arXiv subjects

Gong Cheng

Publications and source records attributed to Gong Cheng.

At least 91 records · Page 5Linked to original sources

arXiv2021

Weakly Supervised Object Localization and Detection: A Survey

As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems and has received significant attention in the past decade. As methods have been proposed, a comprehensive survey of these topics is of great importance. In this work, we review (1) classic models, (2) approaches with feature representations from off-the-shelf deep networks, (3) approaches solely based on deep learning, and (4) publicly available datasets and standard evaluation metrics that are widely used in this field. We also discuss the key challenges in this field, development history of this field, advantages/disadvantages of the methods in each category, the relationships between methods in different categories, applications of the weakly supervised object localization and detection methods, and potential future directions to further promote the development of this research field.

cs.CV↗

arXiv2021

Scrambling with conservation law

In this article we discuss the impact of conservation laws, specifically $U(1)$ charge conservation and energy conservation, on scrambling dynamics, especially on the approach to the late time fully scrambled state. As a model, we consider a $d+1$ dimensional ($d\geq 2$) holographic conformal field theory with Einstein gravity dual. Using the holographic dictionary, we calculate out-of-time-order-correlators (OTOCs) that involve the conserved $U(1)$ current operator or energy-momentum tensor. We show that these OTOCs approach their late time value as a power law in time, with a universal exponent $\frac{d}{2}$. We also generalize the result to compute OTOCs between general operators which have overlap with the conserved charges.

cond-mat.stat-mech↗

arXiv2021

TSQA: Tabular Scenario Based Question Answering

Scenario-based question answering (SQA) has attracted an increasing research interest. Compared with the well-studied machine reading comprehension (MRC), SQA is a more challenging task: a scenario may contain not only a textual passage to read but also structured data like tables, i.e., tabular scenario based question answering (TSQA). AI applications of TSQA such as answering multiple-choice questions in high-school exams require synthesizing data in multiple cells and combining tables with texts and domain knowledge to infer answers. To support the study of this task, we construct GeoTSQA. This dataset contains 1k real questions contextualized by tabular scenarios in the geography domain. To solve the task, we extend state-of-the-art MRC methods with TTGen, a novel table-to-text generator. It generates sentences from variously synthesized tabular data and feeds the downstream MRC method with the most useful sentences. Its sentence ranking model fuses the information in the scenario, question, and domain knowledge. Our approach outperforms a variety of strong baseline methods on GeoTSQA.

cs.CL↗

arXiv2020

Combinatorics-Based Approaches to Controllability Characterization for Bilinear Systems

The control of bilinear systems has attracted considerable attention in the field of systems and control for decades, owing to their prevalence in diverse applications across science and engineering disciplines. Although much work has been conducted on analyzing controllability properties, the mostly used tool remains the Lie algebra rank condition. In this paper, we develop alternative approaches based on theory and techniques in combinatorics to study controllability of bilinear systems. The core idea of our methodology is to represent vector fields of a bilinear system by permutations or graphs, so that Lie brackets are represented by permutation multiplications or graph operations, respectively. Following these representations, we derive combinatorial characterization of controllability for bilinear systems, which consequently provides novel applications of symmetric group and graph theory to control theory. Moreover, the developed combinatorial approaches are compatible with Lie algebra decompositions, including the Cartan and non-intertwining decomposition. This compatibility enables the exploitation of representation theory for analyzing controllability, which allows us to characterize controllability properties of bilinear systems governed by semisimple and reductive Lie algebras.

math.OC↗

arXiv2020

Cross-Correlation of Far-Infrared Background Anisotropies and CMB Lensing from Herschel and Planck satellites

