arXiv subjects

Yu Liu

Publications and source records attributed to Yu Liu.

At least 847 records · Page 47Linked to original sources

arXiv2021

Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing

Deep learning based virtual try-on system has achieved some encouraging progress recently, but there still remain several big challenges that need to be solved, such as trying on arbitrary clothes of all types, trying on the clothes from one category to another and generating image-realistic results with few artifacts. To handle this issue, we in this paper first collect a new dataset with all types of clothes, \ie tops, bottoms, and whole clothes, each one has multiple categories with rich information of clothing characteristics such as patterns, logos, and other details. Based on this dataset, we then propose the Arbitrary Virtual Try-On Network (AVTON) that is utilized for all-type clothes, which can synthesize realistic try-on images by preserving and trading off characteristics of the target clothes and the reference person. Our approach includes three modules: 1) Limbs Prediction Module, which is utilized for predicting the human body parts by preserving the characteristics of the reference person. This is especially good for handling cross-category try-on task (\eg long sleeves $\leftrightarrow$ short sleeves or long pants $\leftrightarrow$ skirts, \etc), where the exposed arms or legs with the skin colors and details can be reasonably predicted; 2) Improved Geometric Matching Module, which is designed to warp clothes according to the geometry of the target person. We improve the TPS based warping method with a compactly supported radial function (Wendland's $Ψ$-function); 3) Trade-Off Fusion Module, which is to trade off the characteristics of the warped clothes and the reference person. This module is to make the generated try-on images look more natural and realistic based on a fine-tune symmetry of the network structure. Extensive simulations are conducted and our approach can achieve better performance compared with the state-of-the-art virtual try-on methods.

cs.CV↗

arXiv2021

Reviewing continual learning from the perspective of human-level intelligence

Humans' continual learning (CL) ability is closely related to Stability Versus Plasticity Dilemma that describes how humans achieve ongoing learning capacity and preservation for learned information. The notion of CL has always been present in artificial intelligence (AI) since its births. This paper proposes a comprehensive review of CL. Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism. Analogous to biological counterpart, "smart" AI agents are supposed to i) remember previously learned information (information retrospection); ii) infer on new information continuously (information prospection:); iii) transfer useful information (information transfer), to achieve high-level CL. According to the taxonomy, evaluation metrics, algorithms, applications as well as some open issues are then introduced. Our main contributions concern i) rechecking CL from the level of artificial general intelligence; ii) providing a detailed and extensive overview on CL topics; iii) presenting some novel ideas on the potential development of CL.

cs.LG↗

arXiv2021

Learning by Active Forgetting for Neural Networks

Remembering and forgetting mechanisms are two sides of the same coin in a human learning-memory system. Inspired by human brain memory mechanisms, modern machine learning systems have been working to endow machine with lifelong learning capability through better remembering while pushing the forgetting as the antagonist to overcome. Nevertheless, this idea might only see the half picture. Up until very recently, increasing researchers argue that a brain is born to forget, i.e., forgetting is a natural and active process for abstract, rich, and flexible representations. This paper presents a learning model by active forgetting mechanism with artificial neural networks. The active forgetting mechanism (AFM) is introduced to a neural network via a "plug-and-play" forgetting layer (P\&PF), consisting of groups of inhibitory neurons with Internal Regulation Strategy (IRS) to adjust the extinction rate of themselves via lateral inhibition mechanism and External Regulation Strategy (ERS) to adjust the extinction rate of excitatory neurons via inhibition mechanism. Experimental studies have shown that the P\&PF offers surprising benefits: self-adaptive structure, strong generalization, long-term learning and memory, and robustness to data and parameter perturbation. This work sheds light on the importance of forgetting in the learning process and offers new perspectives to understand the underlying mechanisms of neural networks.

