arXiv subjects

Yu Zhou

Publications and source records attributed to Yu Zhou.

At least 397 records · Page 22Linked to original sources

arXiv2019

NCLS: Neural Cross-Lingual Summarization

Cross-lingual summarization (CLS) is the task to produce a summary in one particular language for a source document in a different language. Existing methods simply divide this task into two steps: summarization and translation, leading to the problem of error propagation. To handle that, we present an end-to-end CLS framework, which we refer to as Neural Cross-Lingual Summarization (NCLS), for the first time. Moreover, we propose to further improve NCLS by incorporating two related tasks, monolingual summarization and machine translation, into the training process of CLS under multi-task learning. Due to the lack of supervised CLS data, we propose a round-trip translation strategy to acquire two high-quality large-scale CLS datasets based on existing monolingual summarization datasets. Experimental results have shown that our NCLS achieves remarkable improvement over traditional pipeline methods on both English-to-Chinese and Chinese-to-English CLS human-corrected test sets. In addition, NCLS with multi-task learning can further significantly improve the quality of generated summaries. We make our dataset and code publicly available here: http://www.nlpr.ia.ac.cn/cip/dataset.htm.

cs.CL↗

arXiv2019

Single-Electron Transistor Made of a 3D Topological Insulator Nanoplate

Quantum confined devices of three-dimensional topological insulators have been proposed to be promising and of great importance for studies of confined topological states and for applications in low energy-dissipative spintronics and quantum information processing. The absence of energy gap on the TI surface limits the experimental realization of a quantum confined system in three-dimensional topological insulators. This communication reports on the successful realization of single-electron transistor devices in Bi$_2$Te$_3$ nanoplates by state of the art nanofabrication techniques. Each device consists of a confined central island, two narrow constrictions that connect the central island to the source and drain, and surrounding gates. Low-temperature transport measurements demonstrate that the two narrow constrictions function as tunneling junctions and the device shows well-defined Coulomb current oscillations and Coulomb diamond shaped charge stability diagrams. This work provides a controllable and reproducible way to form quantum confined systems in three-dimensional topological insulators, which should greatly stimulate research towards confined topological states, low energy-dissipative devices and quantum information processing.

cond-mat.mes-hall↗

arXiv2019

Coarse-to-fine Kidney Segmentation Framework Incorporating with Abnormal Detection and Correction

In this paper, we formulated the kidney segmentation task in a coarse-to-fine fashion, predicting a coarse label based on the entire CT image and a fine label based on the coarse segmentation and separated image patches. A key difference between the two stages lies in how input images were preprocessed; for the coarse segmentation, each 2D CT slice was normalized to be of the same image size (but possible different pixel size), and for the fine segmentation, each 2D CT slice was first resampled to be of the same pixel size and then cropped to be of the same image size. In other words, the image inputs to the coarse segmentation were 2D CT slices of the same image size whereas those to the fine segmentation were 2D MR patches of the same image size as well as the same pixel size. In addition, we design an abnormal detection method based on component analysis and use another 2D convolutional neural network to correct these abnormal regions between two stages. A total of 168 CT images were used to train the proposed framework and the evaluations were conducted qualitatively on other 42 testing images. The proposed method showed promising results and achieved 94.53 \% averaged DSC in testing data.

eess.IV↗

arXiv2019

Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning

Detecting curved text in the wild is very challenging. Recently, most state-of-the-art methods are segmentation based and require pixel-level annotations. We propose a novel scheme to train an accurate text detector using only a small amount of pixel-level annotated data and a large amount of data annotated with rectangles or even unlabeled data. A baseline model is first obtained by training with the pixel-level annotated data and then used to annotate unlabeled or weakly labeled data. A novel strategy which utilizes ground-truth bounding boxes to generate pseudo mask annotations is proposed in weakly-supervised learning. Experimental results on CTW1500 and Total-Text demonstrate that our method can substantially reduce the requirement of pixel-level annotated data. Our method can also generalize well across two datasets. The performance of the proposed method is comparable with the state-of-the-art methods with only 10% pixel-level annotated data and 90% rectangle-level weakly annotated data.

