arXiv subjects

Sheng Li

Publications and source records attributed to Sheng Li.

At least 271 records · Page 15Linked to original sources

arXiv2019

Robust Unsupervised Flexible Auto-weighted Local-Coordinate Concept Factorization for Image Clustering

We investigate the high-dimensional data clustering problem by proposing a novel and unsupervised representation learning model called Robust Flexible Auto-weighted Local-coordinate Concept Factorization (RFA-LCF). RFA-LCF integrates the robust flexible CF, robust sparse local-coordinate coding and the adaptive reconstruction weighting learning into a unified model. The adaptive weighting is driven by including the joint manifold preserving constraints on the recovered clean data, basis concepts and new representation. Specifically, our RFA-LCF uses a L2,1-norm based flexible residue to encode the mismatch between clean data and its reconstruction, and also applies the robust adaptive sparse local-coordinate coding to represent the data using a few nearby basis concepts, which can make the factorization more accurate and robust to noise. The robust flexible factorization is also performed in the recovered clean data space for enhancing representations. RFA-LCF also considers preserving the local manifold structures of clean data space, basis concept space and the new coordinate space jointly in an adaptive manner way. Extensive comparisons show that RFA-LCF can deliver enhanced clustering results.

cs.CV↗

arXiv2019

Scalable Block-Diagonal Locality-Constrained Projective Dictionary Learning

We propose a novel structured discriminative block-diagonal dictionary learning method, referred to as scalable Locality-Constrained Projective Dictionary Learning (LC-PDL), for efficient representation and classification. To improve the scalability by saving both training and testing time, our LC-PDL aims at learning a structured discriminative dictionary and a block-diagonal representation without using costly l0/l1-norm. Besides, it avoids extra time-consuming sparse reconstruction process with the well-trained dictionary for new sample as many existing models. More importantly, LC-PDL avoids using the complementary data matrix to learn the sub-dictionary over each class. To enhance the performance, we incorporate a locality constraint of atoms into the DL procedures to keep local information and obtain the codes of samples over each class separately. A block-diagonal discriminative approximation term is also derived to learn a discriminative projection to bridge data with their codes by extracting the special block-diagonal features from data, which can ensure the approximate coefficients to associate with its label information clearly. Then, a robust multiclass classifier is trained over extracted block-diagonal codes for accurate label predictions. Experimental results verify the effectiveness of our algorithm.

cs.CV↗

arXiv2019

SADIH: Semantic-Aware DIscrete Hashing

Due to its low storage cost and fast query speed, hashing has been recognized to accomplish similarity search in large-scale multimedia retrieval applications. Particularly supervised hashing has recently received considerable research attention by leveraging the label information to preserve the pairwise similarities of data points in the Hamming space. However, there still remain two crucial bottlenecks: 1) the learning process of the full pairwise similarity preservation is computationally unaffordable and unscalable to deal with big data; 2) the available category information of data are not well-explored to learn discriminative hash functions. To overcome these challenges, we propose a unified Semantic-Aware DIscrete Hashing (SADIH) framework, which aims to directly embed the transformed semantic information into the asymmetric similarity approximation and discriminative hashing function learning. Specifically, a semantic-aware latent embedding is introduced to asymmetrically preserve the full pairwise similarities while skillfully handle the cumbersome n times n pairwise similarity matrix. Meanwhile, a semantic-aware autoencoder is developed to jointly preserve the data structures in the discriminative latent semantic space and perform data reconstruction. Moreover, an efficient alternating optimization algorithm is proposed to solve the resulting discrete optimization problem. Extensive experimental results on multiple large-scale datasets demonstrate that our SADIH can clearly outperform the state-of-the-art baselines with the additional benefit of lower computational costs.

cs.CV↗

arXiv2019

Fast Spatio-Temporal Residual Network for Video Super-Resolution

Recently, deep learning based video super-resolution (SR) methods have achieved promising performance. To simultaneously exploit the spatial and temporal information of videos, employing 3-dimensional (3D) convolutions is a natural approach. However, straight utilizing 3D convolutions may lead to an excessively high computational complexity which restricts the depth of video SR models and thus undermine the performance. In this paper, we present a novel fast spatio-temporal residual network (FSTRN) to adopt 3D convolutions for the video SR task in order to enhance the performance while maintaining a low computational load. Specifically, we propose a fast spatio-temporal residual block (FRB) that divide each 3D filter to the product of two 3D filters, which have considerably lower dimensions. Furthermore, we design a cross-space residual learning that directly links the low-resolution space and the high-resolution space, which can greatly relieve the computational burden on the feature fusion and up-scaling parts. Extensive evaluations and comparisons on benchmark datasets validate the strengths of the proposed approach and demonstrate that the proposed network significantly outperforms the current state-of-the-art methods.

