Searcharxiv⌕ Search

arXiv subjects

Yan Yan

Publications and source records attributed to Yan Yan.

At least 271 records · Page 15Linked to original sources
arXiv2018

A Fast Face Detection Method via Convolutional Neural Network

Current face or object detection methods via convolutional neural network (such as OverFeat, R-CNN and DenseNet) explicitly extract multi-scale features based on an image pyramid. However, such a strategy increases the computational burden for face detection. In this paper, we propose a fast face detection method based on discriminative complete features (DCFs) extracted by an elaborately designed convolutional neural network, where face detection is directly performed on the complete feature maps. DCFs have shown the ability of scale invariance, which is beneficial for face detection with high speed and promising performance. Therefore, extracting multi-scale features on an image pyramid employed in the conventional methods is not required in the proposed method, which can greatly improve its efficiency for face detection. Experimental results on several popular face detection datasets show the efficiency and the effectiveness of the proposed method for face detection.

cs.CV↗
arXiv2018

Style Aggregated Network for Facial Landmark Detection

Recent advances in facial landmark detection achieve success by learning discriminative features from rich deformation of face shapes and poses. Besides the variance of faces themselves, the intrinsic variance of image styles, e.g., grayscale vs. color images, light vs. dark, intense vs. dull, and so on, has constantly been overlooked. This issue becomes inevitable as increasing web images are collected from various sources for training neural networks. In this work, we propose a style-aggregated approach to deal with the large intrinsic variance of image styles for facial landmark detection. Our method transforms original face images to style-aggregated images by a generative adversarial module. The proposed scheme uses the style-aggregated image to maintain face images that are more robust to environmental changes. Then the original face images accompanying with style-aggregated ones play a duet to train a landmark detector which is complementary to each other. In this way, for each face, our method takes two images as input, i.e., one in its original style and the other in the aggregated style. In experiments, we observe that the large variance of image styles would degenerate the performance of facial landmark detectors. Moreover, we show the robustness of our method to the large variance of image styles by comparing to a variant of our approach, in which the generative adversarial module is removed, and no style-aggregated images are used. Our approach is demonstrated to perform well when compared with state-of-the-art algorithms on benchmark datasets AFLW and 300-W. Code is publicly available on GitHub: https://github.com/D-X-Y/SAN

cs.CV↗
arXiv2018

Searching for Representative Modes on Hypergraphs for Robust Geometric Model Fitting

In this paper, we propose a simple and effective {geometric} model fitting method to fit and segment multi-structure data even in the presence of severe outliers. We cast the task of geometric model fitting as a representative mode-seeking problem on hypergraphs. Specifically, a hypergraph is firstly constructed, where the vertices represent model hypotheses and the hyperedges denote data points. The hypergraph involves higher-order similarities (instead of pairwise similarities used on a simple graph), and it can characterize complex relationships between model hypotheses and data points. {In addition, we develop a hypergraph reduction technique to remove "insignificant" vertices while retaining as many "significant" vertices as possible in the hypergraph}. Based on the {simplified hypergraph, we then propose a novel mode-seeking algorithm to search for representative modes within reasonable time. Finally, the} proposed mode-seeking algorithm detects modes according to two key elements, i.e., the weighting scores of vertices and the similarity analysis between vertices. Overall, the proposed fitting method is able to efficiently and effectively estimate the number and the parameters of model instances in the data simultaneously. Experimental results demonstrate that the proposed method achieves significant superiority over {several} state-of-the-art model fitting methods on both synthetic data and real images.

cs.CV↗
arXiv2018

Enhanced Linear-array Photoacoustic Beamforming using Modified Coherence Factor

Photoacoustic imaging (PAI) is a promising medical imaging modality providing the spatial resolution of ultrasound (US) imaging and the contrast of pure optical imaging. For linear-array PAI, a beamformer has to be used as the reconstruction algorithm. Delay-and-sum (DAS) is the most prevalent beamforming algorithm in PAI. However, using DAS beamformer leads to low resolution images along with significant effects of the off-axis signals. Coherence factor (CF) is a weighting method in which each pixel of the reconstructed image is weighted, based on the spatial spectrum of the aperture, to improve the contrast. In this paper, it has been shown that the numerator of the formula of CF contains a DAS algebra, and it was proposed to use the delay-multiply-and-sum (DMAS) beamformer instead of the available DAS on the numerator. The proposed weighting technique, modified CF (MCF), has been evaluated numerically and experimentally compared to CF, and it was shown that MCF leads to lower sidelobes and better detectable targets. The quantitative results of the experiment (using wire targets) show that MCF leads to for about 45% and 40% improvement, in comparison with CF, in the terms of signal-to-noise ratio and full-width-half-maximum, respectively.

