BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Nian Liu

Nian Liu appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Computer VisionMachine Learningcond-mat.stat-mechArtificial Intelligenceastro-ph.IMastro-ph.SRComputationcond-mat.mtrl-scimath.OC

Catalog footprint

What is connected

13works
9topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

13 published item(s)

preprint2026arXiv

Permutation-preserving Functions and Neural Vecchia Covariance Kernels

We introduce a novel framework for constructing scalable and flexible covariance kernels for Gaussian processes (GPs) by directly learning the covariance structure under a regression-type parameterization induced by Vecchia approximations, using deep neural architectures. Specifically, we model kriging coefficients and conditional standard deviations, deterministic quantities that uniquely characterize the covariance, providing stable and informative learning targets. Exploiting the permutation-equivariant structure of conditioning sets in the Vecchia factorization, we derive a universal representation for permutation-preserving functions and design neural architectures that respect this symmetry, leading to improved training stability and data efficiency. The proposed approach enables expressive, non-stationary kernel learning while maintaining computational scalability, thereby bridging classical GP methodology with modern deep learning.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retraining

Cross-domain few-shot segmentation (CD-FSS) aims to segment objects of novel classes in new domains, which is often challenging due to the diverse characteristics of target domains and the limited availability of support data. Most CD-FSS methods redesign and retrain in-domain FSS models using abundant base data from the source domain, which are effective but costly to train. To address these issues, we propose adapting informative model structures of the well-trained FSS model for target domains by learning domain characteristics from few-shot labeled support samples during inference, thereby eliminating the need for source domain retraining. Specifically, we first adaptively identify domain-specific model structures by measuring parameter importance using a novel structure Fisher score in a data-dependent manner. Then, we progressively train the selected informative model structures with hierarchically constructed training samples, progressing from fewer to more support shots. The resulting Informative Structure Adaptation (ISA) method effectively addresses domain shifts and equips existing well-trained in-domain FSS models with flexible adaptation capabilities for new domains, eliminating the need to redesign or retrain CD-FSS models on base data. Extensive experiments validate the effectiveness of our method, demonstrating superior performance across multiple CD-FSS benchmarks. Codes are at https://github.com/fanq15/ISA.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Compact Graph Structure Learning via Mutual Information Compression

Graph Structure Learning (GSL) recently has attracted considerable attentions in its capacity of optimizing graph structure as well as learning suitable parameters of Graph Neural Networks (GNNs) simultaneously. Current GSL methods mainly learn an optimal graph structure (final view) from single or multiple information sources (basic views), however the theoretical guidance on what is the optimal graph structure is still unexplored. In essence, an optimal graph structure should only contain the information about tasks while compress redundant noise as much as possible, which is defined as "minimal sufficient structure", so as to maintain the accurancy and robustness. How to obtain such structure in a principled way? In this paper, we theoretically prove that if we optimize basic views and final view based on mutual information, and keep their performance on labels simultaneously, the final view will be a minimal sufficient structure. With this guidance, we propose a Compact GSL architecture by MI compression, named CoGSL. Specifically, two basic views are extracted from original graph as two inputs of the model, which are refinedly reestimated by a view estimator. Then, we propose an adaptive technique to fuse estimated views into the final view. Furthermore, we maintain the performance of estimated views and the final view and reduce the mutual information of every two views. To comprehensively evaluate the performance of CoGSL, we conduct extensive experiments on several datasets under clean and attacked conditions, which demonstrate the effectiveness and robustness of CoGSL.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Debiased Graph Neural Networks with Agnostic Label Selection Bias

Most existing Graph Neural Networks (GNNs) are proposed without considering the selection bias in data, i.e., the inconsistent distribution between the training set with test set. In reality, the test data is not even available during the training process, making selection bias agnostic. Training GNNs with biased selected nodes leads to significant parameter estimation bias and greatly impacts the generalization ability on test nodes. In this paper, we first present an experimental investigation, which clearly shows that the selection bias drastically hinders the generalization ability of GNNs, and theoretically prove that the selection bias will cause the biased estimation on GNN parameters. Then to remove the bias in GNN estimation, we propose a novel Debiased Graph Neural Networks (DGNN) with a differentiated decorrelation regularizer. The differentiated decorrelation regularizer estimates a sample weight for each labeled node such that the spurious correlation of learned embeddings could be eliminated. We analyze the regularizer in causal view and it motivates us to differentiate the weights of the variables based on their contribution on the confounding bias. Then, these sample weights are used for reweighting GNNs to eliminate the estimation bias, thus help to improve the stability of prediction on unknown test nodes. Comprehensive experiments are conducted on several challenging graph datasets with two kinds of label selection biases. The results well verify that our proposed model outperforms the state-of-the-art methods and DGNN is a flexible framework to enhance existing GNNs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning Non-target Knowledge for Few-shot Semantic Segmentation

