arXiv subjects

Zhu Zhang

Publications and source records attributed to Zhu Zhang.

52 records · Page 3Linked to original sources

arXiv2021

Validity of Prandtl expansions for steady MHD in the Sobolev framework

This paper is concerned with the vanishing viscosity and magnetic resistivity limit for the two-dimensional steady incompressible MHD system on the half plane with no-slip boundary condition on velocity field and perfectly conducting wall condition on magnetic field. We prove the nonlinear stability of shear flows of Prandtl type with nondegenerate tangential magnetic field, but without any positivity or monotonicity assumption on the velocity field. It is in sharp contrast to the steady Navier-Stokes equations and reflects the stabilization effect of magnetic field. Unlike the unsteady MHD system, we manage the degeneracy on the boundary caused by no-slip boundary condition and obtain the estimates of solutions by introducing an intrinsic weight function and some good auxiliary functions.

math.AP↗

arXiv2021

Regulating Aggregation of Colloidal Particles in an Electro-Osmotic Micropump

Unrestricted particle transport through microfluidic channels is of paramount importance to a wide range of applications, including lab-on-a-chip devices. In this article, we study using video microscopy the electro-osmotic aggregation of colloidal particles at the opening of a micrometer-sized silica channel in presence of a salt gradient. Particle aggregation eventually leads to clogging of the channel, which may be undone by a time-adjusted reversal of the applied electric potential. We numerically model our system via the Stokes-Poisson-Nernst-Planck equations in a geometry that approximates the real sample. This allows us to identify the transport processes induced by the electric field and salt gradient and to provide evidence that a balance thereof leads to aggregation. We further demonstrate experimentally that a net flow of colloids through the channel may be achieved by applying a square-waveform electric potential with an appropriately tuned duty cycle. Our results serve to guide the design of microfluidic and nanofluidic pumps that allow for controlled particle transport and provide new insights for anti-fouling in ultra-filtration.

cond-mat.soft↗

arXiv2020

RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems

For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various styles, modalities or domains. In pursuit of these goals, we introduce the RADDLE benchmark, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. By including tasks with limited training data, RADDLE is designed to favor and encourage models with a strong generalization ability. RADDLE also includes a diagnostic checklist that facilitates detailed robustness analysis in aspects such as language variations, speech errors, unseen entities, and out-of-domain utterances. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain. Overall, existing models are less than satisfactory in robustness evaluation, which suggests opportunities for future improvement.

cs.CL↗

arXiv2020

Object-Aware Multi-Branch Relation Networks for Spatio-Temporal Video Grounding

Spatio-temporal video grounding aims to retrieve the spatio-temporal tube of a queried object according to the given sentence. Currently, most existing grounding methods are restricted to well-aligned segment-sentence pairs. In this paper, we explore spatio-temporal video grounding on unaligned data and multi-form sentences. This challenging task requires to capture critical object relations to identify the queried target. However, existing approaches cannot distinguish notable objects and remain in ineffective relation modeling between unnecessary objects. Thus, we propose a novel object-aware multi-branch relation network for object-aware relation discovery. Concretely, we first devise multiple branches to develop object-aware region modeling, where each branch focuses on a crucial object mentioned in the sentence. We then propose multi-branch relation reasoning to capture critical object relationships between the main branch and auxiliary branches. Moreover, we apply a diversity loss to make each branch only pay attention to its corresponding object and boost multi-branch learning. The extensive experiments show the effectiveness of our proposed method.

cs.CV↗

arXiv2020

Regularized Two-Branch Proposal Networks for Weakly-Supervised Moment Retrieval in Videos

Video moment retrieval aims to localize the target moment in an video according to the given sentence. The weak-supervised setting only provides the video-level sentence annotations during training. Most existing weak-supervised methods apply a MIL-based framework to develop inter-sample confrontment, but ignore the intra-sample confrontment between moments with semantically similar contents. Thus, these methods fail to distinguish the target moment from plausible negative moments. In this paper, we propose a novel Regularized Two-Branch Proposal Network to simultaneously consider the inter-sample and intra-sample confrontments. Concretely, we first devise a language-aware filter to generate an enhanced video stream and a suppressed video stream. We then design the sharable two-branch proposal module to generate positive proposals from the enhanced stream and plausible negative proposals from the suppressed one for sufficient confrontment. Further, we apply the proposal regularization to stabilize the training process and improve model performance. The extensive experiments show the effectiveness of our method. Our code is released at here.