physics.med-ph↗
arXiv2018

Automatic Image Cropping for Visual Aesthetic Enhancement Using Deep Neural Networks and Cascaded Regression

Despite recent progress, computational visual aesthetic is still challenging. Image cropping, which refers to the removal of unwanted scene areas, is an important step to improve the aesthetic quality of an image. However, it is challenging to evaluate whether cropping leads to aesthetically pleasing results because the assessment is typically subjective. In this paper, we propose a novel cascaded cropping regression (CCR) method to perform image cropping by learning the knowledge from professional photographers. The proposed CCR method improves the convergence speed of the cascaded method, which directly uses random-ferns regressors. In addition, a two-step learning strategy is proposed and used in the CCR method to address the problem of lacking labelled cropping data. Specifically, a deep convolutional neural network (CNN) classifier is first trained on large-scale visual aesthetic datasets. The deep CNN model is then designed to extract features from several image cropping datasets, upon which the cropping bounding boxes are predicted by the proposed CCR method. Experimental results on public image cropping datasets demonstrate that the proposed method significantly outperforms several state-of-the-art image cropping methods.

cs.CV↗
arXiv2017

Revisiting Graph Construction for Fast Image Segmentation

In this paper, we propose a simple but effective method for fast image segmentation. We re-examine the locality-preserving character of spectral clustering by constructing a graph over image regions with both global and local connections. Our novel approach to build graph connections relies on two key observations: 1) local region pairs that co-occur frequently will have a high probability to reside on a common object; 2) spatially distant regions in a common object often exhibit similar visual saliency, which implies their neighborship in a manifold. We present a novel energy function to efficiently conduct graph partitioning. Based on multiple high quality partitions, we show that the generated eigenvector histogram based representation can automatically drive effective unary potentials for a hierarchical random field model to produce multi-class segmentation. Sufficient experiments, on the BSDS500 benchmark, large-scale PASCAL VOC and COCO datasets, demonstrate the competitive segmentation accuracy and significantly improved efficiency of our proposed method compared with other state of the arts.

cs.CV↗
arXiv2017

From Query-By-Keyword to Query-By-Example: LinkedIn Talent Search Approach

One key challenge in talent search is to translate complex criteria of a hiring position into a search query, while it is relatively easy for a searcher to list examples of suitable candidates for a given position. To improve search efficiency, we propose the next generation of talent search at LinkedIn, also referred to as Search By Ideal Candidates. In this system, a searcher provides one or several ideal candidates as the input to hire for a given position. The system then generates a query based on the ideal candidates and uses it to retrieve and rank results. Shifting from the traditional Query-By-Keyword to this new Query-By-Example system poses a number of challenges: How to generate a query that best describes the candidates? When moving to a completely different paradigm, how does one leverage previous product logs to learn ranking models and/or evaluate the new system with no existing usage logs? Finally, given the different nature between the two search paradigms, the ranking features typically used for Query-By-Keyword systems might not be optimal for Query-By-Example. This paper describes our approach to solving these challenges. We present experimental results confirming the effectiveness of the proposed solution, particularly on query building and search ranking tasks. As of writing this paper, the new system has been available to all LinkedIn members.

cs.IR↗
arXiv2017

Optimizing Gross Merchandise Volume via DNN-MAB Dynamic Ranking Paradigm

With the transition from people's traditional `brick-and-mortar' shopping to online mobile shopping patterns in web 2.0 $\mathit{era}$, the recommender system plays a critical role in E-Commerce and E-Retails. This is especially true when designing this system for more than $\mathbf{236~million}$ daily active users. Ranking strategy, the key module of the recommender system, needs to be precise, accurate, and responsive for estimating customers' intents. We propose a dynamic ranking paradigm, named as DNN-MAB, that is composed of a pairwise deep neural network (DNN) $\mathit{pre}$-ranker connecting a revised multi-armed bandit (MAB) dynamic $\mathit{post}$-ranker. By taking into account of explicit and implicit user feedbacks such as impressions, clicks, conversions, etc. DNN-MAB is able to adjust DNN $\mathit{pre}$-ranking scores to assist customers locating items they are interested in most so that they can converge quickly and frequently. To the best of our knowledge, frameworks like DNN-MAB have not been discussed in the previous literature to either E-Commerce or machine learning audiences. In practice, DNN-MAB has been deployed to production and it easily outperforms against other state-of-the-art models by significantly lifting the gross merchandise volume (GMV) which is the objective metrics at JD.

