Salient object detection, a fundamental of many computer vision tasks, aims to find the most attractive objects in a given image. In this paper, we propose an end-to-end multi-scale neural network for salient object detection. Firstly, we propose ...

Traditional text classification methods make a basic assumption: the training and test data are homologous, while this naive assumption may not hold in the real world. Hence, this paper studies the problem of domain-adapted news text classification, ...

Hyperspectral imaging is a hot topic nowadays. It is an urgent problem to be solved how to achieve swift hyperspectral imaging. In this thesis, our primary purpose is to further optimize how to place a mask in front of a sensor in order to achieve ...

With the advance of computer technology and smart device, many applications, such as face recognition and object recognition, have been developed to facilitate human-computer interaction (HCI) efficiently. In this respect, the hand-held object ...

Deep learning has been demonstrated to be a universal and successful tool for classification, detection and segmentation. Convolutional neural network (CNN), as a representative model, achieves excellent performance in many image process areas due to its ...

Road detection is an important part of the environment perception technology of unmanned vehicles. Using computer vision technology to achieve the semantic segmentation of environmental scenes is one of the key technology to ensure the safe driving of ...

Approximate nearest neighbor (ANN) search has been well-studied and weightily applied in the field of large scale multimedia search. In recent years, Product Quantization (PQ) based methods have achieved greate success in ANN search. However, both the ...

In this paper, we propose a vision-based hand gesture recognition system for human-computer interaction. The gesture recognition systems are employed in developing a rock-paper-scissors game between human and our robotic hands in realtime. Our task is ...

Video facial landmark detection and tracking are important computer vision tasks with many applications such as face anti-spoofing, animation and recognition. Most of existing facial landmark detection and tracking methods, however, often suffer from ...

In this paper, we present an automatic web-based framework to insert images to the proper location of travel notes without restrictions on pre-defined vocabulary and training process. Instead of learning region-entity correspondences from explicitly ...

In¹ this paper, we present a novel image stabilization algorithm to deal with the random jitter by estimating camera trajectory and feature block matching. Our goal is estimating camera motion paths that consist of translation, rotation and zooming, ...

Automatic recognition of facial expression images is a challenge for computer due to variation of expression, background, position and label noise. The paper propose a new method for static facial expression recognition. Main process is to perform ...

In this paper, we have proposed an image segmentation approach where we combine the concept of the fuzzy C-means (FCM) and four-chain quantum bee colony optimization (QA BC) named it as FQABC. In the FQABC algorithm, firstly, the four chains quantum ...

Automatic image cropping is of great importance for improving visual quality of images. Existing methods typically repurpose classifiers to perform cropping. Instead, we frame image cropping as a regression problem to bounding boxes and associated ...

Kernel canonical correlation analysis (KCCA) is an efficient method for dimensionality reduction. However KCCA has the problem of finding appropriate type of kernel function and its parameters. In this paper, we propose a kernelized canonical ...

In this paper, we propose an image inpainting approach based on generative adversarial networks (GANs). The model consists of an inpainting network, two discriminative networks, local and global respectively, and a novel neural feature network. The ...

Recently it has shown that the policy-gradient methods for reinforcement learning have been utilized to train deep end-to-end systems on natural language processing tasks. What's more, with the complexity of understanding image content and diverse ways ...

Visual tracking is a challenging vision task due to the complex scenes in real scenarios. Recently, correlation filter (CF) based trackers have achieved impressive performance, showing high frame rates. An increasing research focuses on designing ...

In this work, we propose a novel deep multimodal hashing method, termed as Deep Hashing with Multilevel Similarity Learning (DHMSL), which learns discriminative hash functions with deep neural networks by exploiting multilevel semantic similarity ...

With the development of cloud computing and big data, more and more applications are deployed in the cloud. Data center, as a management unit of computing and storage resources, consists of quantities of computing clusters, and the scale of clusters ...