arXiv subjects

Yang Hu

Publications and source records attributed to Yang Hu.

At least 217 records · Page 12Linked to original sources

arXiv2018

FashionNet: Personalized Outfit Recommendation with Deep Neural Network

With the rapid growth of fashion-focused social networks and online shopping, intelligent fashion recommendation is now in great need. We design algorithms which automatically suggest users outfits (e.g. a shirt, together with a skirt and a pair of high-heel shoes), that fit their personal fashion preferences. Recommending sets, each of which is composed of multiple interacted items, is relatively new to recommender systems, which usually recommend individual items to users. We explore the use of deep networks for this challenging task. Our system, dubbed FashionNet, consists of two components, a feature network for feature extraction and a matching network for compatibility computation. The former is achieved through a deep convolutional network. And for the latter, we adopt a multi-layer fully-connected network structure. We design and compare three alternative architectures for FashionNet. To achieve personalized recommendation, we develop a two-stage training strategy, which uses the fine-tuning technique to transfer a general compatibility model to a model that embeds personal preference. Experiments on a large scale data set collected from a popular fashion-focused social network validate the effectiveness of the proposed networks.

cs.CV↗

arXiv2018

A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation

In this paper, we propose a novel fully convolutional two-stream fusion network (FCTSFN) for interactive image segmentation. The proposed network includes two sub-networks: a two-stream late fusion network (TSLFN) that predicts the foreground at a reduced resolution, and a multi-scale refining network (MSRN) that refines the foreground at full resolution. The TSLFN includes two distinct deep streams followed by a fusion network. The intuition is that, since user interactions are more direct information on foreground/background than the image itself, the two-stream structure of the TSLFN reduces the number of layers between the pure user interaction features and the network output, allowing the user interactions to have a more direct impact on the segmentation result. The MSRN fuses the features from different layers of TSLFN with different scales, in order to seek the local to global information on the foreground to refine the segmentation result at full resolution. We conduct comprehensive experiments on four benchmark datasets. The results show that the proposed network achieves competitive performance compared to current state-of-the-art interactive image segmentation methods

cs.CV↗

arXiv2018

Metabolize Neural Network

The metabolism of cells is the most basic and important part of human function. Neural networks in deep learning stem from neuronal activity. It is self-evident that the significance of metabolize neuronal network(MetaNet) in model construction. In this study, we explore neuronal metabolism for shallow network from proliferation and autophagy two aspects. First, we propose different neuron proliferate methods that constructive the selfgrowing network in metabolism cycle. Proliferate neurons alleviate resources wasting and insufficient model learning problem when network initializes more or less parameters. Then combined with autophagy mechanism in the process of model self construction to ablate under-expressed neurons. The MetaNet can automatically determine the number of neurons during training, further, save more resource consumption. We verify the performance of the proposed methods on datasets: MNIST, Fashion-MNIST and CIFAR-10.

cs.NE↗

arXiv2018

Robotic Sewing and Knot Tying for Personalized Stent Graft Manufacturing

This paper presents a versatile robotic system for sewing 3D structured object. Leveraging on using a customized robotic sewing device and closed-loop visual servoing control, an all-in-one solution for sewing personalized stent graft is demonstrated. Stitch size planning and automatic knot tying are proposed as the two key functions of the system. By using effective stitch size planning, sub-millimetre sewing accuracy is achieved for stitch sizes ranging from 2mm to 5mm. In addition, a thread manipulator for thread management and tension control is also proposed to perform successive knot tying to secure each stitch. Detailed laboratory experiments have been performed to access the proposed instruments and allied algorithms. The proposed framework can be generalised to a wide range of applications including 3D industrial sewing, as well as transferred to other clinical areas such as surgical suturing.

cs.RO↗

arXiv2018

Facial Expression Recognition Based on Complexity Perception Classification Algorithm

Facial expression recognition (FER) has always been a challenging issue in computer vision. The different expressions of emotion and uncontrolled environmental factors lead to inconsistencies in the complexity of FER and variability of between expression categories, which is often overlooked in most facial expression recognition systems. In order to solve this problem effectively, we presented a simple and efficient CNN model to extract facial features, and proposed a complexity perception classification (CPC) algorithm for FER. The CPC algorithm divided the dataset into an easy classification sample subspace and a complex classification sample subspace by evaluating the complexity of facial features that are suitable for classification. The experimental results of our proposed algorithm on Fer2013 and CK-plus datasets demonstrated the algorithm's effectiveness and superiority over other state-of-the-art approaches.