cs.CV↗

arXiv2019

Scene Graph Generation with External Knowledge and Image Reconstruction

Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction,~\etc. However, existing datasets are biased in terms of object and relationship labels, or often come with noisy and missing annotations, which makes the development of a reliable scene graph prediction model very challenging. In this paper, we propose a novel scene graph generation algorithm with external knowledge and image reconstruction loss to overcome these dataset issues. In particular, we extract commonsense knowledge from the external knowledge base to refine object and phrase features for improving generalizability in scene graph generation. To address the bias of noisy object annotations, we introduce an auxiliary image reconstruction path to regularize the scene graph generation network. Extensive experiments show that our framework can generate better scene graphs, achieving the state-of-the-art performance on two benchmark datasets: Visual Relationship Detection and Visual Genome datasets.

cs.CV↗

arXiv2019

Spacing Dependent and Doping Independent Superconductivity in Intercalated 1T Two Dimensional SnSe2

The weak van der Waals interlayer interactions in the transition metal dichalcogenide (TMD) materials have created a rich platform to study their exotic electronic properties through chemical doping or physical gating techniques. We reported bulk superconductivity up to 7.6 K through careful manipulation of the charge carrier density and interlayer spacing d in the chemically intercalated two dimensional 1T-SnSe2 phase. We found, for the first time in the two dimensional SnSe2, that polar organic molecules cointercalated with the alkali metal Li into the basal layers, thus significantly enhancing the superconducting Tc. We observed that the Tc scales with the basal spacing distance, meanwhile being almost independent of x in Lix(THF)ySnSe2 system. Our results offers a new general chemical route to study the rich electron correlations and the interplay of charge density wave and unconventional superconductivity in the two dimensional material.

cond-mat.supr-con↗

arXiv2019

CIA-Towards a Unified Marketing Optimization Framework for e-Commerce Sponsored Search

As the largest e-commerce platform, Taobao helps advertisers reach billions of search queries each day via sponsored search, which has also contributed considerable revenue to the platform. An efficient bidding strategy to cater to diverse advertiser demands while balancing platform revenue and consumer experience is significant to a healthy and sustainable marketing ecosystem. In this paper we propose \emph{Customer Intelligent Agent (CIA)}, a bidding optimization framework which implements an impression-level bidding to reflect advertisers' conversion willingness and budget control. In this way, CIA is capable of fulfilling various e-commerce advertiser demands on different levels, such as Gross Merchandise Volume optimization, style comparison etc. Additionally, a replay based simulation system is designed to predict the performance of different take-rate. CIA unifies the benefits of three parties in the marketing ecosystem without changing the Generalized Second Price mechanism. Our extensive offline simulations and large-scale online experiments on \emph{Taobao Search Advertising (TSA)} platform verify the high effectiveness of the CIA framework. Moreover, CIA has been deployed online as a major bidding tool in TSA.

cs.GT↗

arXiv2019

Supervised Transfer Learning for Product Information Question Answering

Popular e-commerce websites such as Amazon offer community question answering systems for users to pose product related questions and experienced customers may provide answers voluntarily. In this paper, we show that the large volume of existing community question answering data can be beneficial when building a system for answering questions related to product facts and specifications. Our experimental results demonstrate that the performance of a model for answering questions related to products listed in the Home Depot website can be improved by a large margin via a simple transfer learning technique from an existing large-scale Amazon community question answering dataset. Transfer learning can result in an increase of about 10% in accuracy in the experimental setting where we restrict the size of the data of the target task used for training. As an application of this work, we integrate the best performing model trained in this work into a mobile-based shopping assistant and show its usefulness.

cs.CL↗

arXiv2018

Observation of Mollow quintuplet in F=3/2 hyperfine structure state of 3He atomic cell

