arXiv subjects

Chen Zhao

Publications and source records attributed to Chen Zhao.

At least 379 records · Page 21Linked to original sources

arXiv2020

Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization

Fine-grained visual categorization (FGVC) is an important but challenging task due to high intra-class variances and low inter-class variances caused by deformation, occlusion, illumination, etc. An attention convolutional binary neural tree architecture is presented to address those problems for weakly supervised FGVC. Specifically, we incorporate convolutional operations along edges of the tree structure, and use the routing functions in each node to determine the root-to-leaf computational paths within the tree. The final decision is computed as the summation of the predictions from leaf nodes. The deep convolutional operations learn to capture the representations of objects, and the tree structure characterizes the coarse-to-fine hierarchical feature learning process. In addition, we use the attention transformer module to enforce the network to capture discriminative features. The negative log-likelihood loss is used to train the entire network in an end-to-end fashion by SGD with back-propagation. Several experiments on the CUB-200-2011, Stanford Cars and Aircraft datasets demonstrate that the proposed method performs favorably against the state-of-the-arts.

cs.CV↗

arXiv2020

Potassium Isotopic Compositions of Enstatite Meteorites

Enstatite chondrites and aubrites are meteorites that show the closest similarities to the Earth in many isotope systems that undergo mass-independent and mass-dependent isotope fractionations. Due to the analytical challenges to obtain high-precision K isotopic compositions in the past, potential differences in K isotopic compositions between enstatite meteorites and the Earth remained uncertain. We report the first high-precision K isotopic compositions of eight enstatite chondrites and four aubrites and find that there is a significant variation of K isotopic compositions among enstatite meteorites (from -2.34 permil to -0.18 permil). However, K isotopic compositions of nearly all enstatite meteorites scatter around the Bulk Silicate Earth (BSE) value. The average K isotopic composition of the eight enstatite chondrites (-0.47 +/- 0.57 permil) is indistinguishable from the BSE value (-0.48 +/- 0.03 permil), thus further corroborating the isotopic similarity between Earth' building blocks and enstatite meteorite precursors. We found no correlation of K isotopic compositions with the chemical groups, petrological types, shock degrees, and terrestrial weathering conditions; however, the variation of K isotopes among enstatite meteorite can be attributed to the parent body processing. Our sample of the main group aubrite MIL 13004 is exceptional and has an extremely light K isotopic composition (delta 41K= -2.34 +/- 0.12 permil). We attribute this unique K isotopic feature to the presence of abundant djerfisherite inclusions in our sample because this K-bearing sulfide mineral is predicted to be enriched in 39K during equilibrium exchange with silicates.

astro-ph.EP↗

arXiv2020

MacPherson's Conjecture via Hörmander Estimate

In this notes we reprove MacPherson's conjecture on $L^2-(n,q)$-cohomology through Demailly's formulation of Hörmander's Estimate. This approach allows us to weaken the condition of locally semipositivity in Ruppenthal's $L^2$-representation of adjoint bundle. Moreover we prove the MacPherson's conjecture of twisted coefficient bundle under an arbitrary singular hermitian metric. As applications, we study the MacPherson type problem for pluri-canonical bundle.

math.CV↗

arXiv2019

Learning Semantic Neural Tree for Human Parsing

The majority of existing human parsing methods formulate the task as semantic segmentation, which regard each semantic category equally and fail to exploit the intrinsic physiological structure of human body, resulting in inaccurate results. In this paper, we design a novel semantic neural tree for human parsing, which uses a tree architecture to encode physiological structure of human body, and designs a coarse to fine process in a cascade manner to generate accurate results. Specifically, the semantic neural tree is designed to segment human regions into multiple semantic subregions (e.g., face, arms, and legs) in a hierarchical way using a new designed attention routing module. Meanwhile, we introduce the semantic aggregation module to combine multiple hierarchical features to exploit more context information for better performance. Our semantic neural tree can be trained in an end-to-end fashion by standard stochastic gradient descent (SGD) with back-propagation. Several experiments conducted on four challenging datasets for both single and multiple human parsing, i.e., LIP, PASCAL-Person-Part, CIHP and MHP-v2, demonstrate the effectiveness of the proposed method. Code can be found at https://isrc.iscas.ac.cn/gitlab/research/sematree.

