arXiv subjects

Xiaolong Wang

Publications and source records attributed to Xiaolong Wang.

At least 307 records · Page 17Linked to original sources

arXiv2015

Answer Sequence Learning with Neural Networks for Answer Selection in Community Question Answering

In this paper, the answer selection problem in community question answering (CQA) is regarded as an answer sequence labeling task, and a novel approach is proposed based on the recurrent architecture for this problem. Our approach applies convolution neural networks (CNNs) to learning the joint representation of question-answer pair firstly, and then uses the joint representation as input of the long short-term memory (LSTM) to learn the answer sequence of a question for labeling the matching quality of each answer. Experiments conducted on the SemEval 2015 CQA dataset shows the effectiveness of our approach.

cs.CL↗

arXiv2015

Evolutionary Stages and Disk Properties of Young Stellar Objects in the Perseus Cloud

We investigated the evolutionary stages and disk properties of 211 Young stellar objects (YSOs) across the Perseus cloud by modeling the broadband optical to mid-infrared (IR) spectral energy distribution (SED). By exploring the relationships among the turnoff wave bands lambda_turnoff (longward of which significant IR excesses above the stellar photosphere are observed), the excess spectral index alpha_excess at lambda <~ 24 microns, and the disk inner radius R_in (from SED modeling) for YSOs of different evolutionary stages, we found that the median and standard deviation of alpha_excess of YSOs with optically thick disks tend to increase with lambda_turnoff, especially at lambda_turnoff >= 5.8 microns, whereas the median fractional dust luminosities L_dust/L_star tend to decrease with lambda_turnoff. This points to an inside-out disk clearing of small dust grains. Moreover, a positive correlation between alpha_excess and R_in was found at alpha_excess > ~0 and R_in > ~10 $\times$ the dust sublimation radius R_sub, irrespective of lambda_turnoff, L_dust/L_star and disk flaring. This suggests that the outer disk flaring either does not evolve synchronously with the inside-out disk clearing or has little influence on alpha_excess shortward of 24 microns. About 23% of our YSO disks are classified as transitional disks, which have lambda_turnoff >= 5.8 microns and L_dust/L_star >10^(-3). The transitional disks and full disks occupy distinctly different regions on the L_dust/L_star vs. alpha_excess diagram. Taking L_dust/L_star as an approximate discriminator of disks with (>0.1) and without (<0.1) considerable accretion activity, we found that 65% and 35% of the transitional disks may be consistent with being dominantly cleared by photoevaporation and dynamical interaction respectively. [abridged]

astro-ph.SR↗

arXiv2015

In Defense of the Direct Perception of Affordances

The field of functional recognition or affordance estimation from images has seen a revival in recent years. As originally proposed by Gibson, the affordances of a scene were directly perceived from the ambient light: in other words, functional properties like sittable were estimated directly from incoming pixels. Recent work, however, has taken a mediated approach in which affordances are derived by first estimating semantics or geometry and then reasoning about the affordances. In a tribute to Gibson, this paper explores his theory of affordances as originally proposed. We propose two approaches for direct perception of affordances and show that they obtain good results and can out-perform mediated approaches. We hope this paper can rekindle discussion around direct perception and its implications in the long term.

cs.CV↗

arXiv2015

Dynamical And-Or Graph Learning for Object Shape Modeling and Detection

This paper studies a novel discriminative part-based model to represent and recognize object shapes with an "And-Or graph". We define this model consisting of three layers: the leaf-nodes with collaborative edges for localizing local parts, the or-nodes specifying the switch of leaf-nodes, and the root-node encoding the global verification. A discriminative learning algorithm, extended from the CCCP [23], is proposed to train the model in a dynamical manner: the model structure (e.g., the configuration of the leaf-nodes associated with the or-nodes) is automatically determined with optimizing the multi-layer parameters during the iteration. The advantages of our method are two-fold. (i) The And-Or graph model enables us to handle well large intra-class variance and background clutters for object shape detection from images. (ii) The proposed learning algorithm is able to obtain the And-Or graph representation without requiring elaborate supervision and initialization. We validate the proposed method on several challenging databases (e.g., INRIA-Horse, ETHZ-Shape, and UIUC-People), and it outperforms the state-of-the-arts approaches.

