no code implementations • EMNLP 2020 • Ruipeng Jia, Yanan Cao, Hengzhu Tang, Fang Fang, Cong Cao, Shi Wang
Sentence-level extractive text summarization is substantially a node classification task of network mining, adhering to the informative components and concise representations.
Ranked #1 on Extractive Text Summarization on CNN / Daily Mail
no code implementations • 24 Jul 2023 • Menglin Kong, Shaojie Zhao, Juan Cheng, Xingquan Li, Ri Su, Muzhou Hou, Cong Cao
There are two fundamental problems in applying deep learning/machine learning methods to disease classification tasks, one is the insufficient number and poor quality of training samples; another one is how to effectively fuse multiple source features and thus train robust classification models.
no code implementations • 24 Jul 2023 • Menglin Kong, Ruichen Li, Fan Liu, Xingquan Li, Juan Cheng, Muzhou Hou, Cong Cao
Landslide is a natural disaster that can easily threaten local ecology, people's lives and property.
no code implementations • 1 May 2023 • Huanjing Yue, Cong Cao, Lei Liao, Jingyu Yang
In this way, we construct a video denoising dataset (named as ReCRVD) with 120 groups of noisy-clean videos, whose ISO values ranging from 1600 to 25600.
1 code implementation • 13 Mar 2023 • Cong Cao, Huanjing Yue, Xin Liu, Jingyu Yang
We construct a large-scale unpaired HDR-LDR video dataset to facilitate the unsupervised training process for video tone mapping.
no code implementations • 18 Jun 2022 • Ri Su, Alphonse Houssou Hounye, Cong Cao, Muzhou Hou
Based on the Sigmoid activation function of output layer, the linear addition activation value of parallel structures in the training process is easy to make the samples fall into the weak gradient interval, resulting in the phenomenon of weak gradient, and reducing the effectiveness of training.
1 code implementation • 5 Mar 2022 • Cong Cao, Tianwei Lin, Dongliang He, Fu Li, Huanjing Yue, Jingyu Yang, Errui Ding
The perturbations for unlabeled data enable the consistency training loss, which benefits semi-supervised semantic segmentation.
1 code implementation • CVPR 2020 • Huanjing Yue, Cong Cao, Lei Liao, Ronghe Chu, Jingyu Yang
Clean video frames for dynamic scenes cannot be captured with a long-exposure shutter or averaging multi-shots as was done for static images.