-
Chapter and Conference Paper
A Close-Form Iterative Algorithm for Depth Inferring from a Single Image
Inferring depth from a single image is a difficult task in computer vision, which needs to utilize adequate monocular cues contained in the image. Inspired by Saxena et al’s work, this paper presents a close-f...
-
Chapter and Conference Paper
A New Similarity Measure for Non-local Means Denoising
Non-local means (NLM) denoising algorithm is a good similarity measure based denoising algorithm for images with repetitive textures. However, NLM cannot handle the large rotation. In this paper, we propose a ...
-
Chapter and Conference Paper
Color Image Segmentation Combining Rough Depth Information
A novel color image segmentation method is presented in this paper. Firstly a Luv color histogram based method is used to estimate the color bandwidth, then a mean shift algorithm with adaptive color bandwidth is...
-
Chapter and Conference Paper
Video Based Face Tracking and Animation
We propose a system for video based face tracking and animation. With a single video camera, our system can accurately track the facial feature points of a user, and transfer the tracked facial motions to the ...
-
Chapter and Conference Paper
Cross-Level: A Practical Strategy for Convolutional Neural Networks Based Image Classification
Convolutional neural networks (CNNs) have exhibited great potential in the field of image classification in the past few years. In this paper, we present a novel strategy named cross-level to improve the exist...
-
Chapter and Conference Paper
Simultaneously Retargeting and Super-Resolution for Stereoscopic Video
This paper presents a novel approach that is able to resize stereoscopic video to fit various display environments with different aspect-ratios, while preserving the prominent content, kee** temporally consi...
-
Chapter and Conference Paper
Face Video Super-Resolution with Identity Guided Generative Adversarial Networks
Faces are of particular concerns in video surveillance systems. It is challenging to reconstruct clear faces from low-resolution (LR) videos. In this paper, we propose a new method for face video super-resolut...
-
Chapter and Conference Paper
Pedestrian Detection by Using CNN Features with Skip Connection
The CNN based pedestrian detection is develo** rapidly in recent years. Compared to the features used in former pedestrian detection models, the features from deep CNN have outperformed in many aspects. In t...
-
Chapter and Conference Paper
Dynamic Facial Expression Recognition Based on Trained Convolutional Neural Networks
Recently, dynamic facial expression recognition in videos receives more and more attention. In this paper, we propose a method based on trained convolutional neural networks for dynamic facial expression recog...
-
Chapter and Conference Paper
Learning Non-local Representation for Visual Tracking
Discriminative Correlation Filter (DCF) based trackers have tremendously improved the tracking performance. They adopt the first frame of video sequence to initialize the tracker and provide a fast solution du...
-
Chapter and Conference Paper
A Novel Multi-focus Image Fusion Based on Lazy Random Walks
Most existing fusion methods usually suffer from blurred edges and introduce artifacts (such as blocking or ringing). To solve these problems, a novel multi-focus image fusion algorithm using lazy random walks...
