K
Ke Xian
Researcher at Huazhong University of Science and Technology
Publications - 56
Citations - 1050
Ke Xian is an academic researcher from Huazhong University of Science and Technology. The author has contributed to research in topics: Computer science & Rendering (computer graphics). The author has an hindex of 12, co-authored 45 publications receiving 502 citations. Previous affiliations of Ke Xian include Adobe Systems.
Papers
More filters
Proceedings ArticleDOI
Monocular Relative Depth Perception with Web Stereo Data Supervision
TL;DR: A simple yet effective method to automatically generate dense relative depth annotations from web stereo images, and an improved ranking loss is introduced to deal with imbalanced ordinal relations, enforcing the network to focus on a set of hard pairs.
Proceedings ArticleDOI
Structure-Guided Ranking Loss for Single Image Depth Prediction
TL;DR: This work proposes to use a simple pair-wise ranking loss with a novel sampling strategy to improve the quality of depth map prediction and introduces a new relative depth dataset of about 21K diverse high-resolution web stereo photos to enhance the generalization ability of the model.
Proceedings ArticleDOI
When Unsupervised Domain Adaptation Meets Tensor Representations
TL;DR: In this paper, a set of alignment matrices is introduced to align the tensor representations from both domains into the invariant tensor subspace, which can be learned adaptively from the data using the proposed alternative minimization scheme.
Book ChapterDOI
Deep Attention-Based Classification Network for Robust Depth Prediction
TL;DR: Zhang et al. as discussed by the authors proposed a deep attention-based classification (DABC) network for robust single image depth prediction, in the context of the Robust Vision Challenge 2018 (ROB 2018).
Journal ArticleDOI
Fine-grained maize tassel trait characterization with multi-view representations
TL;DR: An automatic fine-grained machine vision system termed mTASSEL is developed that can serve the automatic growth stage detection, accurate yield estimation and machine detasseling, as well as the field-based phenotyping research.