cs.CV↗

arXiv2019

Memories in the Photoluminescence Intermittency of Single Cesium Lead Bromide Nanocrystals

Single cesium lead bromide (CsPbBr3) nanocrystals show strong photoluminescence blinking, with on- and off- dwelling times following power-law distributions. We investigate the memory effect in the photoluminescence blinking of single CsPbBr3 nanocrystals and find positive correlations for successive on-times and successive off-times. This memory effect is not sensitive to the nature of the surface capping ligand and the embedding polymer. These observations suggest that photoluminescence intermittency and its memory are mainly controlled by intrinsic traps in the nanocrystals. These findings will help optimizing light-emitting devices based on inorganic perovskite nanocrystals.

physics.app-ph↗

arXiv2019

Iterative Clustering with Game-Theoretic Matching for Robust Multi-consistency Correspondence

Matching corresponding features between two images is a fundamental task to computer vision with numerous applications in object recognition, robotics, and 3D reconstruction. Current state of the art in image feature matching has focused on establishing a single consistency in static scenes; by contrast, finding multiple consistencies in dynamic scenes has been under-researched. In this paper, we present an end-to-end optimization framework named "iterative clustering with Game-Theoretic Matching" (ic-GTM) for robust multi-consistency correspondence. The key idea is to formulate multi-consistency matching as a generalized clustering problem for an image pair. In our formulation, several local matching games are simultaneously carried out in different corresponding block pairs under the guidance of a novel payoff function consisting of both geometric and descriptive compatibility; the global matching results are further iteratively refined by clustering and thresholding with respect to a payoff matrix. We also propose three new metrics for evaluating the performance of multi-consistency image feature matching. Extensive experimental results have shown that the proposed framework significantly outperforms previous state-of-the-art approaches on both singleconsistency and multi-consistency datasets.

cs.CV↗

arXiv2019

Characteristics of human mobility patterns revealed by high-frequency cell-phone position data

Human mobility is an important characteristic of human behavior, but since tracking personalized position to high temporal and spatial resolution is difficult, most studies on human mobility patterns rely largely on mathematical models. Seminal models which assume frequently visited locations tend to be re-visited, reproduce a wide range of statistical features including collective mobility fluxes and numerous scaling laws. However, these models cannot be verified at a time-scale relevant to our daily travel patterns as most available data do not provide the necessary temporal resolution. In this work, we re-examined human mobility mechanisms via comprehensive cell-phone position data recorded at a high frequency up to every second. We found that the next location visited by users is not their most frequently visited ones in many cases. Instead, individuals exhibit origin-dependent, path-preferential patterns in their short time-scale mobility. These behaviors are prominent when the temporal resolution of the data is high, and are thus overlooked in most previous studies. Incorporating measured quantities from our high frequency data into conventional human mobility models shows contradictory statistical results. We finally revealed that the individual preferential transition mechanism characterized by the first-order Markov process can quantitatively reproduce the observed travel patterns at both individual and population levels at all relevant time-scales.

physics.soc-ph↗

arXiv2019

Comparative evaluation of 2D feature correspondence selection algorithms

Correspondence selection aiming at seeking correct feature correspondences from raw feature matches is pivotal for a number of feature-matching-based tasks. Various 2D (image) correspondence selection algorithms have been presented with decades of progress. Unfortunately, the lack of an in-depth evaluation makes it difficult for developers to choose a proper algorithm given a specific application. This paper fills this gap by evaluating eight 2D correspondence selection algorithms ranging from classical methods to the most recent ones on four standard datasets. The diversity of experimental datasets brings various nuisances including zoom, rotation, blur, viewpoint change, JPEG compression, light change, different rendering styles and multi-structures for comprehensive test. To further create different distributions of initial matches, a set of combinations of detector and descriptor is also taken into consideration. We measure the quality of a correspondence selection algorithm from four perspectives, i.e., precision, recall, F-measure and efficiency. According to evaluation results, the current advantages and limitations of all considered algorithms are aggregately summarized which could be treated as a "user guide" for the following developers.