We experimentally observed the Mollow quintuplet (MQ) in F=3/2 hyperfine structure state of 3He atoms. The metastability-exchange collisions (MECs) transfer the Mollow Triplet (MT) from the ground states of 3He atoms to the metastable states, and the MQ is demonstrated by four Zeeman levels of F=3/2 hyperfine states with linearly polarized light. The similar effect also achieves in the mixture cell of 3He and 4He.

quant-ph↗

arXiv2018

Observation of Mollow triplet with metastability exchange collisions in 3He atoms

We study the dressed states of 3He atoms and experimentally observe the Mollow triplet (MT) induced with an ultra-low-frequency (ULF) oscillating magnetic field as low as 4 Hz. The ULF MT signatures from the ground states of 3He atoms are transferred to the metastable states by metastability-exchange collisions (MECs) and measured optically, which demonstrates 2 s coherence time in the dressed ground states. The result shows the possibility of ULF magnetic field amplitude measurement and a new scheme for optical frequency modulation.

quant-ph↗

arXiv2018

X-GANs: Image Reconstruction Made Easy for Extreme Cases

Image reconstruction including image restoration and denoising is a challenging problem in the field of image computing. We present a new method, called X-GANs, for reconstruction of arbitrary corrupted resource based on a variant of conditional generative adversarial networks (conditional GANs). In our method, a novel generator and multi-scale discriminators are proposed, as well as the combined adversarial losses, which integrate a VGG perceptual loss, an adversarial perceptual loss, and an elaborate corresponding point loss together based on the analysis of image feature. Our conditional GANs have enabled a variety of applications in image reconstruction, including image denoising, image restoration from quite a sparse sampling, image inpainting, image recovery from the severely polluted block or even color-noise dominated images, which are extreme cases and haven't been addressed in the status quo. We have significantly improved the accuracy and quality of image reconstruction. Extensive perceptual experiments on datasets ranging from human faces to natural scenes demonstrate that images reconstructed by the presented approach are considerably more realistic than alternative work. Our method can also be extended to handle high-ratio image compression.

cs.CV↗

arXiv2018

A Multi-task Learning Approach for Improving Product Title Compression with User Search Log Data

It is a challenging and practical research problem to obtain effective compression of lengthy product titles for E-commerce. This is particularly important as more and more users browse mobile E-commerce apps and more merchants make the original product titles redundant and lengthy for Search Engine Optimization. Traditional text summarization approaches often require a large amount of preprocessing costs and do not capture the important issue of conversion rate in E-commerce. This paper proposes a novel multi-task learning approach for improving product title compression with user search log data. In particular, a pointer network-based sequence-to-sequence approach is utilized for title compression with an attentive mechanism as an extractive method and an attentive encoder-decoder approach is utilized for generating user search queries. The encoding parameters (i.e., semantic embedding of original titles) are shared among the two tasks and the attention distributions are jointly optimized. An extensive set of experiments with both human annotated data and online deployment demonstrate the advantage of the proposed research for both compression qualities and online business values.

cs.CL↗

arXiv2017

Investigation on the reported superconductivity in intercalated black phosphorus

Superconductivity intrinsic to the intercalated black phosphorus (BP) with a transition temperature Tc of 3.8 K, independent of the intercalant, whether an alkali or an alkaline earth element, has been reported recently by R. Zhang et al. (2017). However, the reported Tc and the field effect on the superconducting (SC) transition both bear great similarities to those for the pure Sn, which is commonly used for BP synthesis under the vapor transport method. We have therefore decided to determine whether a minute amount of Sn is present in the starting high purity BP crystals and whether it is the culprit for the small SC signal detected. Energy-dispersive X-ray spectroscopy results confirmed the existence of Sn in the starting high purity BP crystals purchased from the same company as in R. Zhang et al. (2017). We have reproduced the SC transition at 3.8 K in Li- and Na-intercalated BP crystals that contain minute amounts of Sn when prepared by the vapor transport method but not in BP crystals that are free of Sn when prepared by the high-pressure method. We have therefore concluded that the SC transition reported by R. Zhang et al. (2017) is associated with the Sn but not intrinsic to the intercalated BP crystals.