cs.LG↗

arXiv2021

Sharpness of phase transition for Voronoi percolation in hyperbolic space

In this paper, we consider Voronoi percolation in the hyperbolic space $\mathbb{H}^d$ ($d\ge 2$) and show that the phase transition is sharp. More precisely, we show that for Voronoi percolation with parameter $p$ generated by a homogeneous Poisson point process with intensity $λ$, there exists $p_c:=p_c(λ,d)$ such that the probability of a monochromatic path from the origin reaching a distance of $n$ decays exponentially fast in $n$. We also prove the mean-field lower bound $\mathbb{P}_{λ,p}(0\leftrightarrow \infty)\ge c(p-p_c)$ for $p>p_c$.

math.PR↗

arXiv2021

Spatio-Temporal Urban Knowledge Graph Enabled Mobility Prediction

With the rapid development of the mobile communication technology, mobile trajectories of humans are massively collected by Internet service providers (ISPs) and application service providers (ASPs). On the other hand, the rising paradigm of knowledge graph (KG) provides us a promising solution to extract structured "knowledge" from massive trajectory data. In this paper, we focus on modeling users' spatio-temporal mobility patterns based on knowledge graph techniques, and predicting users' future movement based on the "knowledge'' extracted from multiple sources in a cohesive manner. Specifically, we propose a new type of knowledge graph, i.e., spatio-temporal urban knowledge graph (STKG), where mobility trajectories, category information of venues, and temporal information are jointly modeled by the facts with different relation types in STKG. The mobility prediction problem is converted to the knowledge graph completion problem in STKG. Further, a complex embedding model with elaborately designed scoring functions is proposed to measure the plausibility of facts in STKG to solve the knowledge graph completion problem, which considers temporal dynamics of the mobility patterns and utilizes PoI categories as the auxiliary information and background knowledge. Extensive evaluations confirm the high accuracy of our model in predicting users' mobility, i.e., improving the accuracy by 5.04% compared with the state-of-the-art algorithms. In addition, PoI categories as the background knowledge and auxiliary information are confirmed to be helpful by improving the performance by 3.85% in terms of accuracy. Additionally, experiments show that our proposed method is time-efficient by reducing the computational time by over 43.12% compared with existing methods.

cs.SI↗

arXiv2021

A model for nuclear spin product-state distributions of ultracold chemical reactions in magnetic fields

Based on a theoretical model where the nuclear spins remain unchanged during a collision, we provide an analytical and general expression for the nuclear spin state-to-state distribution of an ultracold chemical reaction in a magnetic field, for given rotational transitions of the molecules. It simply requires knowledge of the field-dependent eigenfunctions of the molecular reactants and products of the chemical reaction. The final state-to-state distribution drastically changes with the magnetic field. When the distribution is summed over all the final products, a simplified expression is found where only the knowledge of the eigenfunctions of the molecular reactants is required. The present theoretical formalism has been successfully used to explain the magnetic field behavior of the product-state distribution in chemical reactions of ultracold KRb molecules [Hu et al., Nat. Chem. 13, 435 (2021)].

physics.atom-ph↗

arXiv2021

Knowledge-driven Site Selection via Urban Knowledge Graph

Site selection determines optimal locations for new stores, which is of crucial importance to business success. Especially, the wide application of artificial intelligence with multi-source urban data makes intelligent site selection promising. However, existing data-driven methods heavily rely on feature engineering, facing the issues of business generalization and complex relationship modeling. To get rid of the dilemma, in this work, we borrow ideas from knowledge graph (KG), and propose a knowledge-driven model for site selection, short for KnowSite. Specifically, motivated by distilled knowledge and rich semantics in KG, we firstly construct an urban KG (UrbanKG) with cities' key elements and semantic relationships captured. Based on UrbanKG, we employ pre-training techniques for semantic representations, which are fed into an encoder-decoder structure for site decisions. With multi-relational message passing and relation path-based attention mechanism developed, KnowSite successfully reveals the relationship between various businesses and site selection criteria. Extensive experiments on two datasets demonstrate that KnowSite outperforms representative baselines with both effectiveness and explainability achieved.

