C
Chaoqun Hong
Researcher at Xiamen University of Technology
Publications - 46
Citations - 1463
Chaoqun Hong is an academic researcher from Xiamen University of Technology. The author has contributed to research in topics: Feature (computer vision) & Deep learning. The author has an hindex of 14, co-authored 40 publications receiving 1210 citations.
Papers
More filters
Journal ArticleDOI
Multimodal Deep Autoencoder for Human Pose Recovery
TL;DR: A novel pose recovery method using non-linear mapping with multi-layered deep neural network and back-propagation deep learning to obtain a unified feature description by standard eigen-decomposition of the hypergraph Laplacian matrix.
Journal ArticleDOI
Image-Based Three-Dimensional Human Pose Recovery by Multiview Locality-Sensitive Sparse Retrieval
TL;DR: This approach improves traditional methods by adopting multiview locality-sensitive sparse coding in the retrieving process, and incorporates a local similarity preserving term into the objective of sparse coding, which groups similar silhouettes to alleviate the instability of sparse codes.
Journal ArticleDOI
Multitask Autoencoder Model for Recovering Human Poses
TL;DR: Experimental results on two popular datasets demonstrates that the recovery error has been reduced by 10%–20%, which proves the performance improvement of the proposed method.
Journal ArticleDOI
Multi-view ensemble manifold regularization for 3D object recognition
TL;DR: A novel 3D object recognizing method based on multi-view data fusion, called Multi-view Ensemble Manifold Regularization (MEMR), which model image features with a regularization term for SVM and demonstrates the effectiveness of the proposed method.
Journal ArticleDOI
Fast Adaptive K-Means Subspace Clustering for High-Dimensional Data
TL;DR: An efficient alternative optimization algorithm is exploited to solve the proposed FAKM type subspace clustering model, where an adaptive loss function is designed to provide a flexible cluster indicator calculation mechanism, thereby suitable for datasets under different distributions.