Lu, Jiyuan An, Yujie Wang, Liner Yang, Cunliang Kong, Zhenghao Liu, Shuo Wang, Haozhe Lin, Mingwei Fang, Yaping Huang, Erhong Yang
This paper presents the first text-to-CQL task that aims to automate the translation of natural language into CQL.
no code implementations • 11 May 2023 • Yujie Wang, Chao Huang, Liner Yang, Zhixuan Fang, Yaping Huang, Yang Liu, Erhong Yang
The SES method is designed specifically for sequence labeling tasks.
1 code implementation • CVPR 2023 • Caixia Zhou, Yaping Huang, Mengyang Pu, Qingji Guan, Li Huang, Haibin Ling
Deep learning-based edge detectors heavily rely on pixel-wise labels which are often provided by multiple annotators.
no code implementations • 29 Jul 2022 • Caixia Zhou, Yaping Huang, Haibin Ling
Automatic action quality assessment (AQA) has attracted increasing attention due to its wide applications.
1 code implementation • SemEval (NAACL) 2022 • Cunliang Kong, Yujie Wang, Ruining Chong, Liner Yang, Hengyuan Zhang, Erhong Yang, Yaping Huang
This paper describes the BLCU-ICALL system used in the SemEval-2022 Task 1 Comparing Dictionaries and Word Embeddings, the Definition Modeling subtrack, achieving 1st on Italian, 2nd on Spanish and Russian, and 3rd on English and French.
1 code implementation • CVPR 2022 • Mengyang Pu, Yaping Huang, Yuming Liu, Qingji Guan, Haibin Ling
In Stage I, a global transformer encoder is used to capture long-range global context on coarse-grained image patches.
1 code implementation • ICCV 2021 • Mengyang Pu, Yaping Huang, Qingji Guan, Haibin Ling
Taking into consideration the distinct attributes of each type of edges and the relationship between them, RINDNet learns effective representations for each of them and works in three stages.
no code implementations • 26 Mar 2021 • Rumeng Yi, Yaping Huang, Qingji Guan, Mengyang Pu, Runsheng Zhang
In particular, for the generated pixel-level noisy labels from weak supervisions by Class Activation Map (CAM), we train a clean segmentation model with strong supervisions to detect the clean labels from these noisy labels according to the cross-entropy loss.
no code implementations • 25 Mar 2021 • Rumeng Yi, Yaping Huang
Previous methods such as Coteaching and JoCoR introduce two different networks to select clean samples out of the noisy ones and only use these clean ones to train the deep models.
no code implementations • 29 Jan 2021 • Shengsheng Zhang, Yaping Huang, Yun Chen, Liner Yang, Chencheng Wang, Erhong Yang
We exploit a set of data-rich source domains to learn the initialization of model parameters that facilitates fast adaptation on new resource-poor target domains.
no code implementations • 21 Nov 2019 • Yanting Pei, Yaping Huang, Xingyuan Zhang
The generated images generally have better visual appeal, but not always have better performance for high-level vision tasks, e. g. image classification.
no code implementations • 26 Feb 2019 • Runsheng Zhang, Jian Zhang, Yaping Huang, Qi Zou
To tackle this issue, we propose a fully unsupervised part mining (UPM) approach to localize the discriminative parts without even image-level annotations, which largely improves the fine-grained classification performance.
1 code implementation • 26 Feb 2019 • Runsheng Zhang, Yaping Huang, Mengyang Pu, Jian Zhang, Qingji Guan, Qi Zou, Haibin Ling
To tackle this problem, we propose a simple but effective pattern mining-based method, called Object Location Mining (OLM), which exploits the advantages of data mining and feature representation of pre-trained convolutional neural networks (CNNs).
no code implementations • ECCV 2018 • Yanting Pei, Yaping Huang, Qi Zou, Yuhang Lu, Song Wang
Typically, the goal of image dehazing is to produce clearer images from which human vision can better identify the object and structural details present in the images.
no code implementations • 12 Oct 2018 • Yanting Pei, Yaping Huang, Qi Zou, Hao Zang, Xingyuan Zhang, Song Wang
In this paper, we empirically study this problem for four kinds of degraded images -- hazy images, underwater images, motion-blurred images and fish-eye images.
1 code implementation • 30 Jan 2018 • Qingji Guan, Yaping Huang, Zhun Zhong, Zhedong Zheng, Liang Zheng, Yi Yang
This paper considers the task of thorax disease classification on chest X-ray images.