cs.CV↗

arXiv2018

Tongue image constitution recognition based on Complexity Perception method

Background and Object: In China, body constitution is highly related to physiological and pathological functions of human body and determines the tendency of the disease, which is of great importance for treatment in clinical medicine. Tongue diagnosis, as a key part of Traditional Chinese Medicine inspection, is an important way to recognize the type of constitution.In order to deploy tongue image constitution recognition system on non-invasive mobile device to achieve fast, efficient and accurate constitution recognition, an efficient method is required to deal with the challenge of this kind of complex environment. Methods: In this work, we perform the tongue area detection, tongue area calibration and constitution classification using methods which are based on deep convolutional neural network. Subject to the variation of inconstant environmental condition, the distribution of the picture is uneven, which has a bad effect on classification performance. To solve this problem, we propose a method based on the complexity of individual instances to divide dataset into two subsets and classify them separately, which is capable of improving classification accuracy. To evaluate the performance of our proposed method, we conduct experiments on three sizes of tongue datasets, in which deep convolutional neural network method and traditional digital image analysis method are respectively applied to extract features for tongue images. The proposed method is combined with the base classifier Softmax, SVM, and DecisionTree respectively. Results: As the experiments results shown, our proposed method improves the classification accuracy by 1.135% on average and achieves 59.99% constitution classification accuracy. Conclusions: Experimental results on three datasets show that our proposed method can effectively improve the classification accuracy of tongue constitution recognition.

cs.CV↗

arXiv2018

Identifying interatomic potentials for the accurate modeling of interfacial segregation and structural transitions

Chemical segregation and structural transitions at interfaces are important nanoscale phenomena, making them natural targets for atomistic modeling, yet interatomic potentials must be fit to secondary physical properties. To isolate the important factors that interatomic potentials must capture in order to accurately model such behavior, the performance of four interatomic potentials was evaluated for the Cu-Zr system, with experimental observations used to provide validation. While experimental results show strong Zr segregation to grain boundary regions and the formation of nanoscale amorphous complexions at high temperatures and/or dopant compositions, a variety of disparate behaviors can be observed in hybrid Monte Carlo/molecular dynamics simulations of doping, depending on the chosen potential. The potentials that are able to recreate the correct behavior accurately reproduce the enthalpy of mixing as well as the bond energies, providing a roadmap for the exploration of interfacial phenomena with atomistic modeling. Finally, we use our observations to find a reliable potential for the Ni-Zr system and show that this alloy should also be able to sustain amorphous complexions.

cond-mat.mtrl-sci↗

arXiv2018

Non-Thermal Cosmic Rays During Big Bang Nucleosynthesis to Solve the Lithium Problem

The discrepancy between the theoretical prediction of primordial lithium abundances and astronomical observations is called the Lithium Problem. We find that extra contributions from non-thermal hydrogen and helium during Big Bang nucleosynthesis can explain the discrepancy, for both Li-7 and Li-6, and will change the deuterium abundance only little. The allowed parameter space of such an amount of non-thermal particles and the energy range is shown. The hypothesis is stable regardless of the cross-section uncertainty of relevant reactions and the explicit shape of the energy spectrum.

astro-ph.CO↗

arXiv2017

Multi-stage Suture Detection for Robot Assisted Anastomosis based on Deep Learning

In robotic surgery, task automation and learning from demonstration combined with human supervision is an emerging trend for many new surgical robot platforms. One such task is automated anastomosis, which requires bimanual needle handling and suture detection. Due to the complexity of the surgical environment and varying patient anatomies, reliable suture detection is difficult, which is further complicated by occlusion and thread topologies. In this paper, we propose a multi-stage framework for suture thread detection based on deep learning. Fully convolutional neural networks are used to obtain the initial detection and the overlapping status of suture thread, which are later fused with the original image to learn a gradient road map of the thread. Based on the gradient road map, multiple segments of the thread are extracted and linked to form the whole thread using a curvilinear structure detector. Experiments on two different types of sutures demonstrate the accuracy of the proposed framework.