cs.CV↗

arXiv2019

A Novel Multi-layer Framework for Tiny Obstacle Discovery

For tiny obstacle discovery in a monocular image, edge is a fundamental visual element. Nevertheless, because of various reasons, e.g., noise and similar color distribution with background, it is still difficult to detect the edges of tiny obstacles at long distance. In this paper, we propose an obstacle-aware discovery method to recover the missing contours of these obstacles, which helps to obtain obstacle proposals as much as possible. First, by using visual cues in monocular images, several multi-layer regions are elaborately inferred to reveal the distances from the camera. Second, several novel obstacle-aware occlusion edge maps are constructed to well capture the contours of tiny obstacles, which combines cues from each layer. Third, to ensure the existence of the tiny obstacle proposals, the maps from all layers are used for proposals extraction. Finally, based on these proposals containing tiny obstacles, a novel obstacle-aware regressor is proposed to generate an obstacle occupied probability map with high confidence. The convincing experimental results with comparisons on the Lost and Found dataset demonstrate the effectiveness of our approach, achieving around 9.5% improvement on the accuracy than FPHT and PHT, it even gets comparable performance to MergeNet. Moreover, our method outperforms the state-of-the-art algorithms and significantly improves the discovery ability for tiny obstacles at long distance.

cs.CV↗

arXiv2019

Behavior-aware Service Access Control Mechanism using Security Policy Monitoring for SOA Systems

Service-oriented architecture (SOA) system has been widely utilized at many present business areas. However, SOA system is loosely coupled with multiple services and lacks the relevant security protection mechanisms, thus it can easily be attacked by unauthorized access and information theft. The existed access control mechanism can only prevent unauthorized users from accessing the system, but they can not prevent those authorized users (insiders) from attacking the system. To address this problem, we propose a behavior-aware service access control mechanism using security policy monitoring for SOA system. In our mechanism, a monitor program can supervise consumer's behaviors in run time. By means of trustful behavior model (TBM), if finding the consumer's behavior is of misusing, the monitor will deny its request. If finding the consumer's behavior is of malicious, the monitor will early terminate the consumer's access authorizations in this session or add the consumer into the Blacklist, whereby the consumer will not access the system from then on. In order to evaluate the feasibility of proposed mechanism, we implement a prototype system. The final results illustrate that our mechanism can effectively monitor consumer's behaviors and make effective responses when malicious behaviors really occur in run time. Moreover, as increasing the rule's number in TBM continuously, our mechanism can still work well.

cs.CR↗

arXiv2019

Occlusion-shared and Feature-separated Network for Occlusion Relationship Reasoning

Occlusion relationship reasoning demands closed contour to express the object, and orientation of each contour pixel to describe the order relationship between objects. Current CNN-based methods neglect two critical issues of the task: (1) simultaneous existence of the relevance and distinction for the two elements, i.e, occlusion edge and occlusion orientation; and (2) inadequate exploration to the orientation features. For the reasons above, we propose the Occlusion-shared and Feature-separated Network (OFNet). On one hand, considering the relevance between edge and orientation, two sub-networks are designed to share the occlusion cue. On the other hand, the whole network is split into two paths to learn the high-level semantic features separately. Moreover, a contextual feature for orientation prediction is extracted, which represents the bilateral cue of the foreground and background areas. The bilateral cue is then fused with the occlusion cue to precisely locate the object regions. Finally, a stripe convolution is designed to further aggregate features from surrounding scenes of the occlusion edge. The proposed OFNet remarkably advances the state-of-the-art approaches on PIOD and BSDS ownership dataset. The source code is available at https://github.com/buptlr/OFNet.

cs.CV↗

arXiv2019

Understanding Memory Modules on Learning Simple Algorithms

Recent work has shown that memory modules are crucial for the generalization ability of neural networks on learning simple algorithms. However, we still have little understanding of the working mechanism of memory modules. To alleviate this problem, we apply a two-step analysis pipeline consisting of first inferring hypothesis about what strategy the model has learned according to visualization and then verify it by a novel proposed qualitative analysis method based on dimension reduction. Using this method, we have analyzed two popular memory-augmented neural networks, neural Turing machine and stack-augmented neural network on two simple algorithm tasks including reversing a random sequence and evaluation of arithmetic expressions. Results have shown that on the former task both models can learn to generalize and on the latter task only the stack-augmented model can do so. We show that different strategies are learned by the models, in which specific categories of input are monitored and different policies are made based on that to change the memory.

cs.LG↗

arXiv2019

Memory Consolidation for Contextual Spoken Language Understanding with Dialogue Logistic Inference