cs.CV↗

arXiv2015

Deep Joint Task Learning for Generic Object Extraction

This paper investigates how to extract objects-of-interest without relying on hand-craft features and sliding windows approaches, that aims to jointly solve two sub-tasks: (i) rapidly localizing salient objects from images, and (ii) accurately segmenting the objects based on the localizations. We present a general joint task learning framework, in which each task (either object localization or object segmentation) is tackled via a multi-layer convolutional neural network, and the two networks work collaboratively to boost performance. In particular, we propose to incorporate latent variables bridging the two networks in a joint optimization manner. The first network directly predicts the positions and scales of salient objects from raw images, and the latent variables adjust the object localizations to feed the second network that produces pixelwise object masks. An EM-type method is presented for the optimization, iterating with two steps: (i) by using the two networks, it estimates the latent variables by employing an MCMC-based sampling method; (ii) it optimizes the parameters of the two networks unitedly via back propagation, with the fixed latent variables. Extensive experiments suggest that our framework significantly outperforms other state-of-the-art approaches in both accuracy and efficiency (e.g. 1000 times faster than competing approaches).

cs.CV↗

arXiv2015

Learning Contour-Fragment-based Shape Model with And-Or Tree Representation

This paper proposes a simple yet effective method to learn the hierarchical object shape model consisting of local contour fragments, which represents a category of shapes in the form of an And-Or tree. This model extends the traditional hierarchical tree structures by introducing the "switch" variables (i.e. the or-nodes) that explicitly specify production rules to capture shape variations. We thus define the model with three layers: the leaf-nodes for detecting local contour fragments, the or-nodes specifying selection of leaf-nodes, and the root-node encoding the holistic distortion. In the training stage, for optimization of the And-Or tree learning, we extend the concave-convex procedure (CCCP) by embedding the structural clustering during the iterative learning steps. The inference of shape detection is consistent with the model optimization, which integrates the local testings via the leaf-nodes and or-nodes with the global verification via the root-node. The advantages of our approach are validated on the challenging shape databases (i.e., ETHZ and INRIA Horse) and summarized as follows. (1) The proposed method is able to accurately localize shape contours against unreliable edge detection and edge tracing. (2) The And-Or tree model enables us to well capture the intraclass variance.

cs.CV↗

arXiv2015

Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection

This paper proposes a reconfigurable model to recognize and detect multiclass (or multiview) objects with large variation in appearance. Compared with well acknowledged hierarchical models, we study two advanced capabilities in hierarchy for object modeling: (i) "switch" variables(i.e. or-nodes) for specifying alternative compositions, and (ii) making local classifiers (i.e. leaf-nodes) shared among different classes. These capabilities enable us to account well for structural variabilities while preserving the model compact. Our model, in the form of an And-Or Graph, comprises four layers: a batch of leaf-nodes with collaborative edges in bottom for localizing object parts; the or-nodes over bottom to activate their children leaf-nodes; the and-nodes to classify objects as a whole; one root-node on the top for switching multiclass classification, which is also an or-node. For model training, we present an EM-type algorithm, namely dynamical structural optimization (DSO), to iteratively determine the structural configuration, (e.g., leaf-node generation associated with their parent or-nodes and shared across other classes), along with optimizing multi-layer parameters. The proposed method is valid on challenging databases, e.g., PASCAL VOC 2007 and UIUC-People, and it achieves state-of-the-arts performance.

cs.CV↗

arXiv2015

An Expressive Deep Model for Human Action Parsing from A Single Image

This paper aims at one newly raising task in vision and multimedia research: recognizing human actions from still images. Its main challenges lie in the large variations in human poses and appearances, as well as the lack of temporal motion information. Addressing these problems, we propose to develop an expressive deep model to naturally integrate human layout and surrounding contexts for higher level action understanding from still images. In particular, a Deep Belief Net is trained to fuse information from different noisy sources such as body part detection and object detection. To bridge the semantic gap, we used manually labeled data to greatly improve the effectiveness and efficiency of the pre-training and fine-tuning stages of the DBN training. The resulting framework is shown to be robust to sometimes unreliable inputs (e.g., imprecise detections of human parts and objects), and outperforms the state-of-the-art approaches.

