A5101504244- Visual Attention and Saliency Detection
- Retinal Imaging and Analysis
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Industrial Vision Systems and Defect Detection
- Video Analysis and Summarization
- Generative Adversarial Networks and Image Synthesis
- Advanced Vision and Imaging
- Geotechnical Engineering and Analysis
- Railway Engineering and Dynamics
- Computer Graphics and Visualization Techniques
- Geotechnical Engineering and Soil Stabilization
- Adhesion, Friction, and Surface Interactions
- Video Surveillance and Tracking Methods
- Geotechnical Engineering and Underground Structures
- 3D Shape Modeling and Analysis
- Mechanical stress and fatigue analysis
Southwest Jiaotong University
2023-2024
Dalian University of Technology
2021-2022
Dalian University
2022
Glass is very common in the real world. Influenced by uncertainty about glass region and varying complex scenes behind glass, existence of poses severe challenges to many computer vision tasks, making segmentation as an important task. does not have its own visual appearances but only transmit/reflect surroundings, it fundamentally different from other objects. To address such a challenging task, existing methods typically explore combine useful cues levels features deep network. As there...
Glass is very common in our daily life. Existing computer vision systems neglect it and thus may have severe consequences, e.g., a robot crash into glass wall. However, sensing the presence of not straightforward. The key challenge that arbitrary objects/scenes can appear behind glass. In this paper, we propose an important problem detecting surfaces from single RGB image. To address problem, construct first large-scale detection dataset (GDD) novel network, called GDNet-B, which explores...
In this article, we propose a fully automatic system for generating comic books from videos without any human intervention. Given an input video along with its subtitles, our approach first extracts informative keyframes by analyzing the subtitles and stylizes into comic-style images. Then, novel multi-page layout framework that can allocate images across multiple pages synthesize visually interesting layouts based on rich semantics of (e.g., importance inter-image relation). Finally, as...
Mirrors are everywhere in our daily lives. Existing computer vision systems do not consider mirrors, and hence may get confused by the reflected content inside a mirror, resulting severe performance degradation. However, separating real outside mirror from it is non-trivial. The key challenge that mirrors typically reflect contents similar to their surroundings, making very difficult differentiate two. In this article, we present novel method segment single RGB image. To best of knowledge,...
Glass is very common in the real world. Influenced by uncertainty about glass region and varying complex scenes behind glass, existence of poses severe challenges to many computer vision tasks, making segmentation as an important task. does not have its own visual appearances but only transmit/reflect surroundings, it fundamentally different from other objects. To address such a challenging task, existing methods typically explore combine useful cues levels features deep network. As there...
In this paper, we propose a fully automatic system for generating comic books from videos without any human intervention. Given an input video along with its subtitles, our approach first extracts informative keyframes by analyzing the and stylizes into comic-style images. Then, novel multi-page layout framework, which can allocate images across multiple pages synthesize visually interesting layouts based on rich semantics of (e.g., importance inter-image relation). Finally, as opposed to...