A5109011428- Visual Attention and Saliency Detection
- Advanced Image and Video Retrieval Techniques
- Software Reliability and Analysis Research
- Computer Graphics and Visualization Techniques
- Software Engineering Research
- Image Enhancement Techniques
- Image and Video Quality Assessment
- Atmospheric and Environmental Gas Dynamics
- Advanced Image Fusion Techniques
- 3D Shape Modeling and Analysis
- Seismic Imaging and Inversion Techniques
- Reservoir Engineering and Simulation Methods
- Image Retrieval and Classification Techniques
- Image Processing and 3D Reconstruction
- Advanced Decision-Making Techniques
Zhejiang Normal University
2023
Fudan University
2014
This paper presents a new image retargeting method based on seam searching and pixel fusion. First, the importance map of original image, which is represented by saliency every pixel, generated. Second, all pixels in are divided into W (width image) groups with help searching. Then, it performs inter-row coherence filtering to maintain spatial coherence, directly utilizes filtered generate scaling map. Finally, after fusion map, can be retargeted effectively. Experimental results show that...
This paper presents a new image retargeting method, which is able to provide both high efficiency and quality. Firstly, our method calculates the resizing factors in horizontal vertical directions. Then, it resizes these directions sequentially order achieve target aspect ratio with help of proposed mapping functions. Finally, reconstructed can be uniformly scaled resolution. Experimental results show that not only cost effective terms computational resource, but also provides visually...
Considering the uneven distribution of software defect datasets, performance traditional SDP (software prediction) model is relatively low, which cannot predict defects well and fix them in time, resulting low reliability system. This paper proposed an improved method based on GABP, helps to allocate test resources reasonably, ensures quality improves Firstly, combining with BP neural network, SMOTE TOMEK are applied select better data preprocessing obtain initial network architecture;...
We carried out a high time-resolution, multicolour optical observing campaign for eight $γ$-ray detected blazars during 2010-2020. analyze flux variations, correlations between magnitudes and colours on different timescales. Intraday variability (IDV) is in all sources of our sample. A bluer-when-brighter (BWB) chromatic trend dominant intraday On the short timescales, BWB only shows up ON 231, 3C 279, BL Lacertae 1E 1458.8+2249. There 279 long timescale. estimate upper limits black hole...