arXiv subjects

Jian Yao

Publications and source records attributed to Jian Yao.

52 records · Page 3Linked to original sources

arXiv2020

Frequency Ratio Measurements with 18-digit Accuracy Using a Network of Optical Clocks

Atomic clocks occupy a unique position in measurement science, exhibiting higher accuracy than any other measurement standard and underpinning six out of seven base units in the SI system. By exploiting higher resonance frequencies, optical atomic clocks now achieve greater stability and lower frequency uncertainty than existing primary standards. Here, we report frequency ratios of the $^{27}$Al$^+$, $^{171}$Yb and $^{87}$Sr optical clocks in Boulder, Colorado, measured across an optical network spanned by both fiber and free-space links. These ratios have been evaluated with measurement uncertainties between $6\times10^{-18}$ and $8\times10^{-18}$, making them the most accurate reported measurements of frequency ratios to date. This represents a critical step towards redefinition of the SI second and future applications such as relativistic geodesy and tests of fundamental physics.

physics.atom-ph↗

arXiv2020

Vanishing Point Guided Natural Image Stitching

Recently, works on improving the naturalness of stitching images gain more and more extensive attention. Previous methods suffer the failures of severe projective distortion and unnatural rotation, especially when the number of involved images is large or images cover a very wide field of view. In this paper, we propose a novel natural image stitching method, which takes into account the guidance of vanishing points to tackle the mentioned failures. Inspired by a vital observation that mutually orthogonal vanishing points in Manhattan world can provide really useful orientation clues, we design a scheme to effectively estimate prior of image similarity. Given such estimated prior as global similarity constraints, we feed it into a popular mesh deformation framework to achieve impressive natural stitching performances. Compared with other existing methods, including APAP, SPHP, AANAP, and GSP, our method achieves state-of-the-art performance in both quantitative and qualitative experiments on natural image stitching.

cs.CV↗

arXiv2020

GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modeling

Unsupervised image-to-image translation (UNIT) aims at learning a mapping between several visual domains by using unpaired training images. Recent studies have shown remarkable success for multiple domains but they suffer from two main limitations: they are either built from several two-domain mappings that are required to be learned independently, or they generate low-diversity results, a problem known as mode collapse. To overcome these limitations, we propose a method named GMM-UNIT, which is based on a content-attribute disentangled representation where the attribute space is fitted with a GMM. Each GMM component represents a domain, and this simple assumption has two prominent advantages. First, it can be easily extended to most multi-domain and multi-modal image-to-image translation tasks. Second, the continuous domain encoding allows for interpolation between domains and for extrapolation to unseen domains and translations. Additionally, we show how GMM-UNIT can be constrained down to different methods in the literature, meaning that GMM-UNIT is a unifying framework for unsupervised image-to-image translation.

cs.CV↗

arXiv2019

Coarse-to-fine Optimization for Speech Enhancement

In this paper, we propose the coarse-to-fine optimization for the task of speech enhancement. Cosine similarity loss [1] has proven to be an effective metric to measure similarity of speech signals. However, due to the large variance of the enhanced speech with even the same cosine similarity loss in high dimensional space, a deep neural network learnt with this loss might not be able to predict enhanced speech with good quality. Our coarse-to-fine strategy optimizes the cosine similarity loss for different granularities so that more constraints are added to the prediction from high dimension to relatively low dimension. In this way, the enhanced speech will better resemble the clean speech. Experimental results show the effectiveness of our proposed coarse-to-fine optimization in both discriminative models and generative models. Moreover, we apply the coarse-to-fine strategy to the adversarial loss in generative adversarial network (GAN) and propose dynamic perceptual loss, which dynamically computes the adversarial loss from coarse resolution to fine resolution. Dynamic perceptual loss further improves the accuracy and achieves state-of-the-art results compared with other generative models.