cs.CV↗

arXiv2019

Learning to Fuse Local Geometric Features for 3D Rigid Data Matching

This paper presents a simple yet very effective data-driven approach to fuse both low-level and high-level local geometric features for 3D rigid data matching. It is a common practice to generate distinctive geometric descriptors by fusing low-level features from various viewpoints or subspaces, or enhance geometric feature matching by leveraging multiple high-level features. In prior works, they are typically performed via linear operations such as concatenation and min pooling. We show that more compact and distinctive representations can be achieved by optimizing a neural network (NN) model under the triplet framework that non-linearly fuses local geometric features in Euclidean spaces. The NN model is trained by an improved triplet loss function that fully leverages all pairwise relationships within the triplet. Moreover, the fused descriptor by our approach is also competitive to deep learned descriptors from raw data while being more lightweight and rotational invariant. Experimental results on four standard datasets with various data modalities and application contexts confirm the advantages of our approach in terms of both feature matching and geometric registration.

cs.CV↗

arXiv2019

NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences

Feature correspondence selection is pivotal to many feature-matching based tasks in computer vision. Searching for spatially k-nearest neighbors is a common strategy for extracting local information in many previous works. However, there is no guarantee that the spatially k-nearest neighbors of correspondences are consistent because the spatial distribution of false correspondences is often irregular. To address this issue, we present a compatibility-specific mining method to search for consistent neighbors. Moreover, in order to extract and aggregate more reliable features from neighbors, we propose a hierarchical network named NM-Net with a series of convolution layers taking the generated graph as input, which is insensitive to the order of correspondences. Our experimental results have shown the proposed method achieves the state-of-the-art performance on four datasets with various inlier ratios and varying numbers of feature consistencies.

cs.CV↗

arXiv2018

A Lagrangian Dual Based Approach to Sparse Linear Programming

A sparse linear programming (SLP) problem is a linear programming problem equipped with a sparsity (or cardinality) constraint, which is nonconvex and discontinuous theoretically and generally NP-hard computationally due to the combinatorial property involved. By rewriting the sparsity constraint into a disjunctive form, we present an explicit formula of its Lagrangian dual in terms of an unconstrained piecewise-linear convex programming problem which admits a strong duality. A semi-proximal alternating direction method of multipliers (sPADMM) is then proposed to solve this dual problem by taking advantage of the efficient computation of the proximal mapping of the vector Ky-Fan norm function. Based on the optimal solution of the dual problem, we design a dual-primal algorithm for pursuing a global solution of the original SLP problem. Numerical results illustrate that our proposed algorithm is promising especially for large-scale problems.

math.OC↗

arXiv2018

Capillary filling in closed-end nanotubes

Capillary filling in small length scale is an important process in nanotechnology and microfabrication. When one end of the tube or channel is sealed, it is important to consider the escape of the trapped gas. We develop a dynamic model on capillary filling in closed-end tubes, based on the diffusion-convection equation and Henry's law of gas dissolution. We systematically investigate the filling dynamics for various sets of parameters, and compare the results with a previous model which assumes a linear density profile of dissolved gas and neglect the convective term.

cond-mat.soft↗

arXiv2016

LightNet: A Versatile, Standalone Matlab-based Environment for Deep Learning

LightNet is a lightweight, versatile and purely Matlab-based deep learning framework. The idea underlying its design is to provide an easy-to-understand, easy-to-use and efficient computational platform for deep learning research. The implemented framework supports major deep learning architectures such as Multilayer Perceptron Networks (MLP), Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). The framework also supports both CPU and GPU computation, and the switch between them is straightforward. Different applications in computer vision, natural language processing and robotics are demonstrated as experiments.

cs.LG↗

arXiv2016

Fundamental building blocks of controlling complex networks: A universal controllability framework