cs.CV↗

arXiv2020

Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences

In this paper, we consider a novel task, Spatio-Temporal Video Grounding for Multi-Form Sentences (STVG). Given an untrimmed video and a declarative/interrogative sentence depicting an object, STVG aims to localize the spatio-temporal tube of the queried object. STVG has two challenging settings: (1) We need to localize spatio-temporal object tubes from untrimmed videos, where the object may only exist in a very small segment of the video; (2) We deal with multi-form sentences, including the declarative sentences with explicit objects and interrogative sentences with unknown objects. Existing methods cannot tackle the STVG task due to the ineffective tube pre-generation and the lack of object relationship modeling. Thus, we then propose a novel Spatio-Temporal Graph Reasoning Network (STGRN) for this task. First, we build a spatio-temporal region graph to capture the region relationships with temporal object dynamics, which involves the implicit and explicit spatial subgraphs in each frame and the temporal dynamic subgraph across frames. We then incorporate textual clues into the graph and develop the multi-step cross-modal graph reasoning. Next, we introduce a spatio-temporal localizer with a dynamic selection method to directly retrieve the spatio-temporal tubes without tube pre-generation. Moreover, we contribute a large-scale video grounding dataset VidSTG based on video relation dataset VidOR. The extensive experiments demonstrate the effectiveness of our method.

cs.CV↗

arXiv2020

Weakly-Supervised Video Moment Retrieval via Semantic Completion Network

Video moment retrieval is to search the moment that is most relevant to the given natural language query. Existing methods are mostly trained in a fully-supervised setting, which requires the full annotations of temporal boundary for each query. However, manually labeling the annotations is actually time-consuming and expensive. In this paper, we propose a novel weakly-supervised moment retrieval framework requiring only coarse video-level annotations for training. Specifically, we devise a proposal generation module that aggregates the context information to generate and score all candidate proposals in one single pass. We then devise an algorithm that considers both exploitation and exploration to select top-K proposals. Next, we build a semantic completion module to measure the semantic similarity between the selected proposals and query, compute reward and provide feedbacks to the proposal generation module for scoring refinement. Experiments on the ActivityCaptions and Charades-STA demonstrate the effectiveness of our proposed method.

cs.CV↗

arXiv2019

Cross-Modal Interaction Networks for Query-Based Moment Retrieval in Videos

Query-based moment retrieval aims to localize the most relevant moment in an untrimmed video according to the given natural language query. Existing works often only focus on one aspect of this emerging task, such as the query representation learning, video context modeling or multi-modal fusion, thus fail to develop a comprehensive system for further performance improvement. In this paper, we introduce a novel Cross-Modal Interaction Network (CMIN) to consider multiple crucial factors for this challenging task, including (1) the syntactic structure of natural language queries; (2) long-range semantic dependencies in video context and (3) the sufficient cross-modal interaction. Specifically, we devise a syntactic GCN to leverage the syntactic structure of queries for fine-grained representation learning, propose a multi-head self-attention to capture long-range semantic dependencies from video context, and next employ a multi-stage cross-modal interaction to explore the potential relations of video and query contents. The extensive experiments demonstrate the effectiveness of our proposed method.

cs.IR↗

arXiv2019

Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks

Open-ended video question answering aims to automatically generate the natural-language answer from referenced video contents according to the given question. Currently, most existing approaches focus on short-form video question answering with multi-modal recurrent encoder-decoder networks. Although these works have achieved promising performance, they may still be ineffectively applied to long-form video question answering due to the lack of long-range dependency modeling and the suffering from the heavy computational cost. To tackle these problems, we propose a fast Hierarchical Convolutional Self-Attention encoder-decoder network(HCSA). Concretely, we first develop a hierarchical convolutional self-attention encoder to efficiently model long-form video contents, which builds the hierarchical structure for video sequences and captures question-aware long-range dependencies from video context. We then devise a multi-scale attentive decoder to incorporate multi-layer video representations for answer generation, which avoids the information missing of the top encoder layer. The extensive experiments show the effectiveness and efficiency of our method.