cs.AI↗
arXiv2017

Orthogonally Polarized Kerr Frequency Combs

Kerr optical frequency combs with multi-gigahertz spacing have previously been demonstrated in chip-scale microresonators, with potential applications in coherent communication, spectroscopy, arbitrary waveform generation, and radio frequency photonic oscillators. In general, the harmonics of a frequency comb are identically polarized in a single microresonator. In this work, we report that one comb in one polarization is generated by an orthogonally polarized soliton comb and two low-noise, orthogonally polarized combs interact with each other and exist simultaneously in a single microresonator. The second comb generation is attributed to the strong cross-phase modulation with the orthogonally polarized soliton comb and the high peak power of the intracavity soliton pulse. Experimental results show that a second frequency comb is excited even when a continuous wave light as a "seed"-with power as low as 0.1 mW-is input, while its own power level is below the threshold of comb generation. Moreover, the second comb has a concave envelope, which is different from the sech2 envelope of the soliton comb. This is due to the frequency mismatch between the harmonics and the resonant frequency. We also find that the repetition rates of these two combs coincide, although two orthogonal resonant modes are characterized by different free spectral ranges.

physics.optics↗
arXiv2017

Object Discovery via Cohesion Measurement

Color and intensity are two important components in an image. Usually, groups of image pixels, which are similar in color or intensity, are an informative representation for an object. They are therefore particularly suitable for computer vision tasks, such as saliency detection and object proposal generation. However, image pixels, which share a similar real-world color, may be quite different since colors are often distorted by intensity. In this paper, we reinvestigate the affinity matrices originally used in image segmentation methods based on spectral clustering. A new affinity matrix, which is robust to color distortions, is formulated for object discovery. Moreover, a Cohesion Measurement (CM) for object regions is also derived based on the formulated affinity matrix. Based on the new Cohesion Measurement, a novel object discovery method is proposed to discover objects latent in an image by utilizing the eigenvectors of the affinity matrix. Then we apply the proposed method to both saliency detection and object proposal generation. Experimental results on several evaluation benchmarks demonstrate that the proposed CM based method has achieved promising performance for these two tasks.

cs.CV↗
arXiv2017

Learn to Model Motion from Blurry Footages

It is difficult to recover the motion field from a real-world footage given a mixture of camera shake and other photometric effects. In this paper we propose a hybrid framework by interleaving a Convolutional Neural Network (CNN) and a traditional optical flow energy. We first conduct a CNN architecture using a novel learnable directional filtering layer. Such layer encodes the angle and distance similarity matrix between blur and camera motion, which is able to enhance the blur features of the camera-shake footages. The proposed CNNs are then integrated into an iterative optical flow framework, which enable the capability of modelling and solving both the blind deconvolution and the optical flow estimation problems simultaneously. Our framework is trained end-to-end on a synthetic dataset and yields competitive precision and performance against the state-of-the-art approaches.

cs.CV↗
arXiv2017

Person Re-Identification via Recurrent Feature Aggregation

We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches. This is in contrast to previous person re-id works, which rely on either single frame based person to person patch matching, or graph based sequence to sequence matching. We show that a progressive/sequential fusion framework based on long short term memory (LSTM) network aggregates the frame-wise human region representation at each time stamp and yields a sequence level human feature representation. Since LSTM nodes can remember and propagate previously accumulated good features and forget newly input inferior ones, even with simple hand-crafted features, the proposed recurrent feature aggregation network (RFA-Net) is effective in generating highly discriminative sequence level human representations. Extensive experimental results on two person re-identification benchmarks demonstrate that the proposed method performs favorably against state-of-the-art person re-identification methods.

cs.CV↗
arXiv2016

Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than $O(1/ε)$

In this paper, we develop a novel {\bf ho}moto{\bf p}y {\bf s}moothing (HOPS) algorithm for solving a family of non-smooth problems that is composed of a non-smooth term with an explicit max-structure and a smooth term or a simple non-smooth term whose proximal mapping is easy to compute. The best known iteration complexity for solving such non-smooth optimization problems is $O(1/ε)$ without any assumption on the strong convexity. In this work, we will show that the proposed HOPS achieved a lower iteration complexity of $\widetilde O(1/ε^{1-θ})$\footnote{$\widetilde O()$ suppresses a logarithmic factor.} with $θ\in(0,1]$ capturing the local sharpness of the objective function around the optimal solutions. To the best of our knowledge, this is the lowest iteration complexity achieved so far for the considered non-smooth optimization problems without strong convexity assumption. The HOPS algorithm employs Nesterov's smoothing technique and Nesterov's accelerated gradient method and runs in stages, which gradually decreases the smoothing parameter in a stage-wise manner until it yields a sufficiently good approximation of the original function. We show that HOPS enjoys a linear convergence for many well-known non-smooth problems (e.g., empirical risk minimization with a piece-wise linear loss function and $\ell_1$ norm regularizer, finding a point in a polyhedron, cone programming, etc). Experimental results verify the effectiveness of HOPS in comparison with Nesterov's smoothing algorithm and the primal-dual style of first-order methods.