To understand the controllability of complex networks is a forefront problem relevant to different fields of science and engineering. Despite recent advances in network controllability theories, an outstanding issue is to understand the effect of network topology and nodal interactions on the controllability at the most fundamental level. Here we develop a universal framework based on local information only to unearth the most {\em fundamental building blocks} that determine the controllability. In particular, we introduce a network dissection process to fully unveil the origin of the role of individual nodes and links in control, giving rise to a criterion for the much needed strong structural controllability. We theoretically uncover various phase-transition phenomena associated with the role of nodes and links and strong structural controllability. Applying our theory to a large number of empirical networks demonstrates that technological networks are more strongly structurally controllable (SSC) than many social and biological networks, and real world networks are generally much more SSC than their random counterparts with intrinsic resilience and adaptability as a result of human design and natural evolution.

physics.soc-ph↗

arXiv2014

Universal Predictability of Mobility Patterns in Cities

Despite the long history of modelling human mobility, we continue to lack a highly accurate approach with low data requirements for predicting mobility patterns in cities. Here, we present a population-weighted opportunities model without any adjustable parameters to capture the underlying driving force accounting for human mobility patterns at the city scale. We use various mobility data collected from a number of cities with different characteristics to demonstrate the predictive power of our model. We find that insofar as the spatial distribution of population is available, our model offers universal prediction of mobility patterns in good agreement with real observations, including distance distribution, destination travel constraints and flux. In contrast, the models that succeed in modelling mobility patterns in countries are not applicable in cities, which suggests that there is a diversity of human mobility at different spatial scales. Our model has potential applications in many fields relevant to mobility behaviour in cities, without relying on previous mobility measurements.

physics.soc-ph↗

arXiv2014

Individual dynamics induces symmetry in network controllability

Controlling complex networked systems to a desired state is a key research goal in contemporary science. Despite recent advances in studying the impact of network topology on controllability, a comprehensive understanding of the synergistic effect of network topology and individual dynamics on controllability is still lacking. Here we offer a theoretical study with particular interest in the diversity of dynamic units characterized by different types of individual dynamics. Interestingly, we find a global symmetry accounting for the invariance of controllability with respect to exchanging the densities of any two different types of dynamic units, irrespective of the network topology. The highest controllability arises at the global symmetry point, at which different types of dynamic units are of the same density. The lowest controllability occurs when all self-loops are either completely absent or present with identical weights. These findings further improve our understanding of network controllability and have implications for devising the optimal control of complex networked systems in a wide range of fields.

math.OC↗

arXiv2014

Image Compressive Sensing Recovery Using Adaptively Learned Sparsifying Basis via L0 Minimization

From many fewer acquired measurements than suggested by the Nyquist sampling theory, compressive sensing (CS) theory demonstrates that, a signal can be reconstructed with high probability when it exhibits sparsity in some domain. Most of the conventional CS recovery approaches, however, exploited a set of fixed bases (e.g. DCT, wavelet and gradient domain) for the entirety of a signal, which are irrespective of the non-stationarity of natural signals and cannot achieve high enough degree of sparsity, thus resulting in poor CS recovery performance. In this paper, we propose a new framework for image compressive sensing recovery using adaptively learned sparsifying basis via L0 minimization. The intrinsic sparsity of natural images is enforced substantially by sparsely representing overlapped image patches using the adaptively learned sparsifying basis in the form of L0 norm, greatly reducing blocking artifacts and confining the CS solution space. To make our proposed scheme tractable and robust, a split Bregman iteration based technique is developed to solve the non-convex L0 minimization problem efficiently. Experimental results on a wide range of natural images for CS recovery have shown that our proposed algorithm achieves significant performance improvements over many current state-of-the-art schemes and exhibits good convergence property.

cs.CV↗

arXiv2013

Exact Controllability of Complex Networks

Controlling complex networks is of paramount importance in science and engineering. Despite the recent development of structural-controllability theory, we continue to lack a framework to control undirected complex networks, especially given link weights. Here we introduce an exact-controllability paradigm based on the maximum multiplicity to identify the minimum set of driver nodes required to achieve full control of networks with arbitrary structures and link-weight distributions. The framework reproduces the structural controllability of directed networks characterized by structural matrices. We explore the controllability of a large number of real and model networks, finding that dense networks with identical weights are difficult to be controlled. An efficient and accurate tool is offered to assess the controllability of large sparse and dense networks. The exact-controllability framework enables a comprehensive understanding of the impact of network properties on controllability, a fundamental problem towards our ultimate control of complex systems.

physics.soc-ph↗