cs.AI↗

arXiv2021

A Novel Binocular Eye-Tracking SystemWith Stereo Stimuli for 3D Gaze Estimation

Eye-tracking technologies have been widely used in applications like psychological studies and human computer interactions (HCI). However, most current eye trackers focus on 2D point of gaze (PoG) estimation and cannot provide accurate gaze depth.Concerning future applications such as HCI with 3D displays, we propose a novel binocular eye tracking device with stereo stimuli to provide highly accurate 3D PoG estimation. In our device, the 3D stereo imaging system can provide users with a friendly and immersive 3D visual experience without wearing any accessories. The eye capturing system can directly record the users eye movements under 3D stimuli without disturbance. A regression based 3D eye tracking model is built based on collected eye movement data under stereo stimuli. Our model estimates users 2D gaze with features defined by eye region landmarks and further estimates 3D PoG with a multi source feature set constructed by comprehensive eye movement features and disparity features from stereo stimuli. Two test stereo scenes with different depths of field are designed to verify the model effectiveness. Experimental results show that the average error for 2D gaze estimation was 0.66\degree and for 3D PoG estimation, the average errors are 1.85~cm/0.15~m over the workspace volume 50~cm $\times$ 30~cm $\times$ 75~cm/2.4~m $\times$ 4.0~m $\times$ 7.9~m separately.

cs.CV↗

arXiv2021

Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings

Recent knowledge graph embedding (KGE) models based on hyperbolic geometry have shown great potential in a low-dimensional embedding space. However, the necessity of hyperbolic space in KGE is still questionable, because the calculation based on hyperbolic geometry is much more complicated than Euclidean operations. In this paper, based on the state-of-the-art hyperbolic-based model RotH, we develop two lightweight Euclidean-based models, called RotL and Rot2L. The RotL model simplifies the hyperbolic operations while keeping the flexible normalization effect. Utilizing a novel two-layer stacked transformation and based on RotL, the Rot2L model obtains an improved representation capability, yet costs fewer parameters and calculations than RotH. The experiments on link prediction show that Rot2L achieves the state-of-the-art performance on two widely-used datasets in low-dimensional knowledge graph embeddings. Furthermore, RotL achieves similar performance as RotH but only requires half of the training time.

cs.AI↗

arXiv2021

Photoinduced anisotropic lattice dynamic response and domain formation in thermoelectric SnSe

Identifying and understanding the mechanisms behind strong phonon-phonon scattering in condensed matter systems is critical to maximizing the efficiency of thermoelectric devices. To date, the leading method to address this has been to meticulously survey the full phonon dispersion of the material in order to isolate modes with anomalously large linewidth and temperature-dependence. Here we combine quantitative MeV ultrafast electron diffraction (UED) analysis with Monte Carlo based dynamic diffraction simulation and first-principles calculations to directly unveil the soft, anharmonic lattice distortions of model thermoelectric material SnSe. A small single-crystal sample is photoexcited with ultrafast optical pulses and the soft, anharmonic lattice distortions are isolated using MeV-UED as those associated with long relaxation time and large displacements. We reveal that these modes have interlayer shear strain character, induced mainly by c-axis atomic displacements, resulting in domain formation in the transient state. These findings provide an innovative approach to identify mechanisms for ultralow and anisotropic thermal conductivity and a promising route to optimizing thermoelectric devices.

cond-mat.mtrl-sci↗

arXiv2021

Three-dimensional ferromagnetism and magnetotransport in van der Waals Mn-intercalated tantalum disufide

Van der Waals (vdW) ferromagnets are an important class of materials for spintronics applications. The recent discovery of atomically vdW magnets CrI$_3$ and Cr$_2$Ge$_2$Te$_6$ has triggered a renaissance in the area of two-dimensional (2D) magnetism. Herein we systematically studied 2H-Mn$_{0.28}$TaS$_2$ single crystal, a 2D vdW ferromagnet with $T_c$ $\sim$ 82.3 K and a large in-plane magnetic anisotropy. Mn $K$-edge x-ray absorption spectroscopy was measured to provide information on its electronic state and local atomic environment. The detailed magnetic isotherms measured in the vicinity of $T_c$ indicates that the spin coupling inside 2H-Mn$_{0.28}$TaS$_2$ is of a three-dimensional (3D) Heisenberg-type coupled with the attractive long-range interaction between spins that decay as $J(r)\approx r^{-4.85}$. Both resistivity $ρ(T)$ and thermopower $S(T)$ exhibit anomalies near $T_c$, confirming that the hole-type transport carriers strongly interact with local moments. An unusual angle-dependent magnetoresistance is further observed, suggesting a possible field-induced novel magnetic structure.