cs.CV↗

arXiv2017

A Multi-Robot Cooperation Framework for Sewing Personalized Stent Grafts

This paper presents a multi-robot system for manufacturing personalized medical stent grafts. The proposed system adopts a modular design, which includes: a (personalized) mandrel module, a bimanual sewing module, and a vision module. The mandrel module incorporates the personalized geometry of patients, while the bimanual sewing module adopts a learning-by-demonstration approach to transfer human hand-sewing skills to the robots. The human demonstrations were firstly observed by the vision module and then encoded using a statistical model to generate the reference motion trajectories. During autonomous robot sewing, the vision module plays the role of coordinating multi-robot collaboration. Experiment results show that the robots can adapt to generalized stent designs. The proposed system can also be used for other manipulation tasks, especially for flexible production of customized products and where bimanual or multi-robot cooperation is required.

cs.RO↗

arXiv2017

Endoscopic Depth Measurement and Super-Spectral-Resolution Imaging

Intra-operative measurements of tissue shape and multi/ hyperspectral information have the potential to provide surgical guidance and decision making support. We report an optical probe based system to combine sparse hyperspectral measurements and spectrally-encoded structured lighting (SL) for surface measurements. The system provides informative signals for navigation with a surgical interface. By rapidly switching between SL and white light (WL) modes, SL information is combined with structure-from-motion (SfM) from white light images, based on SURF feature detection and Lucas-Kanade (LK) optical flow to provide quasi-dense surface shape reconstruction with known scale in real-time. Furthermore, "super-spectral-resolution" was realized, whereby the RGB images and sparse hyperspectral data were integrated to recover dense pixel-level hyperspectral stacks, by using convolutional neural networks to upscale the wavelength dimension. Validation and demonstration of this system is reported on ex vivo/in vivo animal/ human experiments.

cs.CV↗

arXiv2017

DOA Estimation of Coherent Signals on Coprime Arrays Exploiting Fourth-Order Cumulants

This paper considers the problem of direction-of-arrival (DOA) estimation of coherent signals on passive coprime arrays, where we resort to the fourth-order cumulants of the received signal to explore more information. A fourth-order cumulant matrix (FCM) is introduced for the coprime arrays. The special structure of the FCM is combined with the array configuration to resolve the coherent signals. Since each sparse array of the coprime arrays is uniform, a series of overlapping identical subarrays can be extracted. Using this property, we propose a generalized spatial smoothing scheme applied to the FCM. From the smoothed FCM, the DOAs of both the coherent and independent signals can be successfully estimated on the pseudo-spectrum generated by the fourth-order MUSIC algorithm. To overcome the problem of occasional false peak appearing on the pseudo-spectrum, we use a supplementary sparse array whose inter-sensor spacing is coprime to that of either existing sparse array. From the combined spectrum aided by the supplementary sensors, the false peaks are removed while the true peaks remain. The effectiveness of the proposed methods is demonstrated by simulation examples.

cs.IT↗

arXiv2016

Taming Energy Cost of Disk Encryption Software on Data-Intensive Mobile Devices

Disk encryption is frequently used to secure confidential data on mobile devices. However, the high energy cost of disk encryption poses a heavy burden on those devices with limited battery capacity especially when a large amount of data needs to be protected by disk encryption. To address the challenge, we develop a new kernel-level disk encryption software, Populus. Almost 98% of Populus's encryption/decryption computation is not related with the input plaintext/ciphertext, so we accomplish the computation in advance during initialization when a consistent power supply is available. We conduct cryptanalysis on Populus and finally conclude that state-of-the-art cryptanalysis techniques fail to break Populus in reasonable computational complexity. We also conduct energy consumption experiments on Populus and dm-crypt, a famous disk encryption software for Android and Linux mobile devices. The experimental results demonstrate that Populus consumes 50%-70% less energy than dm-crypt.

cs.CR↗

arXiv2015

Person Re-identification by Local Maximal Occurrence Representation and Metric Learning