The cosmic infrared background (CIB) anisotropies and cosmic microwave background (CMB) lensing are powerful measurements for exploring the cosmological and astrophysical problems. In this work, we measure the auto-correlation power spectrum of the CIB anisotropies in the Herschel-SPIRE HerMES Large Mode Survey (HeLMS) field, and the cross power spectrum with the CMB lensing measurements from the Planck satellite. The HeLMS field covers more than 270 deg^2, which is much larger than the previous analysis. We use the Herschel Level 1 time stream data to merge the CIB maps at 250, 350, and 500 um bands, and mask the areas where the flux is greater than 3-sigma (~50 mJy/beam) or no measured data. We obtain the final CIB power spectra at 100<ell<20000 by considering several effects, such as beam function, mode coupling, transfer function, and so on. We also calculate the theoretical CIB auto- and cross-power spectra of CIB and CMB lensing by assuming that the CIB emissivity follows Gaussian distribution in redshift. We find that, for the CIB auto power spectra, we obtain the signal to noise ratio (SNR) of 15.9, 15.7, and 15.3 at 250, 350, and 500 um, and for the CIBxCMB lensing power spectra, SNR of 7.5, 7.0, and 6.2 at 250, 350, and 500 um, respectively. Comparing to previous works, the constraints on the relevant CIB parameters are improved by factors of 2~5 in this study.

astro-ph.CO↗

arXiv2020

Testing interacting dark matter and dark energy model with cosmological data

We investigate the model of dark matter-dark energy (DM-DE) interaction with coupling strength proportional to the multiplication of dark sector densities with different power indices $Q = γρ_{\rm c}^α ρ_{\rm d}^β$. We first investigate the modification of the cosmic expansion history, and then further develop the formalism to take into account the cosmological perturbations and dark matter temperature evolution. We then use the latest observational cosmology data, including cosmic microwave background (CMB) data, baryon acoustic oscillations (BAO) data, redshift-space distortion (RSD) data and Type Ia supernovae (SNe) data to constrain the model parameters. We find in the phantom region, a positive $α$ is preferred by the data above $2\, σ$ statistic significance. If we choose the power indices to be integers or half-integers for {\it plausible} physics of particle interaction, the allowed values within $1\, σ$ confidence regions are $α= 0.5$ and $β= 0, 0.5, 1$. The inclusion of BAO and RSD data from large-scale structure and SNe data improves the constraints significantly. Our model predicts lower values of $f(z) σ_8(z)$ at $z<1$ comparing to $Λ$CDM model, which alleviates the tension of $Λ$CDM with various RSD data from optical galaxy surveys. Overall, the DM-DE interaction model is consistent with the current observational data, especially providing a better fit to the RSD data.

astro-ph.CO↗

arXiv2020

Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities

Remote sensing image scene classification, which aims at labeling remote sensing images with a set of semantic categories based on their contents, has broad applications in a range of fields. Propelled by the powerful feature learning capabilities of deep neural networks, remote sensing image scene classification driven by deep learning has drawn remarkable attention and achieved significant breakthroughs. However, to the best of our knowledge, a comprehensive review of recent achievements regarding deep learning for scene classification of remote sensing images is still lacking. Considering the rapid evolution of this field, this paper provides a systematic survey of deep learning methods for remote sensing image scene classification by covering more than 160 papers. To be specific, we discuss the main challenges of remote sensing image scene classification and survey (1) Autoencoder-based remote sensing image scene classification methods, (2) Convolutional Neural Network-based remote sensing image scene classification methods, and (3) Generative Adversarial Network-based remote sensing image scene classification methods. In addition, we introduce the benchmarks used for remote sensing image scene classification and summarize the performance of more than two dozen of representative algorithms on three commonly-used benchmark data sets. Finally, we discuss the promising opportunities for further research.

cs.CV↗

arXiv2020

Neural Entity Summarization with Joint Encoding and Weak Supervision

In a large-scale knowledge graph (KG), an entity is often described by a large number of triple-structured facts. Many applications require abridged versions of entity descriptions, called entity summaries. Existing solutions to entity summarization are mainly unsupervised. In this paper, we present a supervised approach NEST that is based on our novel neural model to jointly encode graph structure and text in KGs and generate high-quality diversified summaries. Since it is costly to obtain manually labeled summaries for training, our supervision is weak as we train with programmatically labeled data which may contain noise but is free of manual work. Evaluation results show that our approach significantly outperforms the state of the art on two public benchmarks.

