Search Results for author: Lihong Cao

Found 6 papers, 3 papers with code

基于关系图注意力网络和宽度学习的负面情绪识别方法(Negative Emotion Recognition Method Based on Rational Graph Attention Network and Broad Learning)

no code implementations CCL 2022 Sancheng Peng, Guanghao Chen, Lihong Cao, Rong Zeng, Yongmei Zhou, Xinguang Li

“对话文本负面情绪识别主要是从对话文本中识别出每个话语的负面情绪, 近年来已成为了一个研究热点。然而, 让机器在对话文本中识别负面情绪是一项具有挑战性的任务, 因为人们在对话中的情感表达通常存在上下文关系。为了解决上述问题, 本文提出一种基于关系图注意力网络(Rational Graph Attention Network, RGAT)和宽度学习(Broad Learning, BL)的对话文本负面情绪识别方法, 即RGAT-BL。该方法采用预训练模型RoBERTa生成对话文本的初始向量;然后, 采用Bi-LSTM对文本向量的局部特征和上下文语义特征进行提取, 从而获取话语级别的特征;采用RGAT对说话者之间的长距离依赖关系进行提取, 从而获取说话者级别的特征;采用BL对上述两种拼接后的特征进行处理, 从而实现对负面情绪进行分类输出。通过在三种数据集上与基线模型进行对比实验, 结果表明所提出的方法在三个数据集上的weighted-F 1、macroF 1值都优于基线模型。”

Emotion Recognition Graph Attention

BIFRNet: A Brain-Inspired Feature Restoration DNN for Partially Occluded Image Recognition

1 code implementation2 Mar 2023 Jiahong Zhang, Lihong Cao, Qiuxia Lai, Binyao Li, Yunxiao Qin

Several studies in neuroscience reveal that feature restoration which fills in the occluded information and is called amodal completion is essential for human brains to recognize partially occluded images.

A Multi-Head Convolutional Neural Network With Multi-path Attention improves Image Denoising

5 code implementations27 Apr 2022 Jiahong Zhang, Meijun Qu, Ye Wang, Lihong Cao

Unlike previous attention mechanisms that handle pixel-level, channel-level, or patch-level features, MPA focuses on features at the image level.

Image Denoising

Adversarial Attack across Datasets

no code implementations13 Oct 2021 Yunxiao Qin, Yuanhao Xiong, JinFeng Yi, Lihong Cao, Cho-Jui Hsieh

In this paper, we define a Generalized Transferable Attack (GTA) problem where the attacker doesn't know this information and is acquired to attack any randomly encountered images that may come from unknown datasets.

Adversarial Attack Image Classification

A Biologically Plausible Audio-Visual Integration Model for Continual Learning

no code implementations17 Jul 2020 Wenjie Chen, Fengtong Du, Ye Wang, Lihong Cao

Furthermore, we define a new continual learning paradigm to simulate the possible continual learning process in the human brain.

Continual Learning

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