cs.CV↗

arXiv2019

Localizing Unseen Activities in Video via Image Query

Action localization in untrimmed videos is an important topic in the field of video understanding. However, existing action localization methods are restricted to a pre-defined set of actions and cannot localize unseen activities. Thus, we consider a new task to localize unseen activities in videos via image queries, named Image-Based Activity Localization. This task faces three inherent challenges: (1) how to eliminate the influence of semantically inessential contents in image queries; (2) how to deal with the fuzzy localization of inaccurate image queries; (3) how to determine the precise boundaries of target segments. We then propose a novel self-attention interaction localizer to retrieve unseen activities in an end-to-end fashion. Specifically, we first devise a region self-attention method with relative position encoding to learn fine-grained image region representations. Then, we employ a local transformer encoder to build multi-step fusion and reasoning of image and video contents. We next adopt an order-sensitive localizer to directly retrieve the target segment. Furthermore, we construct a new dataset ActivityIBAL by reorganizing the ActivityNet dataset. The extensive experiments show the effectiveness of our method.

cs.CV↗

arXiv2018

The Boltzmann equation with time-periodic boundary temperature

This paper is concerned with the boundary-value problem on the Boltzmann equation in bounded domains with diffuse-reflection boundary where the boundary temperature is time-periodic. We establish the existence of time-periodic solutions with the same period for both hard and soft potentials, provided that the time-periodic boundary temperature is sufficiently close to a stationary one which has small variations around a positive constant. The dynamical stability of time-periodic profiles is also proved under small perturbations, and this in turn yields the non-negativity of the profile. For the proof, we develop new estimates in the time-periodic setting.

math.AP↗

arXiv2018

Effects of soft interaction and non-isothermal boundary upon long-time dynamics of rarefied gas

In the paper, assuming that the motion of rarefied gases in a bounded domain is governed by the angular cutoff Boltzmann equation with diffuse reflection boundary, we study the effects of both soft intermolecular interaction and non-isothermal wall temperature upon the long-time dynamics of solutions to the corresponding initial boundary value problem. Specifically, we are devoted to proving the existence and dynamical stability of stationary solutions whenever the boundary temperature has suitably small variations around a positive constant. For the proof of existence, we introduce a new mild formulation of solutions to the steady boundary-value problem along the speeded backward bicharacteristic, and develop the uniform estimates on approximate solutions in both $L^2$ and $L^\infty$. Such mild formulation proves to be useful for treating the steady problem with soft potentials even over unbounded domains. In showing the dynamical stability, a new point is that we can obtain the sub-exponential time-decay rate in $L^\infty$ without losing any velocity weight, which is actually quite different from the classical results as in [11,43] for the torus domain and essentially due to the diffuse reflection boundary and the boundedness of the domain.

math.AP↗

arXiv2018

Ion-acoustic shock in a collisional plasma

The paper is concerned with the propagation of ion-acoustic shock waves in a collision dominated plasma. We firstly establish the existence and uniqueness of a small-amplitude smooth travelling wave, then justify its approximation to the shock profile of the KdV-Burgers equations in a suitable asymptotic regime where dissipation in terms of viscosity coefficient is much stronger than dispersion by the Debye length, and prove in the end the large time asymptotic stability of travelling waves under suitably small smooth perturbations.

math.AP↗

arXiv2018

Instability in a Vlasov-Fokker-Planck binary mixture

This paper is concerned with a kinetic model of a Vlasov-Fokker-Planck system used to describe the evolution of two species of particles interacting through a potential and a thermal reservoir at given temperature. We prove that at low temperature, the homogeneous equilibrium is dynamically unstable under certain perturbations. Our work is motivated by a problem arising in \cite{EGM1}.

math.AP↗

arXiv2013

A Statistical Learning Based System for Fake Website Detection

Existing fake website detection systems are unable to effectively detect fake websites. In this study, we advocate the development of fake website detection systems that employ classification methods grounded in statistical learning theory (SLT). Experimental results reveal that a prototype system developed using SLT-based methods outperforms seven existing fake website detection systems on a test bed encompassing 900 real and fake websites.

cs.CY↗

arXiv2013

A Random Walk Model for Item Recommendation in Folksonomies

Social tagging, as a novel approach to information organization and discovery, has been widely adopted in many Web2.0 applications. The tags provide a new type of information that can be exploited by recommender systems. Nevertheless, the sparsity of ternary interaction data limits the performance of tag-based collaborative filtering. This paper proposes a random-walk-based algorithm to deal with the sparsity problem in social tagging data, which captures the potential transitive associations between users and items through their interaction with tags. In particular, two smoothing strategies are presented from both the user-centric and item-centric perspectives. Experiments on real-world data sets empirically demonstrate the efficacy of the proposed algorithm.

cs.IR↗