cs.CL↗

arXiv2020

Enriching Documents with Compact, Representative, Relevant Knowledge Graphs

A prominent application of knowledge graph (KG) is document enrichment. Existing methods identify mentions of entities in a background KG and enrich documents with entity types and direct relations. We compute an entity relation subgraph (ERG) that can more expressively represent indirect relations among a set of mentioned entities. To find compact, representative, and relevant ERGs for effective enrichment, we propose an efficient best-first search algorithm to solve a new combinatorial optimization problem that achieves a trade-off between representativeness and compactness, and then we exploit ontological knowledge to rank ERGs by entity-based document-KG and intra-KG relevance. Extensive experiments and user studies show the promising performance of our approach.

cs.AI↗

arXiv2020

SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases

Semantic parsing transforms a natural language question into a formal query over a knowledge base. Many existing methods rely on syntactic parsing like dependencies. However, the accuracy of producing such expressive formalisms is not satisfying on long complex questions. In this paper, we propose a novel skeleton grammar to represent the high-level structure of a complex question. This dedicated coarse-grained formalism with a BERT-based parsing algorithm helps to improve the accuracy of the downstream fine-grained semantic parsing. Besides, to align the structure of a question with the structure of a knowledge base, our multi-strategy method combines sentence-level and word-level semantics. Our approach shows promising performance on several datasets.

cs.CL↗

arXiv2020

ESBM: An Entity Summarization BenchMark

Entity summarization is the problem of computing an optimal compact summary for an entity by selecting a size-constrained subset of triples from RDF data. Entity summarization supports a multiplicity of applications and has led to fruitful research. However, there is a lack of evaluation efforts that cover the broad spectrum of existing systems. One reason is a lack of benchmarks for evaluation. Some benchmarks are no longer available, while others are small and have limitations. In this paper, we create an Entity Summarization BenchMark (ESBM) which overcomes the limitations of existing benchmarks and meets standard desiderata for a benchmark. Using this largest available benchmark for evaluating general-purpose entity summarizers, we perform the most extensive experiment to date where 9~existing systems are compared. Considering that all of these systems are unsupervised, we also implement and evaluate a supervised learning based system for reference.

cs.IR↗

arXiv2020

DeepLENS: Deep Learning for Entity Summarization

Entity summarization has been a prominent task over knowledge graphs. While existing methods are mainly unsupervised, we present DeepLENS, a simple yet effective deep learning model where we exploit textual semantics for encoding triples and we score each candidate triple based on its interdependence on other triples. DeepLENS significantly outperformed existing methods on a public benchmark.

cs.IR↗

arXiv2020

Relaxing Relationship Queries on Graph Data

In many domains we have witnessed the need to search a large entity-relation graph for direct and indirect relationships between a set of entities specified in a query. A search result, called a semantic association (SA), is typically a compact (e.g., diameter-constrained) connected subgraph containing all the query entities. For this problem of SA search, efficient algorithms exist but will return empty results if some query entities are distant in the graph. To reduce the occurrence of failing query and provide alternative results, we study the problem of query relaxation in the context of SA search. Simply relaxing the compactness constraint will sacrifice the compactness of an SA, and more importantly, may lead to performance issues and be impracticable. Instead, we focus on removing the smallest number of entities from the original failing query, to form a maximum successful sub-query which minimizes the loss of result quality caused by relaxation. We prove that verifying the success of a sub-query turns into finding an entity (called a certificate) that satisfies a distance-based condition about the query entities. To efficiently find a certificate of the success of a maximum sub-query, we propose a best-first search algorithm that leverages distance-based estimation to effectively prune the search space. We further improve its performance by adding two fine-grained heuristics: one based on degree and the other based on distance. Extensive experiments over popular RDF datasets demonstrate the efficiency of our algorithm, which is more scalable than baselines.

cs.IR↗

arXiv2020

Parameter sensitivity analysis of dynamic ice sheet models

The velocity field and the height at the surface of a dynamic ice sheet are observed. The ice sheets are modeled by the full Stokes equations and shallow shelf/shelfy stream approximations. Time dependence is introduced by a kinematic free surface equation which updates the surface elevation using the velocity solution. The sensitivity of the observed quantities at the ice surface to parameters in the models, for example the basal topography and friction coefficients, is analyzed by first deriving the time dependent adjoint equations. Using the adjoint solutions, the effect of a perturbation in a parameter is obtained showing the importance of including the time dependence, in particular when the height is observed. The adjoint equations are solved analytically and numerically and the sensitivity of the desired parameters is determined in several examples in two dimensions. A closed form of the analytical solutions to the adjoint equations is given for a two dimensional grounding line migration problem in steady state under the shallow shelf approximation.