Dialogue contexts are proven helpful in the spoken language understanding (SLU) system and they are typically encoded with explicit memory representations. However, most of the previous models learn the context memory with only one objective to maximizing the SLU performance, leaving the context memory under-exploited. In this paper, we propose a new dialogue logistic inference (DLI) task to consolidate the context memory jointly with SLU in the multi-task framework. DLI is defined as sorting a shuffled dialogue session into its original logical order and shares the same memory encoder and retrieval mechanism as the SLU model. Our experimental results show that various popular contextual SLU models can benefit from our approach, and improvements are quite impressive, especially in slot filling.

cs.CL↗

arXiv2019

High-precision terahertz frequency modulated continuous wave imaging method using continuous wavelet transform

Inspired by the extensive application of terahertz imaging technologies in the field of aerospace, we exploit a terahertz frequency modulated continuous wave imaging method with continuous wavelet transform algorithm to detect a multilayer heat shield made of special materials. This method uses the frequency modulation continuous wave system to catch the reflected terahertz signal and then processing the image data by the continuous wavelet transform with different basis functions. By calculating the sizes of the defects area in the final images and then comparing the results with real samples, a novel and practical high-precision terahertz imaging method are demonstrated. Our method can be an effective tool for the terahertz nondestructive testing of composites, drugs and some cultural heritages.

eess.SP↗

arXiv2019

Ultra-high-speed color imaging with single-pixel detectors under low light level

Single-pixel imaging is suitable for low light level scenarios because a bucket detector is employed to maximally collect the light from an object. However, one of the challenges is its slow imaging speed, mainly due to the slow light modulation technique. We here demonstrate 1.4MHz video imaging based on computational ghost imaging with a RGB LED array having a full-range frame rate up to 100MHz. With this method, the motion of a high speed propeller is observed. Moreover, by exploiting single-photon detectors to increase the detection efficiency, this method is developed for ultra-high-speed imaging under low light level.

physics.ins-det↗

arXiv2019

Naked-Eye Ghost Imaging via Photoelectric-Feedback

Based on optical correlations, ghost imaging is usually reconstructed by computer algorithm from the acquired data. We here proposed an alternatively high contrast naked-eye ghost imaging scheme which avoids computer algorithm processing. Instead, the proposed scheme uses a photoelectric feedback loop to realize the multiplication process of traditional ghost imaging. Meanwhile, it exploits the vision persistence effect to implement integral process and to generate negative images observed by naked eyes. To realize high contrast naked-eye ghost imaging, a special pattern-scanning architecture on a low-speed light-modulation mask is designed, which enables high-resolution imaging with lower-order Hadamard vectors and boosts the imaging speed as well. Moreover, two kinds of feedback circuits, the digital circuit and the analog circuit, are presented respectively, which can achieve high-speed feedback operation on the light intensity. With this approach, we demonstrate high-contrast real-time imaging for moving objects.

eess.IV↗

arXiv2019

All-optical naked-eye ghost imaging

Ghost imaging is usually based on optoelectronic process and eletronic computing. We here propose a new ghost imaging scheme, which avoids any optoelectronic or electronic process. Instead, the proposed scheme exploits all-optical correlation via the light-light interaction and the vision persistence effect to generate images observed by naked eyes. To realize high contrast naked-eye ghost imaging, a special pattern-scanning architecture on a low-speed light-modulation disk is designed, which also enables high-resolution imaging with lower-order Hadamard vectors and boosts the imaging speed. With this approach, we realize high-contrast real-time ghost imaging for moving colored objects.

eess.IV↗

arXiv2019

Optical switching of resonance fluorescence from a single germanium vacancy color center in diamond

Scalable quantum photonic networks require coherent excitation of quantum emitters. However, many solid-state systems can undergo a transition to a dark shelving state that inhibits the fluorescence. Here we demonstrate that a controlled gating using a weak non-resonant laser, the resonant excitation can be recovered and amplified for single germanium vacancies (GeVs). Employing the gated resonance excitation, we achieve optically stable resonance fluorescence of GeV centers. Our results are pivotal for the deployment of diamond color centers as reliable building blocks for scalable solid state quantum networks.

cond-mat.mes-hall↗

arXiv2019

Context-Constrained Accurate Contour Extraction for Occlusion Edge Detection

Occlusion edge detection requires both accurate locations and context constraints of the contour. Existing CNN-based pipeline does not utilize adaptive methods to filter the noise introduced by low-level features. To address this dilemma, we propose a novel Context-constrained accurate Contour Extraction Network (CCENet). Spatial details are retained and contour-sensitive context is augmented through two extraction blocks, respectively. Then, an elaborately designed fusion module is available to integrate features, which plays a complementary role to restore details and remove clutter. Weight response of attention mechanism is eventually utilized to enhance occluded contours and suppress noise. The proposed CCENet significantly surpasses state-of-the-art methods on PIOD and BSDS ownership dataset of object edge detection and occlusion orientation detection.