cs.SD↗

arXiv2019

Demonstration of a time scale based on a stable optical carrier

We demonstrate a time scale based on a phase stable optical carrier that accumulates an estimated time error of $48\pm94$ ps over 34 days of operation. This all-optical time scale is formed with a cryogenic silicon cavity exhibiting improved long-term stability and an accurate $^{87}$Sr lattice clock. We show that this new time scale architecture outperforms existing microwave time scales, even when they are steered to optical frequency standards. Our analysis indicates that this time scale is capable of reaching a stability below $1\times10^{-17}$ after a few months of averaging, making timekeeping at the $10^{-18}$ level a realistic prospect.

physics.atom-ph↗

arXiv2019

Optical-Clock-Based Time Scale

A time scale is a procedure for accurately and continuously marking the passage of time. It is exemplified by Coordinated Universal Time (UTC), and provides the backbone for critical navigation tools such as the Global Positioning System (GPS). Present time scales employ microwave atomic clocks, whose attributes can be combined and averaged in a manner such that the composite is more stable, accurate, and reliable than the output of any individual clock. Over the past decade, clocks operating at optical frequencies have been introduced which are orders of magnitude more stable than any microwave clock. However, in spite of their great potential, these optical clocks cannot be operated continuously, which makes their use in a time scale problematic. In this paper, we report the development of a hybrid microwave-optical time scale, which only requires the optical clock to run intermittently while relying upon the ensemble of microwave clocks to serve as the flywheel oscillator. The benefit of using clock ensemble as the flywheel oscillator, instead of a single clock, can be understood by the Dick-effect limit. This time scale demonstrates for the first time sub-nanosecond accuracy for a few months, attaining a fractional frequency uncertainty of 1.45*10-16 at 30 days and reaching the 10-17 decade at 50 days, with respect to UTC. This time scale significantly improves the accuracy in timekeeping and could change the existing time-scale architectures.

physics.app-ph↗

arXiv2018

Testing the ABS method with the simulated Planck temperature maps

In this study, we apply the Analytical method of Blind Separation (ABS) of the cosmic microwave background (CMB) from foregrounds to estimate the CMB temperature power spectrum from multi-frequency microwave maps. We test the robustness of the ABS estimator and assess the accuracy of the power spectrum recovery by using realistic simulations based on the seven-frequency Planck data, including various frequency-dependent and spatially-varying foreground components (synchrotron, free-free, thermal dust and anomalous microwave emission), as well as an uncorrelated Gaussian-distributed instrumental noise. Considering no prior information about the foregrounds, the ABS estimator can analytically recover the CMB power spectrum over almost all scales with less than $0.5\%$ error for maps where the Galactic plane region ($|b|<10^{\circ}$) is masked out. To further test the flexibility and effectiveness of the ABS approach in a variety of situations, we apply the ABS to the simulated Planck maps in three cases: (1) without any mask, (2) imposing a two-times-stronger synchrotron emission and (3) including only the Galactic plane region ($|b|<10^{\circ}$) in the analysis. In such extreme cases, the ABS approach can still provide an unbiased estimate of band powers at the level of 1 $μ\rm{K}^2$ on average over all $\ell$ range, and the recovered powers are consistent with the input values within 1-$σ$ for most $\ell$ bins.

astro-ph.CO↗

arXiv2018

Multiple Combined Constraints for Image Stitching

Several approaches to image stitching use different constraints to estimate the motion model between image pairs. These constraints can be roughly divided into two categories: geometric constraints and photometric constraints. In this paper, geometric and photometric constraints are combined to improve the alignment quality, which is based on the observation that these two kinds of constraints are complementary. On the one hand, geometric constraints (e.g., point and line correspondences) are usually spatially biased and are insufficient in some extreme scenes, while photometric constraints are always evenly and densely distributed. On the other hand, photometric constraints are sensitive to displacements and are not suitable for images with large parallaxes, while geometric constraints are usually imposed by feature matching and are more robust to handle parallaxes. The proposed method therefore combines them together in an efficient mesh-based image warping framework. It achieves better alignment quality than methods only with geometric constraints, and can handle larger parallax than photometric-constraint-based method. Experimental results on various images illustrate that the proposed method outperforms representative state-of-the-art image stitching methods reported in the literature.