cs.CV↗

arXiv2015

Discriminatively Trained And-Or Graph Models for Object Shape Detection

In this paper, we investigate a novel reconfigurable part-based model, namely And-Or graph model, to recognize object shapes in images. Our proposed model consists of four layers: leaf-nodes at the bottom are local classifiers for detecting contour fragments; or-nodes above the leaf-nodes function as the switches to activate their child leaf-nodes, making the model reconfigurable during inference; and-nodes in a higher layer capture holistic shape deformations; one root-node on the top, which is also an or-node, activates one of its child and-nodes to deal with large global variations (e.g. different poses and views). We propose a novel structural optimization algorithm to discriminatively train the And-Or model from weakly annotated data. This algorithm iteratively determines the model structures (e.g. the nodes and their layouts) along with the parameter learning. On several challenging datasets, our model demonstrates the effectiveness to perform robust shape-based object detection against background clutter and outperforms the other state-of-the-art approaches. We also release a new shape database with annotations, which includes more than 1500 challenging shape instances, for recognition and detection.

cs.CV↗

arXiv2015

3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks

Human activity understanding with 3D/depth sensors has received increasing attention in multimedia processing and interactions. This work targets on developing a novel deep model for automatic activity recognition from RGB-D videos. We represent each human activity as an ensemble of cubic-like video segments, and learn to discover the temporal structures for a category of activities, i.e. how the activities to be decomposed in terms of classification. Our model can be regarded as a structured deep architecture, as it extends the convolutional neural networks (CNNs) by incorporating structure alternatives. Specifically, we build the network consisting of 3D convolutions and max-pooling operators over the video segments, and introduce the latent variables in each convolutional layer manipulating the activation of neurons. Our model thus advances existing approaches in two aspects: (i) it acts directly on the raw inputs (grayscale-depth data) to conduct recognition instead of relying on hand-crafted features, and (ii) the model structure can be dynamically adjusted accounting for the temporal variations of human activities, i.e. the network configuration is allowed to be partially activated during inference. For model training, we propose an EM-type optimization method that iteratively (i) discovers the latent structure by determining the decomposed actions for each training example, and (ii) learns the network parameters by using the back-propagation algorithm. Our approach is validated in challenging scenarios, and outperforms state-of-the-art methods. A large human activity database of RGB-D videos is presented in addition.

cs.CV↗

arXiv2015

Electric Field and Humidity Trigger Contact Electrification

Here, we study the old problem of why identical insulators can charge one another on contact. We perform several experiments showing that, if driven by a preexisting electric field, charge is transferred between contacting insulators. This happens because the insulator surfaces adsorb small amounts of water from a humid atmosphere. We believe the electric field then separates positively from negatively charged ions prevailing within the water, which we believe to be hydronium and hydroxide ions, such that at the point of contact, positive ions of one insulator neutralize negative ions of the other one, charging both of them. This mechanism can explain for the first time the observation made four decades ago that wind-blown sand discharges in sparks if and only if a thunderstorm is nearby.

cond-mat.soft↗

arXiv2014

Designing Deep Networks for Surface Normal Estimation

In the past few years, convolutional neural nets (CNN) have shown incredible promise for learning visual representations. In this paper, we use CNNs for the task of predicting surface normals from a single image. But what is the right architecture we should use? We propose to build upon the decades of hard work in 3D scene understanding, to design new CNN architecture for the task of surface normal estimation. We show by incorporating several constraints (man-made, manhattan world) and meaningful intermediate representations (room layout, edge labels) in the architecture leads to state of the art performance on surface normal estimation. We also show that our network is quite robust and show state of the art results on other datasets as well without any fine-tuning.