math.OC↗
arXiv2016

Long-range Correlation and Market Segmentation in Bond Market

This paper looks into the analysis of the long-range auto-correlations and cross-correlations in bond market. Based on Detrended Moving Average (DMA) method, empirical results present a clear evidence of long-range persistence that exists in one year scale. The degree of long-range correlation related to maturities has an upward tendency with a peak in short term. These findings confirm the expectations of fractal market hypothesis (FMH). Furthermore, we have developed a method based on a complex network to study the long-range cross-correlation structure and apply it to our data, and found a clear pattern of market segmentation in the long run. We also detected the nature of long-range correlation in the sub-period 2007 to 2012 and 2011 to 2016. The result from our research shows that long-range auto-correlations are decreasing in the recent years while long-range cross-correlations are strengthening.

q-fin.ST↗
arXiv2016

Superpixel-based Two-view Deterministic Fitting for Multiple-structure Data

This paper proposes a two-view deterministic geometric model fitting method, termed Superpixel-based Deterministic Fitting (SDF), for multiple-structure data. SDF starts from superpixel segmentation, which effectively captures prior information of feature appearances. The feature appearances are beneficial to reduce the computational complexity for deterministic fitting methods. SDF also includes two original elements, i.e., a deterministic sampling algorithm and a novel model selection algorithm. The two algorithms are tightly coupled to boost the performance of SDF in both speed and accuracy. Specifically, the proposed sampling algorithm leverages the grouping cues of superpixels to generate reliable and consistent hypotheses. The proposed model selection algorithm further makes use of desirable properties of the generated hypotheses, to improve the conventional fit-and-remove framework for more efficient and effective performance. The key characteristic of SDF is that it can efficiently and deterministically estimate the parameters of model instances in multi-structure data. Experimental results demonstrate that the proposed SDF shows superiority over several state-of-the-art fitting methods for real images with single-structure and multiple-structure data.

cs.CV↗
arXiv2016

Diagnosing the Source Region of a Solar Burst on 26 September 2011 by Microwave Type III Pairs

This work reports a peculiar and interesting train of microwave type III pair bursts in the impulsive rising phase of a solar flare on 2011 September 26. The observations include radio spectrometers at frequency of 0.80 - 2.00 GHz, hard X-ray (RHESSI and FERMI), EUV images of SWAP/PROBA-2 and magnetogram of HMI/SDO. By using a recently developed method (Tan et al. 2016a), we diagnosed the plasma density, temperature, plasma beta, magnetic field near the source region, the energy of energetic electrons and the distance between the acceleration region and the emission start sites of type III bursts. From the diagnostics, we find that: (1) The plasma density, temperature, magnetic field, and the distance between the acceleration region and the emission start sites almost have no obvious variations during the period of type III pair trains, while the energy of electrons has an obvious peak value which is consistent to the hard X-ray emission. (2) The plasma beta is much higher than an unity showing a highly dynamic process near the emission start site of type III bursts. (3) Although the reversed-slope type III branches drift slower at one order of magnitude than that of the normal type III branches, the related downgoing and upgoing electrons still could have same order of magnitude of energy. These facts indicate that both of the upgoing and downgoing electrons are possibly accelerated by similar mechanism and in a small source region. This diagnostics can help us to understand the microphysics in the source region of solar bursts.

astro-ph.SR↗
arXiv2016

Spatial Phase and Amplitude Structuring of Beams Using a Combination of Multiple Orthogonal Spatial Functions with Complex Coefficients

Analogous to time signals that can be composed of multiple frequency functions, we use uniquely structured orthogonal spatial modes to create different beam shapes. We tailor the spatial structure by judiciously choosing a weighted combination of multiple modal states within an orthogonal basis set, and we can tunably create beam phase and intensity "shapes" that are not otherwise readily achievable. As an example shape, we use a series of orbital-angular-momentum (OAM) functions with adjustable complex weights to create a reconfigurable spatial region of higher localized power as compared to traditional beam combining. We simulate a structured beam created by coherently combining several orthogonal OAM beams with different complex weights, and we achieve a >10X localized power density enhancement with 19 beams. Additionally, we can create unique shapes by passing a single beam through a specially designed phase and intensity mask that contains the combination of multiple OAM functions each with complex weights. Using this approach, we experimentally demonstrate a ~2.5X localized power density increase when utilizing 9 functions.

physics.optics↗