physics.comp-ph↗

arXiv2019

Cosmological constraints on ultra-light axion fields

Ultra-light axions (ULAs) with mass less than 10^-20 eV have interesting behaviors that may contribute to either dark energy or dark matter at different epochs of the Universe. Its properties can be explored by cosmological observations, such as expansion history of the Universe, cosmic large-scale structure, cosmic microwave background, etc. In this work, we study the ULAs with a mass around 10^-33 eV, which means the ULA field still rolls slowly at present with the equation of state w=-1 as dark energy. In order to investigate the mass and other properties of this kind of ULA field, we adopt the measurements of Type Ia supernova (SN Ia), baryon acoustic oscillation (BAO), and Hubble parameter H(z). The Markov Chain Monte Carlo (MCMC) technique is employed to perform the constraints on the parameters. Finally, by exploring four cases of the model, we find that the mass of this ULA field is about 3x10^-33 eV if assuming the initial axion field phi_i=M_pl. We also investigate a general case by assuming phi_i< M_pl and find that the fitting results of phi_i/M_pl are consistent with or close to 1 for the datasets we use.

astro-ph.CO↗

arXiv2019

GREASE: A Generative Model for Relevance Search over Knowledge Graphs

Relevance search is to find top-ranked entities in a knowledge graph (KG) that are relevant to a query entity. Relevance is ambiguous, particularly over a schema-rich KG like DBpedia which supports a wide range of different semantics of relevance based on numerous types of relations and attributes. As users may lack the expertise to formalize the desired semantics, supervised methods have emerged to learn the hidden user-defined relevance from user-provided examples. Along this line, in this paper we propose a novel generative model over KGs for relevance search, named GREASE. The model applies to meta-path based relevance where a meta-path characterizes a particular type of semantics of relating the query entity to answer entities. It is also extended to support properties that constrain answer entities. Extensive experiments on two large-scale KGs demonstrate that GREASE has advanced the state of the art in effectiveness, expressiveness, and efficiency.

cs.IR↗

arXiv2019

Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark

Substantial efforts have been devoted more recently to presenting various methods for object detection in optical remote sensing images. However, the current survey of datasets and deep learning based methods for object detection in optical remote sensing images is not adequate. Moreover, most of the existing datasets have some shortcomings, for example, the numbers of images and object categories are small scale, and the image diversity and variations are insufficient. These limitations greatly affect the development of deep learning based object detection methods. In the paper, we provide a comprehensive review of the recent deep learning based object detection progress in both the computer vision and earth observation communities. Then, we propose a large-scale, publicly available benchmark for object DetectIon in Optical Remote sensing images, which we name as DIOR. The dataset contains 23463 images and 192472 instances, covering 20 object classes. The proposed DIOR dataset 1) is large-scale on the object categories, on the object instance number, and on the total image number; 2) has a large range of object size variations, not only in terms of spatial resolutions, but also in the aspect of inter- and intra-class size variability across objects; 3) holds big variations as the images are obtained with different imaging conditions, weathers, seasons, and image quality; and 4) has high inter-class similarity and intra-class diversity. The proposed benchmark can help the researchers to develop and validate their data-driven methods. Finally, we evaluate several state-of-the-art approaches on our DIOR dataset to establish a baseline for future research.

cs.CV↗

arXiv2019

A full Stokes subgrid model for simulation of grounding line migration in ice sheets

The full Stokes equations are solved by a finite element method for simulation of large ice sheets and glaciers. The simulation is particularly sensitive to the discretization of the grounding line which separates the ice resting on the bedrock and the ice floating on water and is moving in time. The boundary conditions at the ice base are enforced by Nitsche's method and a subgrid treatment of the elements in the discretization close to the grounding line. Simulations with the method in two dimensions for an advancing and a retreating grounding line illustrate the performance of the method. It is implemented in the two dimensional version of the open source code Elmer/ICE.

physics.comp-ph↗