cs.CV↗

arXiv2014

Previous R&D of vibrating wire alignment technique for HEPS

The alignment tolerance of multipoles on a girder is better than 30um in the storage ring of High Energy Photon Source HEPS which will be the next project at IHEP Institute of High Energy Physics. This is difficult to meet the precision only using the traditional optical survey method. In order to achieve this goal, vibrating wire alignment technique with high precision and sensitivity is considered to be used in this project. This paper presents some previous research works about theory, scheme design and achievements.

physics.acc-ph↗

arXiv2014

Radical-Enhanced Chinese Character Embedding

We present a method to leverage radical for learning Chinese character embedding. Radical is a semantic and phonetic component of Chinese character. It plays an important role as characters with the same radical usually have similar semantic meaning and grammatical usage. However, existing Chinese processing algorithms typically regard word or character as the basic unit but ignore the crucial radical information. In this paper, we fill this gap by leveraging radical for learning continuous representation of Chinese character. We develop a dedicated neural architecture to effectively learn character embedding and apply it on Chinese character similarity judgement and Chinese word segmentation. Experiment results show that our radical-enhanced method outperforms existing embedding learning algorithms on both tasks.

cs.CL↗

arXiv2013

Damage threshold and focusability of mid-infrared free-electron laser pulses gated by a plasma mirror with nanosecond switching pulses

The presence of a pulse train structure of an oscillator-type free-electron laser (FEL) results in the immediate damage of a solid target upon focusing. We demonstrate that the laser-induced damage threshold can be significantly improved by gating the mid-infrared (MIR) FEL pulses with a plasma mirror. Although the switching pulses we employ have a nanosecond duration which does not guarantee the clean wavefront of the gated FEL pulses, the high focusablity is experimentally confirmed through the observation of spectral broadening by a factor of 2.1 when we tightly focus the gated FEL pulses onto the Ge plate.

physics.optics↗

arXiv2013

Diagnosis of the Wavelength Stability of a Mid-Infrared Free-Electron Laser

Wavelength stability of free-electron lasers (FELs) is one of the important parameters for various applications. In this paper we describe two different methods to diagnose the wavelength stability of a mid-infrared (MIR) FEL. The first one is based on autocorrelation which is usually used to measure the pulse duration, and the second one is based on frequency upconversion through sum-frequency mixing (SFM).

physics.optics↗

arXiv2013

Automatic Calibration Method of Voxel Size for Cone-beam 3D-CT Scanning System

For cone-beam three-dimensional computed tomography (3D-CT) scanning system, voxel size is an important indicator to guarantee the accuracy of data analysis and feature measurement based on 3D-CT images. Meanwhile, the voxel size changes with the movement of the rotary table along X-ray direction. In order to realize the automatic calibration of the voxel size, a new easily-implemented method is proposed. According to this method, several projections of a spherical phantom are captured at different imaging positions and the corresponding voxel size values are calculated by non-linear least square fitting. Through these interpolation values, a linear equation is obtained, which reflects the relationship between the rotary table displacement distance from its nominal zero position and the voxel size. Finally, the linear equation is imported into the calibration module of the 3D-CT scanning system, and when the rotary table is moving along X-ray direction, the accurate value of the voxel size is dynamically exported. The experimental results prove that this method meets the requirements of the actual CT scanning system, and has virtues of easy implementation and high accuracy

physics.ins-det↗

arXiv2012

Single-shot spectra of temporally selected micropulses from a mid-infrared free-electron laser by upconversion

We demonstrate the measurement of single-shot spectra of temporally selected micropulses from a mid-infrared (MIR) free-electron laser (FEL) by upconversion. We achieve the upconversion of FEL pulses at 11 μm using externally synchronized Nd:YAG or microchip laser pulses at 1064 nm to produce sum-frequency mixing (SFM) signals at 970 nm, which are detected by a compact CCD spectrometer without an intensifier. Our experimental system is very cost-effective, and allows us to obtain the laser spectra of selected micropulses at any temporal position within a single macropulse from an oscillator-type FEL.

physics.optics↗