17 Result(s)
within
Conference Paper
**an-Sheng Liu
Image Processing and Computer Vision
-
Chapter and Conference Paper
Unleashing the Potential of Adaptation Models via Go-getting Domain Labels
In this paper, we propose an embarrassingly simple yet highly effective adversarial domain adaptation (ADA) method. We view ADA problem primarily from an optimization perspective and point out a fundamental di...
-
Chapter and Conference Paper
Box-Supervised Instance Segmentation with Level Set Evolution
In contrast to the fully supervised methods using pixel-wise mask labels, box-supervised instance segmentation takes advantage of the simple box annotations, which has recently attracted a lot of research atte...
-
Chapter and Conference Paper
Landmarks Detection with Anatomical Constraints for Total Hip Arthroplasty Preoperative Measurements
Total hip arthroplasty (THA) is a valid and reliable treatment for degenerative hip disease, and an elaborate preoperative planning is vital for such surgery. The key step of planning is to localize several an...
-
Chapter and Conference Paper
Differentiable Hierarchical Graph Grou** for Multi-person Pose Estimation
Multi-person pose estimation is challenging because it localizes body keypoints for multiple persons simultaneously. Previous methods can be divided into two streams, i.e. top-down and bottom-up methods. The top-...
-
Chapter and Conference Paper
Whole-Body Human Pose Estimation in the Wild
This paper investigates the task of 2D human whole-body pose estimation, which aims to localize dense landmarks on the entire human body including face, hands, body, and feet. As existing datasets do not have ...
-
Chapter and Conference Paper
Cross-View Action Recognition Using View-Invariant Pose Feature Learned from Synthetic Data with Domain Adaptation
Recognizing human activities from unknown views is a challenging pr...
-
Chapter and Conference Paper
A New Algorithm of Automatic Grading in Computer Paperless Test System
Efficient automatic grading of programs in computer paperless test system is a hotspot in current research. In allusion to the deficiency of scoring computer language in current test system, a kind of machine ...
-
Chapter and Conference Paper
Superpixel-Based Global Optimization Method for Stereo Disparity Estimation
We proposed a novel global optimization method based on superpixel for stereo matching in this paper. Comparing with the pixel-based global optimization methods, the matching accuracy of our method is signific...
-
Chapter and Conference Paper
A Novel Feature Extractor Based on Wavelet and Kernel PCA for Spike Sorting Neural Signals
Spike sorting is often required for analyzing neural recordings to isolate the activity of single neurons. In this paper, a new feature extractor based on Wavelet and kernel PCA for spike sorting was proposed....
-
Chapter and Conference Paper
2D to 3D Image Conversion Based on Classification of Background Depth Profiles
In this paper, a 2D to 3D stereo image conversion scheme is proposed for 3D content creation. The difficulty in this problem lies on depth estimation/assignment from a mono image, which actually does not have ...
-
Chapter and Conference Paper
Comprehensive Evaluation of Effects of Naomaitong and Rhubarb Aglycone Combined with Bone Mesenchymal Stem Cells Transplantation on Brain in Rats with Cerebral Ischemia Based on Analytic Hierarchy Process
To calculate the experimental data of indexes with computer through the multi-objective decision-making, and then to make the comprehensive evaluation of effects of different Chinese Medicines combined with Bo...
-
Chapter and Conference Paper
Image Search Result Summarization with Informative Priors
Though current commercial image search engines provide effective ways to retrieve the relevant images, they are ineffective for users to find the desired from the retrieved hundreds of results, especially for ...
-
Chapter and Conference Paper
Graph-Based Pairwise Learning to Rank for Video Search
Learning-based ranking is a promising approach to a variety of search tasks, which is aimed at automatically creating the ranking model based on training samples and machine learning techniques. However, the p...
-
Chapter and Conference Paper
Multiple-Instance Active Learning for Image Categorization
Both multiple-instance learning and active learning are widely employed in image categorization, but generally they are applied separately. This paper studies the integration of these two methods. Different fr...
-
Chapter and Conference Paper
Intelligent Spot Detection for 2-DE Gel Image
In this study, a novel method for spot detection is proposed with the addition of confidence evaluation for each detected spot. The confidence of a spot will give useful hints for subsequent processing such as...
-
Chapter and Conference Paper
Video Histogram: A Novel Video Signature for Efficient Web Video Duplicate Detection
The explosive growth of information technology and digital content industry stimulates various video applications over the Internet. Since it is quite easy to copy, reformat, modify and republish video files o...
-
Chapter and Conference Paper
A Linear Approximation Based Method for Noise-Robust and Illumination-Invariant Image Change Detection
Image change detection plays a very important role in real-time video surveillance systems. To deal with the illumination, a category of linear algebra based algorithms were designed in the literature. They ha...