cs.CV↗

arXiv2019

Ferroelectric driven exciton and trion modulation in monolayer MoSe2 and WSe2

In this work, we show how domain engineered lithium niobate can be used to selectively dope monolayer MoSe2 and WSe2 and demonstrate that these ferroelectric domains can significantly enhance or inhibit photoluminescence (PL) with the most dramatic modulation occurring at the heterojunction interface between two domains. A micro-PL and Raman system is used to obtain spatially resolved images of the differently doped transition metal dichalcogenides (TMDs). The domain inverted lithium niobate causes changes in the TMDs due to electrostatic doping as a result of the remnant polarization from the substrate. Moreover, the differently doped TMDs (n-type MoSe2 and p-type WSe2) exhibit opposite PL modulation. Distinct oppositely charged domains were obtained with a 9-fold PL enhancement for the same single MoSe2 sheet when adhered to the positive (P+) and negative (P-) domains. This sharp PL modulation on the ferroelectric domain results from different free electron or hole concentrations in the materials conduction band or valence band. Moreover, excitons dissociate rapidly at the interface between the P+ and P- domains due to the built-in electric field. We are able to adjust the charge on the P+ and P- domains using temperature via the pyroelectric effect and observe rapid PL quenching over a narrow temperature range illustrating the observed PL modulation is electronic in nature. This observation creates an opportunity to harness the direct bandgap TMD 2D materials as an active optical component for the lithium niobate platform using domain engineering of the lithium niobate substrate to create optically active heterostructures that could be used for photodetectors or even electrically driven optical sources on-chip.

cond-mat.mtrl-sci↗

arXiv2018

Neural Abstract Style Transfer for Chinese Traditional Painting

Chinese traditional painting is one of the most historical artworks in the world. It is very popular in Eastern and Southeast Asia due to being aesthetically appealing. Compared with western artistic painting, it is usually more visually abstract and textureless. Recently, neural network based style transfer methods have shown promising and appealing results which are mainly focused on western painting. It remains a challenging problem to preserve abstraction in neural style transfer. In this paper, we present a Neural Abstract Style Transfer method for Chinese traditional painting. It learns to preserve abstraction and other style jointly end-to-end via a novel MXDoG-guided filter (Modified version of the eXtended Difference-of-Gaussians) and three fully differentiable loss terms. To the best of our knowledge, there is little work study on neural style transfer of Chinese traditional painting. To promote research on this direction, we collect a new dataset with diverse photo-realistic images and Chinese traditional paintings. In experiments, the proposed method shows more appealing stylized results in transferring the style of Chinese traditional painting than state-of-the-art neural style transfer methods.

cs.CV↗

arXiv2018

Evidence for Optically Thick, Eddington-limited Winds Driven by Supercritical Accretion

Supercritical accretion onto compact objects powers a massive wind that is optically thick and Eddington-limited. If most of the hard X-rays from the central disk are obscured by the wind, the source will display a blackbody-like spectrum with a luminosity scaled with the mass of the compact object. From the Chandra archive of nearby galaxies, we selected a sample of luminous and very soft sources and excluded contaminations from foreground objects and supernova remnants. They are found to be preferentially associated with late-type galaxies. The majority of sources in our sample are either too hot or too luminous to be explained by nuclear burning on the surface of white dwarfs, and are argued to be powered by accretion. The most likely explanation is that they are due to emission from the photosphere of a wind driven by supercritical accretion onto compact objects. Their blackbody luminosity ranges from ~10^37 to nearly 10^40 erg/s, indicative of the presence of both neutron stars and stellar-mass black holes. The blackbody luminosity also shows a possible bimodal distribution, albeit at low significance, peaked around the Eddington limit for neutron stars and stellar-mass black holes, respectively. If this can be confirmed, it will be smoking gun evidence that supercritical accretion powers thick winds. Based on a wind model, the inferred mass accretion rate of these objects is around a few hundred times the Eddington rate, suggesting that they may be intermediate between the canonical ultraluminous X-ray sources and SS 433 in terms of the accretion rate.

astro-ph.HE↗