Xiaoming Liu

Xiaoming Liu
Are you Xiaoming Liu?

Claim your profile, edit publications, add additional information:

Contact Details

Name
Xiaoming Liu
Affiliation
Location

Pubs By Year

Pub Categories

 
Computer Science - Digital Libraries (7)
 
Computer Science - Computer Vision and Pattern Recognition (6)
 
Physics - Materials Science (2)
 
Physics - Physics and Society (2)
 
Physics - Optics (2)
 
Computer Science - Information Retrieval (1)
 
Computer Science - Data Structures and Algorithms (1)
 
Computer Science - Distributed; Parallel; and Cluster Computing (1)

Publications Authored By Xiaoming Liu

Despite recent advances in face recognition using deep learning, severe accuracy drops are observed for large pose variations in unconstrained environments. Learning pose-invariant features is one solution, but needs expensively labeled large scale data and carefully designed feature learning algorithms. In this work, we focus on frontalizing faces in the wild under various head poses, including extreme profile views. Read More

This paper explores multi-task learning (MTL) for face recognition. We answer the questions of how and why MTL can improve the face recognition performance. First, we propose a multi-task Convolutional Neural Network (CNN) for face recognition where identity recognition is the main task and pose, illumination, and expression estimations are the side tasks. Read More

Global motion compensation (GMC) removes the impact of camera motion and creates a video in which the background appears static over the progression of time. Various vision problems, such as human activity recognition, background reconstruction, and multi-object tracking can benefit from GMC. Existing GMC algorithms rely on sequentially processing consecutive frames, by estimating the transformation mapping the two frames, and obtaining a composite transformation to a global motion compensated coordinate. Read More

Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in CV community. However, most algorithms are designed for faces in small to medium poses (below 45 degree), lacking the ability to align faces in large poses up to 90 degree. The challenges are three-fold: Firstly, the commonly used landmark-based face model assumes that all the landmarks are visible and is therefore not suitable for profile views. Read More

Anomalous field enhancement accompanied by resonant absorption phenomenon was originally discussed in the context of plasma physics and in applications related to radio-communications between the ground and spacecraft returning to Earth. Indeed, there is a critical period of time when all communications are lost due to the reflection/absorption of electromagnetic waves by the sheath of plasma created by a high speed vehicle re-entering the atmosphere. While detailed experimental studies of these phenomena in space are challenging, the emergence of electromagnetic metamaterials enables researchers exceptional flexibility to study them in the laboratory environment. Read More

Face alignment aims to estimate the locations of a set of landmarks for a given image. This problem has received much attention as evidenced by the recent advancement in both the methodology and performance. However, most of the existing works neither explicitly handle face images with arbitrary poses, nor perform large-scale experiments on non-frontal and profile face images. Read More

This paper proposes a novel framework for fluorescence plant video processing. Biologists are interested in the leaf level photosynthetic analysis within a plant. A prerequisite for such analysis is to segment all leaves, estimate their structures and track them over time. Read More

Graph partition is a fundamental problem of parallel computing for big graph data. Many graph partition algorithms have been proposed to solve the problem in various applications, such as matrix computations and PageRank, etc., but none has pay attention to random walks. Read More

All-optical switching based on optical nonlinearity must undergo complex processes of light-mater interaction in atom and electron scale, so a relative high power and long response time is required, that construct main bottlenecks in all-optical technology. In this paper, we propose a new mechanism for building all-optical switching based on a change resonance modes of meta-atoms in metamaterials, not involved optical nonlinearity of materials. A metamaterial composed of cubic dielectric meta-atoms periodically embedded in a background matrix is designed and constructed. Read More

Dielectric materials with tunable permittivity are highly desirable for wireless communication, radar technology. However, the tunability of dielectric properties in the microwave frequency range and higher is an immense challenge for conventional materials. Here, we demonstrate a giant magnetodielectric effect in the GHz region in a metamaterial based on ferrite unit cells. Read More

Overlap is one of the characteristics of social networks, in which a person may belong to more than one social group. For this reason, discovering overlapping structures is necessary for realistic social analysis. In this paper, we present a novel, general framework to detect and analyze both individual overlapping nodes and entire communities. Read More

In the emerging eScience environment, repositories of papers, datasets, software, etc., should be the foundation of a global and natively-digital scholarly communications system. The current infrastructure falls far short of this goal. Read More

Various efforts aimed at representing digital assets have emerged from several communities over the last years, including the Metadata Encoding and Transmission Standard (METS), the IMS Content Packaging (IMS-CP) XML Binding and the XML Formatted Data Units (XFDU). The MPEG-21 Digital Item Declaration (MPEG-21 DID) is another approach that can be used for the representation of digital assets in XML. This paper will explore the potential of the MPEG-21 DID in a Digital Preservation context, by looking at the core building blocks of the OAIS Information Model and the way in which they map to the MPEG-21 DID abstract model and the MPEG-21 DIDL XML syntax. Read More

We describe mod_oai, an Apache 2.0 module that implements the Open Archives Initiative Protocol for Metadata Harvesting (OAI-PMH). OAIPMH is the de facto standard for metadata exchange in digital libraries and allows repositories to expose their contents in a structured, application-neutral format with semantics optimized for accurate incremental harvesting. Read More

This paper introduces the write-once/read-many XMLtape/ARC storage approach for Digital Objects and their constituent datastreams. The approach combines two interconnected file-based storage mechanisms that are made accessible in a protocol-based manner. First, XML-based representations of multiple Digital Objects are concatenated into a single file named an XMLtape. Read More

The field of digital libraries (DLs) coalesced in 1994: the first digital library conferences were held that year, awareness of the World Wide Web was accelerating, and the National Science Foundation awarded $24 Million (U.S.) for the Digital Library Initiative (DLI). Read More

This paper describes the aDORe repository architecture, designed and implemented for ingesting, storing, and accessing a vast collection of Digital Objects at the Research Library of the Los Alamos National Laboratory. The aDORe architecture is highly modular and standards-based. In the architecture, the MPEG-21 Digital Item Declaration Language is used as the XML-based format to represent Digital Objects that can consist of multiple datastreams as Open Archival Information System Archival Information Packages (OAIS AIPs). Read More

This paper discusses the requirements of current and emerging applications based on the Open Archives Initiative (OAI) and emphasizes the need for a common infrastructure to support them. Inspired by HTTP proxy, cache, gateway and web service concepts, a design for a scalable and reliable infrastructure that aims at satisfying these requirements is presented. Moreover it is shown how various applications can exploit the services included in the proposed infrastructure. Read More