Chen Wang
Beihang University
95 Papers
232 Citations
Chen Wang is an academic researcher from Beihang University. The author has contributed to research in topics: Computer science & Instability. The author has an hindex of 13, co-authored 71 publications. Previous affiliations of Chen Wang include Capital Medical University & Sichuan University.
Chat about Author
Papers
Imbalance-XGBoost: leveraging weighted and focal losses for binary label-imbalanced classification with XGBoost
TL;DR: The paper presents Imbalance-XGBoost, a Python package that combines the powerful X GBoost software with weighted and focal losses to tackle binary label-imbalanced classification tasks, and is, to the best of the authors' knowledge, the first of its kind which provides an integrated implementation for the two losses on XGBOost.
248
Multiscale Visual Attention Networks for Object Detection in VHR Remote Sensing Images
TL;DR: An end-to-end multiscale visual attention networks (MS-VANs) method that outperforms several state-of-the-art approaches in remote sensing applications and uses skip-connected encoder–decoder model to extract multiscales features from a full-size image.
120
Voxel-based three-view hybrid parallel network for 3D object classification
TL;DR: Wang et al. as mentioned in this paper proposed a voxel-based three-view hybrid parallel network for 3D shape classification, which first obtains the depth projection views of the three-dimensional model from the front view, the top view and the side view, and output its predicted probability value for the category of the 3D model.
87
Multi-view stereo in the Deep Learning Era: A comprehensive revfiew
TL;DR: In this paper, a comprehensive review of recent deep learning methods for multi-view stereo is presented, which is mainly categorized into depth map based and volumetric based methods according to the 3D representation form and representative methods are reviewed in detail.
78
Self-Supervised Multiscale Adversarial Regression Network for Stereo Disparity Estimation
TL;DR: A novel deep stereo approach called the “self-supervised multiscale adversarial regression network (SMAR-Net),” which relaxes the need for ground-truth depth maps for training and outperforms the current state-of-the-art self- supervised methods and achieves comparable outcomes to supervised methods.
58