cond-mat.str-el↗

arXiv2021

Polaronic transport and thermoelectricity in Mn$_3$Si$_2$Te$_6$ single crystals

We carried out a comprehensive study of the structural, electrical transport, thermal and thermodynamic properties in ferrimagnetic Mn$_3$Si$_2$Te$_6$ single crystals. Mn and Te $K$-edge X-ray absorption spectroscopy and synchrotron powder X-ray diffraction were measured to provide information on the local atomic environment and the average crystal structure. The dc and ac magnetic susceptibility measurements indicate a second-order paramagnetic to ferrimagnetic transition at $T_c$ $\sim$ 74 K, which is further confirmed by the specific heat measurement. Mn$_3$Si$_2$Te$_6$ exhibits semiconducting behavior along with a large negative magnetoresistance of -87\% at $T_c$ and relatively high value of thermopower up to $\sim$ 10 mV/K at 5 K. Besides the rapidly increasing resistivity $ρ(T)$ and thermopower $S(T)$ below 20 K, the large discrepancy between activation energy for resistivity $E_ρ$ and thermopower $E_S$ above 20 K indicates the polaronic transport mechanism. Furthermore, the thermal conductivity $κ(T)$ of Mn$_3$Si$_2$Te$_6$ is notably rather low, comparable to Cr$_2$Si$_2$Te$_6$, and is strongly suppressed in magnetic field across $T_c$, indicating the presence of strong spin-lattice coupling, also similar with Cr$_2$Si$_2$Te$_6$.

cond-mat.str-el↗

arXiv2021

Magnetic critical behavior and anomalous Hall effect in 2H-Co$_{0.22}$TaS$_{2}$ single crystals

We report ferromagnetism in 2H-Co$_{0.22}$TaS$_2$ single crystals where Co atoms are intercalated in the van der Waals gap, and a systematic study of its magnetic critical behavior in the vicinity of $T_c \sim 28$ K. The obtained critical exponents $β$ = 0.43(2), $γ$ = 1.15(1), and $δ= 3.54(1)$ fulfill the Widom scaling relation $δ= 1+γ/β$ and follow the scaling equation. This indicates that the spin coupling in 2H-Co$_{0.22}$TaS$_2$ is of three-dimensional Hersenberg type coupled with long-range magnetic interaction, and that the exchange interaction decays with distance as $J(r)\approx r^{-4.69}$. 2H-Co$_{0.22}$TaS$_2$ exhibits a weak temperature-dependent metallic behavior in resistivity and negative values of thermopower with dominant electron-type carriers, in which obvious anomalies were observed below $T_c$ as well as the anomalous Hall effect (AHE). The linear scaling behavior between the modified anomalous Hall resistivity $ρ_{xy}/μ_0H$ and longitudinal resistivity $ρ_{xx}^2M/μ_0H$ implies that the origin of AHE in 2H-Co$_{0.22}$TaS$_2$ should be dominated by the extrinsic side-jump mechanism.

cond-mat.mtrl-sci↗

arXiv2021

RelationRS: Relationship Representation Network for Object Detection in Aerial Images

Object detection is a basic and important task in the field of aerial image processing and has gained much attention in computer vision. However, previous aerial image object detection approaches have insufficient use of scene semantic information between different regions of large-scale aerial images. In addition, complex background and scale changes make it difficult to improve detection accuracy. To address these issues, we propose a relationship representation network for object detection in aerial images (RelationRS): 1) Firstly, multi-scale features are fused and enhanced by a dual relationship module (DRM) with conditional convolution. The dual relationship module learns the potential relationship between features of different scales and learns the relationship between different scenes from different patches in a same iteration. In addition, the dual relationship module dynamically generates parameters to guide the fusion of multi-scale features. 2) Secondly, The bridging visual representations module (BVR) is introduced into the field of aerial images to improve the object detection effect in images with complex backgrounds. Experiments with a publicly available object detection dataset for aerial images demonstrate that the proposed RelationRS achieves a state-of-the-art detection performance.