cs.CV↗

arXiv2018

Generalized Content-Preserving Warps for Image Stitching

Local misalignment caused by global homography is a common issue in image stitching task. Content-Preserving Warping (CPW) is a typical method to deal with this issue, in which geometric and photometric constraints are imposed to guide the warping process. One of its essential condition however, is colour consistency, and an elusive goal in real world applications. In this paper, we propose a Generalized Content-Preserving Warping (GCPW) method to alleviate this problem. GCPW extends the original CPW by applying a colour model that expresses the colour transformation between images locally, thus meeting the photometric constraint requirements for effective image stitching. We combine the photometric and geometric constraints and jointly estimate the colour transformation and the warped mesh vertexes, simultaneously. We align images locally with an optimal grid mesh generated by our GCPW method. Experiments on both synthetic and real images demonstrate that our new method is robust to colour variations, outperforming other state-of-the-art CPW-based image stitching methods.

cs.CV↗

arXiv2018

Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present

Recently, caption generation with an encoder-decoder framework has been extensively studied and applied in different domains, such as image captioning, code captioning, and so on. In this paper, we propose a novel architecture, namely Auto-Reconstructor Network (ARNet), which, coupling with the conventional encoder-decoder framework, works in an end-to-end fashion to generate captions. ARNet aims at reconstructing the previous hidden state with the present one, besides behaving as the input-dependent transition operator. Therefore, ARNet encourages the current hidden state to embed more information from the previous one, which can help regularize the transition dynamics of recurrent neural networks (RNNs). Extensive experimental results show that our proposed ARNet boosts the performance over the existing encoder-decoder models on both image captioning and source code captioning tasks. Additionally, ARNet remarkably reduces the discrepancy between training and inference processes for caption generation. Furthermore, the performance on permuted sequential MNIST demonstrates that ARNet can effectively regularize RNN, especially on modeling long-term dependencies. Our code is available at: https://github.com/chenxinpeng/ARNet

cs.CV↗

arXiv2018

Fine-grained Video Attractiveness Prediction Using Multimodal Deep Learning on a Large Real-world Dataset

Nowadays, billions of videos are online ready to be viewed and shared. Among an enormous volume of videos, some popular ones are widely viewed by online users while the majority attract little attention. Furthermore, within each video, different segments may attract significantly different numbers of views. This phenomenon leads to a challenging yet important problem, namely fine-grained video attractiveness prediction. However, one major obstacle for such a challenging problem is that no suitable benchmark dataset currently exists. To this end, we construct the first fine-grained video attractiveness dataset, which is collected from one of the most popular video websites in the world. In total, the constructed FVAD consists of 1,019 drama episodes with 780.6 hours covering different categories and a wide variety of video contents. Apart from the large amount of videos, hundreds of millions of user behaviors during watching videos are also included, such as "view counts", "fast-forward", "fast-rewind", and so on, where "view counts" reflects the video attractiveness while other engagements capture the interactions between the viewers and videos. First, we demonstrate that video attractiveness and different engagements present different relationships. Second, FVAD provides us an opportunity to study the fine-grained video attractiveness prediction problem. We design different sequential models to perform video attractiveness prediction by relying solely on video contents. The sequential models exploit the multimodal relationships between visual and audio components of the video contents at different levels. Experimental results demonstrate the effectiveness of our proposed sequential models with different visual and audio representations, the necessity of incorporating the two modalities, and the complementary behaviors of the sequential prediction models at different levels.

