Z
Zechao Li
Researcher at Nanjing University of Science and Technology
Publications - 150
Citations - 6311
Zechao Li is an academic researcher from Nanjing University of Science and Technology. The author has contributed to research in topics: Computer science & Image retrieval. The author has an hindex of 36, co-authored 126 publications receiving 4281 citations. Previous affiliations of Zechao Li include Chinese Academy of Sciences.
Papers
More filters
Proceedings Article
Unsupervised feature selection using nonnegative spectral analysis
TL;DR: A new unsupervised learning algorithm, namely Nonnegative Discriminative Feature Selection (NDFS), which exploits the discriminative information and feature correlation simultaneously to select a better feature subset.
Proceedings ArticleDOI
Single Image Dehazing via Conditional Generative Adversarial Network
TL;DR: This paper proposes an algorithm to directly restore a clear image from a hazy image based on a conditional generative adversarial network (cGAN), where the clear image is estimated by an end-to-end trainable neural network.
Journal ArticleDOI
Robust Structured Subspace Learning for Data Representation
TL;DR: A novel Robust Structured Subspace Learning (RSSL) algorithm by integrating image understanding and feature learning into a joint learning framework is proposed, and the learned subspace is adopted as an intermediate space to reduce the semantic gap between the low-level visual features and the high-level semantics.
Journal ArticleDOI
Clustering-Guided Sparse Structural Learning for Unsupervised Feature Selection
TL;DR: A novel unsupervised feature selection algorithm, named clustering-guided sparse structural learning (CGSSL), is proposed by integrating cluster analysis and sparse structural analysis into a joint framework and experimentally evaluated and demonstrated efficiency and effectiveness.
Journal ArticleDOI
Deep Collaborative Embedding for Social Image Understanding
Zechao Li,Jinhui Tang,Tao Mei +2 more
TL;DR: A Deep Collaborative Embedding model is proposed to uncover a unified latent space for images and tags and integrates the weakly-supervised image-tag correlation, image correlation and tag correlation simultaneously and seamlessly to collaboratively explore the rich context information of social images.