Existing studies in few-shot semantic segmentation only focus on mining the target object information, however, often are hard to tell ambiguous regions, especially in non-target regions, which include background (BG) and Distracting Objects (DOs). To alleviate this problem, we propose a novel framework, namely Non-Target Region Eliminating (NTRE) network, to explicitly mine and eliminate BG and DO regions in the query. First, a BG Mining Module (BGMM) is proposed to extract the BG region via learning a general BG prototype. To this end, we design a BG loss to supervise the learning of BGMM only using the known target object segmentation ground truth. Then, a BG Eliminating Module and a DO Eliminating Module are proposed to successively filter out the BG and DO information from the query feature, based on which we can obtain a BG and DO-free target object segmentation result. Furthermore, we propose a prototypical contrastive learning algorithm to improve the model ability of distinguishing the target object from DOs. Extensive experiments on both PASCAL-5i and COCO-20i datasets show that our approach is effective despite its simplicity.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Salient Object Detection via Integrity Learning

Although current salient object detection (SOD) works have achieved significant progress, they are limited when it comes to the integrity of the predicted salient regions. We define the concept of integrity at both a micro and macro level. Specifically, at the micro level, the model should highlight all parts that belong to a certain salient object. Meanwhile, at the macro level, the model needs to discover all salient objects in a given image. To facilitate integrity learning for SOD, we design a novel Integrity Cognition Network (ICON), which explores three important components for learning strong integrity features. 1) Unlike existing models, which focus more on feature discriminability, we introduce a diverse feature aggregation (DFA) component to aggregate features with various receptive fields (i.e., kernel shape and context) and increase feature diversity. Such diversity is the foundation for mining the integral salient objects. 2) Based on the DFA features, we introduce an integrity channel enhancement (ICE) component with the goal of enhancing feature channels that highlight the integral salient objects, while suppressing the other distracting ones. 3) After extracting the enhanced features, the part-whole verification (PWV) method is employed to determine whether the part and whole object features have strong agreement. Such part-whole agreements can further improve the micro-level integrity for each salient object. To demonstrate the effectiveness of our ICON, comprehensive experiments are conducted on seven challenging benchmarks. Our ICON outperforms the baseline methods in terms of a wide range of metrics. Notably, our ICON achieves about 10% relative improvement over the previous best model in terms of average false negative ratio (FNR), on six datasets. Codes and results are available at: https://github.com/mczhuge/ICON.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Stochastic Adaptive Linear Quadratic Differential Games

Game theory is playing more and more important roles in understanding complex systems and in investigating intelligent machines with various uncertainties. As a starting point, we consider the classical two-player zero-sum linear-quadratic stochastic differential games, but in contrast to most of the existing studies, the coefficient matrices of the systems are assumed to be unknown to both players, and consequently it is necessary to study adaptive strategies of the players, which may be termed as adaptive games and which has rarely been explored in the literature. In this paper, it will be shown that the adaptive strategies of both players can be constructed by the combined use of a weighted least squares (WLS) estimation algorithm, a random regularization method and a diminishing excitation method. Under almost the same structural conditions as those in the traditional known parameters case, we will show that the closed-loop adaptive game systems will be globally stable and asymptotically reaches the Nash equilibrium as the time tends to infinity.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Structured Attention Composition for Temporal Action Localization

Temporal action localization aims at localizing action instances from untrimmed videos. Existing works have designed various effective modules to precisely localize action instances based on appearance and motion features. However, by treating these two kinds of features with equal importance, previous works cannot take full advantage of each modality feature, making the learned model still sub-optimal. To tackle this issue, we make an early effort to study temporal action localization from the perspective of multi-modality feature learning, based on the observation that different actions exhibit specific preferences to appearance or motion modality. Specifically, we build a novel structured attention composition module. Unlike conventional attention, the proposed module would not infer frame attention and modality attention independently. Instead, by casting the relationship between the modality attention and the frame attention as an attention assignment process, the structured attention composition module learns to encode the frame-modality structure and uses it to regularize the inferred frame attention and modality attention, respectively, upon the optimal transport theory. The final frame-modality attention is obtained by the composition of the two individual attentions. The proposed structured attention composition module can be deployed as a plug-and-play module into existing action localization frameworks. Extensive experiments on two widely used benchmarks show that the proposed structured attention composition consistently improves four state-of-the-art temporal action localization methods and builds new state-of-the-art performance on THUMOS14. Code is availabel at https://github.com/VividLe/Structured-Attention-Composition.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection

Traditional saliency models usually adopt hand-crafted image features and human-designed mechanisms to calculate local or global contrast. In this paper, we propose a novel computational saliency model, i.e., deep spatial contextual long-term recurrent convolutional network (DSCLRCN) to predict where people looks in natural scenes. DSCLRCN first automatically learns saliency related local features on each image location in parallel. Then, in contrast with most other deep network based saliency models which infer saliency in local contexts, DSCLRCN can mimic the cortical lateral inhibition mechanisms in human visual system to incorporate global contexts to assess the saliency of each image location by leveraging the deep spatial long short-term memory (DSLSTM) model. Moreover, we also integrate scene context modulation in DSLSTM for saliency inference, leading to a novel deep spatial contextual LSTM (DSCLSTM) model. The whole network can be trained end-to-end and works efficiently when testing. Experimental results on two benchmark datasets show that DSCLRCN can achieve state-of-the-art performance on saliency detection. Furthermore, the proposed DSCLSTM model can significantly boost the saliency detection performance by incorporating both global spatial interconnections and scene context modulation, which may uncover novel inspirations for studies on them in computational saliency models.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Efficiency at maximum power of thermochemical engines with near-independent particles