cs.CV↗

arXiv2021

Silting reduction in extriangulated categories

Presilting and silting subcategories in extriangulated categories were introduced by Adachi and Tsukamoto recently. In this paper, we prove that the Gabriel-Zisman localization $\mathcal B/({\rm thick}\mathcal W)$ of an extriangulated category $\mathcal B$ with respect to a presilting subcategory $\mathcal W$ satisfying certain condition can be realized as a subfactor category of $\mathcal B$. This generalizes the result by Iyama-Yang for silting reduction on triangulated categories. Then we discuss the relation between silting subcategories and tilting subcategories in extriangulated categories, this gives us a kind of important examples of our results. In particular, for a finite dimensional Gorenstein algebra, we get the relative version of the description of the singularity category due to Happel and Chen-Zhang by this reduction.

math.RT↗

arXiv2021

UniNet: Unified Architecture Search with Convolution, Transformer, and MLP

Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. A few works investigated manually combining those operators to design visual network architectures, and can achieve satisfactory performances to some extent. In this paper, we propose to jointly search the optimal combination of convolution, transformer, and MLP for building a series of all-operator network architectures with high performances on visual tasks. We empirically identify that the widely-used strided convolution or pooling based down-sampling modules become the performance bottlenecks when the operators are combined to form a network. To better tackle the global context captured by the transformer and MLP operators, we propose two novel context-aware down-sampling modules, which can better adapt to the global information encoded by transformer and MLP operators. To this end, we jointly search all operators and down-sampling modules in a unified search space. Notably, Our searched network UniNet (Unified Network) outperforms state-of-the-art pure convolution-based architecture, EfficientNet, and pure transformer-based architecture, Swin-Transformer, on multiple public visual benchmarks, ImageNet classification, COCO object detection, and ADE20K semantic segmentation.

cs.CV↗

arXiv2021

Radio-frequency C-V measurements with sub-attofarad sensitivity

We demonstrate the use of radio-frequency (rf) resonators to measure the capacitance of nano-scale semiconducting devices in field-effect transistor configurations. The rf resonator is attached to the gate or the lead of the device. Consequently, tuning the carrier density in the conducting channel of the device affects the resonance frequency, quantitatively reflecting its capacitance. We test the measurement method on InSb and InAs nanowires at dilution-refrigerator temperatures. The measured capacitances are consistent with those inferred from the periodicity of the Coulomb blockade of quantum dots realized in the same devices. In an implementation of the resonator using an off-chip superconducting spiral inductor we find sensitivity values reaching down to 75~zF/$\sqHz$ at 1~kHz measurement bandwidth, and noise down to 0.45~aF at 1~Hz bandwidth. We estimate the sensitivity of the method for a number of other implementations. In particular we predict typical sensitivity of about 40~zF/$\sqHz$ at room temperature with a resonator comprised of off-the-shelf components. Of several proposed applications, we demonstrate two: the capacitance measurement of several identical 80~nm-wide gates with a single resonator, and the field-effect mobility measurement of an individual nanowire with the gate capacitance measured in-situ.

cond-mat.mes-hall↗

arXiv2021

Gluing n-tilting and n-cotilting subcategories

Recently, Wang, Wei and Zhang define the recollement of extriangulated categories, which is a generalization of both recollement of abelian categories and recollement of triangulated categories. For a recollement $(\mathcal A ,\mathcal B,\mathcal C)$ of extriangulated categories, we show that $n$-tilting (resp. $n$-cotilting) subcategories in $\mathcal A$ and $\mathcal C$ can be glued to get $n$-tilting (resp. $n$-cotilting) subcategories in $\mathcal B$ under certain conditions.

math.RT↗