Person re-identification is an important technique towards automatic search of a person's presence in a surveillance video. Two fundamental problems are critical for person re-identification, feature representation and metric learning. An effective feature representation should be robust to illumination and viewpoint changes, and a discriminant metric should be learned to match various person images. In this paper, we propose an effective feature representation called Local Maximal Occurrence (LOMO), and a subspace and metric learning method called Cross-view Quadratic Discriminant Analysis (XQDA). The LOMO feature analyzes the horizontal occurrence of local features, and maximizes the occurrence to make a stable representation against viewpoint changes. Besides, to handle illumination variations, we apply the Retinex transform and a scale invariant texture operator. To learn a discriminant metric, we propose to learn a discriminant low dimensional subspace by cross-view quadratic discriminant analysis, and simultaneously, a QDA metric is learned on the derived subspace. We also present a practical computation method for XQDA, as well as its regularization. Experiments on four challenging person re-identification databases, VIPeR, QMUL GRID, CUHK Campus, and CUHK03, show that the proposed method improves the state-of-the-art rank-1 identification rates by 2.2%, 4.88%, 28.91%, and 31.55% on the four databases, respectively.

cs.CV↗

arXiv2014

High Range Resolution Profiling in Missing Data Case: A New Approach

We have proposed a novel method for Synthetic High Range Resolution (HRR) profiling, under the condition of missing frequency domain samples. This new approach estimates the autocovariance function (ACF) of the signal by valid sample pairs. Autocovariance matrix is formed from ACF estimations. Even with large part of data missing, new approach exhibits robust profiling result. Simulations are presented to show a advantage over other approaches in missing data case. Moreover, a real radar experiment was conducted to validate the new approach.

cs.IT↗

arXiv2014

Open-set Person Re-identification

Person re-identification is becoming a hot research for developing both machine learning algorithms and video surveillance applications. The task of person re-identification is to determine which person in a gallery has the same identity to a probe image. This task basically assumes that the subject of the probe image belongs to the gallery, that is, the gallery contains this person. However, in practical applications such as searching a suspect in a video, this assumption is usually not true. In this paper, we consider the open-set person re-identification problem, which includes two sub-tasks, detection and identification. The detection sub-task is to determine the presence of the probe subject in the gallery, and the identification sub-task is to determine which person in the gallery has the same identity as the accepted probe. We present a database collected from a video surveillance setting of 6 cameras, with 200 persons and 7,413 images segmented. Based on this database, we develop a benchmark protocol for evaluating the performance under the open-set person re-identification scenario. Several popular metric learning algorithms for person re-identification have been evaluated as baselines. From the baseline performance, we observe that the open-set person re-identification problem is still largely unresolved, thus further attention and effort is needed.

cs.CV↗

arXiv2013

Vector cross product in n-dimensional vector space

The definition of vector cross product (VCP) introduced by Eckmann only exists in thethree- and the seven- dimensional vector space. In this paper, according to the orthogonal completeness, magnitude of basis vector cross product and all kinds of combinations of basis vector $\hat{e}_i$, the generalized definition of VCP in the odd n-dimensional vector space is given by introducing a cross term $X_{AB}$. In addition, the definition is validated by reducing the generalization definition to the fundamental three- and seven-dimensional vector space.

math-ph↗

arXiv2013

Fast Matching by 2 Lines of Code for Large Scale Face Recognition Systems

In this paper, we propose a method to apply the popular cascade classifier into face recognition to improve the computational efficiency while keeping high recognition rate. In large scale face recognition systems, because the probability of feature templates coming from different subjects is very high, most of the matching pairs will be rejected by the early stages of the cascade. Therefore, the cascade can improve the matching speed significantly. On the other hand, using the nested structure of the cascade, we could drop some stages at the end of feature to reduce the memory and bandwidth usage in some resources intensive system while not sacrificing the performance too much. The cascade is learned by two steps. Firstly, some kind of prepared features are grouped into several nested stages. And then, the threshold of each stage is learned to achieve user defined verification rate (VR). In the paper, we take a landmark based Gabor+LDA face recognition system as baseline to illustrate the process and advantages of the proposed method. However, the use of this method is very generic and not limited in face recognition, which can be easily generalized to other biometrics as a post-processing module. Experiments on the FERET database show the good performance of our baseline and an experiment on a self-collected large scale database illustrates that the cascade can improve the matching speed significantly.

cs.CV↗