cs.CV↗

arXiv2017

Unveiling soliton booting dynamics in ultrafast fiber lasers

Ultrafast fiber lasers play important roles in many aspects of our life for their various applications in fields ranging from fundamental sciences to industrial purposes. Passive mode-locking technique is a key step to realize the ultrafast soliton fiber lasers. However, the booting dynamics of the soliton fiber lasers have not yet been well understood. Herein, we reveal the soliton buildup dynamics of ultrafast fiber lasers operating both in anomalous and net-normal dispersion regimes. Based on the advanced experimental methodologies of spatio-temporal reconstruction and dispersive Fourier transform (DFT), the soliton booting dynamics are analyzed in the time and spectral domains. It was found that the booting dynamics of conventional and dissipative solitons operating in the anomalous and net-normal dispersion regimes, respectively, are different from each other due to the different pulse shaping mechanisms. In particular, the spectral interference pattern with strong relaxation oscillation behavior was observed near the mode-locking transition for conventional soliton, while no relaxation oscillation of spectral pattern was obtained for dissipative soliton. We firstly revealed that the spectral pattern distributions are induced by the transient structured soliton formation during the pulse shaping from the noise background. The experimental results were verified by the theoretical simulations. The obtained results would provide a general guideline for understanding the soliton booting dynamics in ultrafast fiber lasers, and will prove to be fruitful to the various communities interested in solitons and fiber lasers.

physics.optics↗

arXiv2017

Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network

We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and multi-level features; and (2) applying an effective top-down refined approach in the networks. TD-CEDN performs the pixel-wise prediction by means of leveraging features at all layers of the net. Unlike skip connections and previous encoder-decoder methods, we first learn a coarse feature map after the encoder stage in a feedforward pass, and then refine this feature map in a top-down strategy during the decoder stage utilizing features at successively lower layers. Therefore, the deconvolutional process is conducted stepwise, which is guided by Deeply-Supervision Net providing the integrated direct supervision. The above proposed technologies lead to a more precise and clearer prediction. Our proposed algorithm achieved the state-of-the-art on the BSDS500 dataset (ODS F-score of 0.788), the PASCAL VOC2012 dataset (ODS F-score of 0.588), and and the NYU Depth dataset (ODS F-score of 0.735).

cs.CV↗

arXiv2017

Incorporating an Optical Clock into a Time Scale

This paper discusses how to build a time scale with an intermittently-operated optical clock. In particular, it gives suggestions on how long and how often to run an optical clock. It also explores the benefits of having an optical clock in a time scale, by comparing with the current UTC(NIST) performance and the time scale with a continuously-operated Cs fountain.

physics.app-ph↗

arXiv2016

Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network

We introduce a new top-down pipeline for scene text detection. We propose a novel Cascaded Convolutional Text Network (CCTN) that joints two customized convolutional networks for coarse-to-fine text localization. The CCTN fast detects text regions roughly from a low-resolution image, and then accurately localizes text lines from each enlarged region. We cast previous character based detection into direct text region estimation, avoiding multiple bottom- up post-processing steps. It exhibits surprising robustness and discriminative power by considering whole text region as detection object which provides strong semantic information. We customize convolutional network by develop- ing rectangle convolutions and multiple in-network fusions. This enables it to handle multi-shape and multi-scale text efficiently. Furthermore, the CCTN is computationally efficient by sharing convolutional computations, and high-level property allows it to be invariant to various languages and multiple orientations. It achieves 0.84 and 0.86 F-measures on the ICDAR 2011 and ICDAR 2013, delivering substantial improvements over state-of-the-art results [23, 1].

cs.CV↗

arXiv2016

Text-Attentional Convolutional Neural Networks for Scene Text Detection

Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images. They extract a high-level feature computed globally from a whole image component (patch), where the cluttered background information may dominate true text features in the deep representation. This leads to less discriminative power and poorer robustness. In this work, we present a new system for scene text detection by proposing a novel Text-Attentional Convolutional Neural Network (Text-CNN) that particularly focuses on extracting text-related regions and features from the image components. We develop a new learning mechanism to train the Text-CNN with multi-level and rich supervised information, including text region mask, character label, and binary text/nontext information. The rich supervision information enables the Text-CNN with a strong capability for discriminating ambiguous texts, and also increases its robustness against complicated background components. The training process is formulated as a multi-task learning problem, where low-level supervised information greatly facilitates main task of text/non-text classification. In addition, a powerful low-level detector called Contrast- Enhancement Maximally Stable Extremal Regions (CE-MSERs) is developed, which extends the widely-used MSERs by enhancing intensity contrast between text patterns and background. This allows it to detect highly challenging text patterns, resulting in a higher recall. Our approach achieved promising results on the ICDAR 2013 dataset, with a F-measure of 0.82, improving the state-of-the-art results substantially.

cs.CV↗