Two-reservoir thermochemical engines are established in by using near-independent particles (including Maxwell-Boltzmann, Fermi-Dirac, and Bose-Einstein particles) as the working substance. Particle and heat fluxes can be formed based on the temperature and chemical potential gradients between two different reservoirs. A rectangular-type energy filter with width $Γ$ is introduced for each engine to weaken the coupling between the particle and heat fluxes. The efficiency at maximum power of each particle system decreases monotonously from an upper bound $η^+$ to a lower bound $η^-$ when $Γ$ increases from 0 to $\infty$. It is found that the $η^+$ values for all three systems are bounded by $η_{\mathrm{C}}/2 \leq η^+ \leq η_{\mathrm{C}}/(2-η_{\mathrm{C}})$ due to strong coupling, where $η_{\mathrm{C}}$ is the Carnot efficiency. For the Bose-Einstein system, it is found that the upper bound is approximated by the Curzon-Ahlborn efficiency: $η_{\mathrm{CA}}=1-\sqrt{1-η_{\mathrm{C}}}$. When $Γ\rightarrow\infty$, the intrinsic maximum powers are proportional to the square of the temperature difference of two reservoirs for all three systems, and the corresponding lower bounds of efficiency at maximum power can be simplified in the same form of $η^{-}=η_{\mathrm{C}}/[1+a_0(2-η_{\mathrm{C}})]$.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Footprints of the weak s-process in the carbon-enhanced metal-poor star ET0097

Historically, the weak s-process contribution to metal-poor stars is thought to be extremely small, due to the effect of the secondary-like nature of the neutron source 22Ne(a;n)25Mg in massive stars, which means that metal-poor weak s-process stars could not be found. ET0097 is the first observed carbon-enhanced metal-poor (CEMP) star in the Sculptor dwarf spheroidal galaxy. Because C is enriched and the elements heavier than Ba are not overabundant, ET0097 can be classified as a CEMP-no star. However, this star shows overabundances of lighter n-capture elements (i.e., Sr, Y and Zr). In this work, having adopted the abundance decomposition approach, we investigate the astrophysical origins of the elements in ET0097. We find that the light elements and iron-peak elements (from O to Zn) of the star mainly originate from the primary process of massive stars and the heavier n-capture elements (heavier than Ba) mainly come from the main r-process. However, the lighter n-capture elements such as Sr, Y and Zr should mainly come from the primary weak s-process. The contributed fractions of the primary weak s-process to the Sr, Y and Zr abundances of ET0097 are about 82%, 84% and 58% respectively, suggesting that the CEMP star ET0097 should have the footprints of the weak s-process. The derived result should be a significant evidence that the weak s-process elements can be produced in metal-poor massive stars.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

A theoretical study on the performances of thermoelectric heat engine and refrigerator with two-dimensional electron reservoirs

Theoretical thermoelectric nanophysics models of low-dimensional electronic heat engine and refrigerator devices, comprising two-dimensional hot and cold reservoirs and an interconnecting filtered electron transport mechanism have been established. The models were used to numerically simulate and evaluate the thermoelectric performance and energy conversion efficiencies of these low-dimensional devices, based on three different types of electron transport momentum-dependent filters, referred to herein as: kx, ky and kr filters. Assuming the Fermi-Dirac distribution of electrons, expressions for key thermoelectric performance parameters were derived for the resonant transport processes, in which the transmission of electrons has been approximated as a Lorentzian resonance function. Optimizations were carried out and the corresponding optimized design parameters have been determined, including but not limited to the universal theoretical upper bound of the efficiency at maximum power for heat engines, and the maximum coefficient of performance for refrigerators. From the results, it was determined that kr filter delivers the best thermoelectric performance, followed by the kx filter, and then the ky filter. For refrigerators with any one of three filters, an optimum range for the full width at half maximum of the transport resonance was found to be <2kT .

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

The site conditions of the Guo Shou Jing Telescope

The weather at Xinglong Observing Station, where the Guo Shou Jing Telescope (GSJT) is located, is strongly affected by the monsoon climate in north-east China. The LAMOST survey strategy is constrained by these weather patterns. In this paper, we present a statistics on observing hours from 2004 to 2007, and the sky brightness, seeing, and sky transparency from 1995 to 2011 at the site. We investigate effects of the site conditions on the survey plan. Operable hours each month shows strong correlation with season: on average there are 8 operable hours per night available in December, but only 1-2 hours in July and August. The seeing and the sky transparency also vary with seasons. Although the seeing is worse in windy winters, and the atmospheric extinction is worse in the spring and summer, the site is adequate for the proposed scientific program of LAMOST survey. With a Monte Carlo simulation using historical data on the site condition, we find that the available observation hours constrain the survey footprint from 22h to 16h in right ascension; the sky brightness allows LAMOST to obtain the limit magnitude of V = 19.5mag with S/N = 10.

0 citations0 reviewsNo code linkedOpen access