cond-mat.supr-con↗

arXiv2017

Superconductivity from site-selective Ru doping studies in Zr$_5$Ge$_3$ compound

Systematical doping studies have been carried out to search for the possible superconductivity in the transition metal doped Zr$_5$Ge$_3$ system. Superconductivity up to 5.7K is discovered in the Ru-doped Zr$_5$Ge$_{2.5}$Ru$_{0.5}$ sample. Interestingly, with the same Ru-doping, superconductivity is only induced with doping at the Ge site, but remains absent down to 1.8K with doping at the Zr site or interstitial site. Both magnetic and transport studies have revealed the bulk superconductivity nature for Ru-doped Zr$_5$Ge$_{2.5}$Ru$_{0.5}$ sample. The high upper critical field, enhanced electron correlation, and extremely small electron-phonon coupling, have indicated possible unconventional superconductivity in this system, which warrants further detailed theoretical and experimental studies.

cond-mat.supr-con↗

arXiv2017

Superconductivity in the ternary compound SrPt$_{10}$P$_4$ with complex new structure

We report superconductivity at 1.4K in the ternary SrPt$_{10}$P$_4$ with a complex new structure. SrPt$_{10}$P$_4$ crystallizes in a monoclinic space-group C2/c (\#15) with lattice parameters a= 22.9151(9)$Å$, b= 13.1664(5)$Å$, c=13.4131(5)$Å$, and $β$= 90.0270(5)${^\circ}$. Bulk superconductivity in the samples has been demonstrated through resistivity, ac susceptibility, and heat capacity measurements. High pressure measurements have shown that the superconducting T$_C$ is systematically suppressed upon application of pressure, with a dT$_C$/dP coefficient of -0.016 K/GPa.

cond-mat.supr-con↗

arXiv2017

New strategy for black phosphorus crystal growth through ternary clathrate

We are reporting a new synthetic strategy to grow large size black phosphorus (Black-P) crystals through a ternary clathrate Sn$_{24}$P$_{22-x}$I$_8$, under lower synthetic temperature and pressure. The Black-P crystals are found grown in situ at the site where the solid clathrate originally resides, which suggests chemical vapor mineralizer does not play a critical role for the Black-P formation. More detailed systematical studies has indicated the P vacancies in the framework of ternary clathrate Sn$_{24}$P$_{22-x}$I$_8$ is important for the subsequent Black-P from phosphorus vapors, and a likely Vapor-Solid-Solid (VSS) model is responsible for the Black-P crystal growth. The obtained room temperature mobility μ is ~ 350 $cm^2/Vs$ from Hall measurements at mechanically-cleaved flake, where noticeable micro-cracks are visible. The obtained high mobility value further suggest the high quality of the Black-P crystals synthesized through this route.

cond-mat.mtrl-sci↗

arXiv2017

Enabling Sparse Winograd Convolution by Native Pruning

Sparse methods and the use of Winograd convolutions are two orthogonal approaches, each of which significantly accelerates convolution computations in modern CNNs. Sparse Winograd merges these two and thus has the potential to offer a combined performance benefit. Nevertheless, training convolution layers so that the resulting Winograd kernels are sparse has not hitherto been very successful. By introducing a Winograd layer in place of a standard convolution layer, we can learn and prune Winograd coefficients "natively" and obtain sparsity level beyond 90% with only 0.1% accuracy loss with AlexNet on ImageNet dataset. Furthermore, we present a sparse Winograd convolution algorithm and implementation that exploits the sparsity, achieving up to 31.7 effective TFLOP/s in 32-bit precision on a latest Intel Xeon CPU, which corresponds to a 5.4x speedup over a state-of-the-art dense convolution implementation.

cs.CV↗

arXiv2017

Data hiding in Fingerprint Minutiae Template for Privacy Protection

In this paper, we propose a novel scheme for data hiding in the fingerprint minutiae template, which is the most popular in fingerprint recognition systems. Various strategies are proposed in data embedding in order to maintain the accuracy of fingerprint recognition as well as the undetectability of data hiding. In bits replacement based data embedding, we replace the last few bits of each element of the original minutiae template with the data to be hidden. This strategy can be further improved using an optimized bits replacement based data embedding, which is able to minimize the impact of data hiding on the performance of fingerprint recognition. The third strategy is an order preserving mechanism which is proposed to reduce the detectability of data hiding. By using such a mechanism, it would be difficult for the attacker to differentiate the minutiae template with hidden data from the original minutiae templates. The experimental results show that the proposed data hiding scheme achieves sufficient capacity for hiding common personal data, where the accuracy of fingerprint recognition is acceptable after the data hiding.

cs.CR↗