P
Peidong Liu
Researcher at Tsinghua University
Publications - 16
Citations - 57
Peidong Liu is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 2, co-authored 9 publications receiving 26 citations. Previous affiliations of Peidong Liu include Sun Yat-sen University & Association for Computing Machinery.
Papers
More filters
Proceedings ArticleDOI
LDA Meets Word2Vec: A Novel Model for Academic Abstract Clustering
Chang-Zhou Li,Yao Lu,Jun-Feng Wu,Yongrui Zhang,Xia Zhongzhou,Tianchen Wang,Dantian Yu,Xurui Chen,Peidong Liu,Guo Junyu +9 more
TL;DR: A novel clustering model that uses abstract text instead of keywords to cluster because keywords may be ambiguous and cause unsatisfied clustering results shown by previous work, and Experimental results show that the clusteringresults of PW-LDA are much more accurate and stable than state-of-the-art techniques.
Proceedings ArticleDOI
WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations
TL;DR: WeClick as mentioned in this paper proposes an effective weakly-supervised video semantic segmentation pipeline with click annotations, called WeClick, for saving laborious annotating effort by segmenting an instance of the semantic class with only a single click.
Posted Content
Visual Privacy Protection via Mapping Distortion
TL;DR: In the modified dataset generated by MDP, the image and its label are not consistent, whereas the DNNs trained on it can still achieve good performance on benign testing set, and this method can protect privacy when the dataset is leaked.
Proceedings Article
Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
TL;DR: CSE-Autoloss as discussed by the authors proposes an effective convergence-simulation driven evolutionary search algorithm, which can accelerate the search progress by regularizing the mathematical rationality of loss candidates via two progressive convergence simulation modules: convergence property verification and model optimization simulation.
Journal ArticleDOI
Re-Examining the Income–CO2 Emissions Nexus Using the New Kink Regression Model: Does the Kuznets Curve Exist in G7 Countries?
TL;DR: In this article , the EKC hypothesis between income and CO2 emissions is reassessed by applying a new kink regression model for the G7 countries from 1890 to 2015, and the results reveal that the inverted U-shaped nexus does not exist for US, Germany, Italy, Canada and Japan.