134 Result(s)
within
Computer Science
Artificial Intelligence
Computer Graphics
Image Processing and Computer Vision
Multimedia Information Systems
**hu Li
-
Chapter and Conference Paper
Accurate Detection for Scene Texts with a Cascaded CNN Networks
We propose an algorithm of text detection to accurately and reliably determine the bounding regions of texts in a natural scene. The cascaded convolutional neural networks are aggregated in our system in order...
-
Chapter and Conference Paper
k-Labelsets for Multimedia Classification with Global and Local Label Correlation
Multimedia data, e.g., text and images, can be associated with more than one label. Existing methods for multimedia data classification either consider label correlation globally by assuming that it is shared ...
-
Chapter and Conference Paper
Person Re-id by Incorporating PCA Loss in CNN
This paper proposes an algorithm, particularly a loss function and its end to end learning manner, for person re-identification task. The main idea is to take full advantage of the labels in a batch during tra...
-
Chapter and Conference Paper
LVFS: A Lightweight Video Storage File System for IP Camera-Based Surveillance Applications
Surveillance video data are characterized by a high-volume write-oriented workload and cyclic use of storage space at full capacity. Besides, the video data needs indexing to support accurate-query. Data archi...
-
Chapter and Conference Paper
ShapeCreator: 3D Shape Generation from Isomorphic Datasets Based on Autoencoder
With the development of 3D digital geometry media, the creation of 3D content is becoming more and more important. This paper presents a novel method for 3D shape generation from the isomorphic examples in ter...
-
Chapter and Conference Paper
A New Accurate Image Denoising Method Based on Sparse Coding Coefficients
Although sparse coding error has been introduced to improve the performance of sparse representation-based image denoising, however, the sparse coding noise is not tight enough. To suppress the sparse coding n...
-
Chapter and Conference Paper
Scalable Bag of Selected Deep Features for Visual Instance Retrieval
Recent studies show that aggregating activations of convolutional layers from CNN models together as a global descriptor leads to promising performance for instance retrieval. However, due to the global poolin...
-
Chapter and Conference Paper
Altered Functional Specialization in Temporal Lobe Epilepsy
Temporal epileptogenic network has been extensively characterized in temporal lobe epilepsy (TLE). How epilepsy networks supporting the pathological mechanisms interact with each other via within- and across-h...
-
Chapter and Conference Paper
Saliency Detection by Unifying Regression and Propagation
This paper introduces a novel saliency detection method by incorporating logistic regression into the label propagation framework, along with a principled weight computation for saliency fusion. First, the ini...
-
Chapter and Conference Paper
Robust Underwater Image Stitching Based on Graph Matching
Image stitching is important in intelligent perception and manipulation of underwater robots. In spite of a well developed technique, it is still challenging for underwater images because of their inevitable a...
-
Chapter and Conference Paper
Geographical and Overlap** Community Modeling Based on Business Circles for POI Recommendation
Point-of-interest (POI) recommendation is a challenging task since check-in data is extremely sparse and the social relationships in traditional recommendation have a limited effect. To solve this challenge, w...
-
Chapter and Conference Paper
Subspace Clustering Under Multiplicative Noise Corruption
Traditional subspace clustering models generally adopt the hypothesis of additive noise, which, however, dose not always hold. When it comes to multiplicative noise corruption, these models usually have poor p...
-
Chapter and Conference Paper
Hyperspectral Image Classification Based on Empirical Mode Decomposition and Local Binary Pattern
Traditional hyperspectral image classification methods always focused on spectral information, and lots of spatial information was neglected. Therefore, this paper introduces the spatial texture information in...
-
Chapter and Conference Paper
Blind Multi-frame Super Resolution with Non-identical Blur
Real world video super resolution is an challenging problem due to the complex motion field and unknown blur kernel. Although multi-frame super resolution has been extensively studied in past decades, it still...
-
Chapter and Conference Paper
Decentralized Pinning Synchronization of Colored Time-Delayed Networks via Decentralized Pinning Periodically Intermittent Control
This paper investigates synchronization of colored time-delayed networks via decentralized pinning periodically intermittent control. Unlike most pinning periodically intermittent control applying the pinned n...
-
Chapter and Conference Paper
Multi-image Deblurring Using Complement
The purpose of image restoration is to recover the latent image from the observed blurred images. In multi-image restoration, the input image’s quality directly affects the final deblurring result. In this pap...
-
Chapter and Conference Paper
Component Selection in Blind Source Separation of Brain Imaging Data
Brain imaging technology has been wildly used in neuroscience field. Because original imaging data usually have high dimensionality and a high noise level, dimensionality reduction is generally required to rem...
-
Chapter and Conference Paper
Robust Face Hallucination via Locality-Constrained Nuclear Norm Regularized Regression
The performance of traditional face recognition approaches is sharply reduced when facing a low-resolution (LR) probe face image. Various face hallucination methods have been proposed in the past decade to obt...
-
Chapter and Conference Paper
Fast Vein Pattern Extraction Based on a Binary Filter
Vein pattern extraction from Near-infrared (NIR) images is essential in most vein recognition algorithms. Among many vein recognition systems, the matched filter has been widely applied because it works well i...
-
Chapter and Conference Paper
Index Tracking by Using Sparse Support Vector Regression
In this paper a sparse support vector regression (SVR) model and its solution method are considered for the index tracking problem. The sparse SVR model is structured by adding a cardinality constraint in a ...
