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

Xi Peng

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

ResearcherUnclaimed source record
Computer VisionMachine LearningArtificial IntelligenceInformation Theorymath.ITNetworking and Internet Architecturenlin.PSphysics.opticsLogic in Computer Sciencemath.PRRobotics

Catalog footprint

What is connected

29works
11topics
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

29 published item(s)

preprint2026arXiv

Attention Transfer Is Not Universally Effective for Vision Transformers

A recent work shows that Attention Transfer, which transfers only the attention patterns from a pre-trained teacher Vision Transformer (ViT) to a randomly initialized standard student ViT, is sufficient to recover the full benefit of the teacher's pre-trained weights. We revisit this finding on a comprehensive benchmark of 20 teachers from 11 well-known ViT families and reveal that Attention Transfer is not universally effective. While 7 families transfer successfully, 4 consistently fail, falling up to 5.1\% below the from-scratch no-transfer baseline. Further results demonstrate that this failure is family-consistent across model sizes, and persists under extended training durations, different transfer datasets, and out-of-distribution evaluations. Controlled analyses then consistently localize the problem to the attention-routing channel, indicating that the key issue is not whether the student can match the teacher's attention patterns, but whether the matched patterns remain functional for the student. Crucially, we identify architectural mismatch between the pre-trained teacher and the standard student as the primary mechanism. By adding only the teacher's native architectural components to the student in a randomly initialized state, we completely reverse the failure for all 4 families. Notably, these components alone do not improve from-scratch training, confirming that they specifically unlock the usability of the teacher's attention. We further systematically show that this failure is not explained by the inadequate choice of transfer loss or by differences in pre-training recipes. Our findings refine the prevailing understanding of attention in ViT representations: attention is sufficient \textit{only} when the student architecture matches the teacher.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

Cross-modal Active Complementary Learning with Self-refining Correspondence

Recently, image-text matching has attracted more and more attention from academia and industry, which is fundamental to understanding the latent correspondence across visual and textual modalities. However, most existing methods implicitly assume the training pairs are well-aligned while ignoring the ubiquitous annotation noise, a.k.a noisy correspondence (NC), thereby inevitably leading to a performance drop. Although some methods attempt to address such noise, they still face two challenging problems: excessive memorizing/overfitting and unreliable correction for NC, especially under high noise. To address the two problems, we propose a generalized Cross-modal Robust Complementary Learning framework (CRCL), which benefits from a novel Active Complementary Loss (ACL) and an efficient Self-refining Correspondence Correction (SCC) to improve the robustness of existing methods. Specifically, ACL exploits active and complementary learning losses to reduce the risk of providing erroneous supervision, leading to theoretically and experimentally demonstrated robustness against NC. SCC utilizes multiple self-refining processes with momentum correction to enlarge the receptive field for correcting correspondences, thereby alleviating error accumulation and achieving accurate and stable corrections. We carry out extensive experiments on three image-text benchmarks, i.e., Flickr30K, MS-COCO, and CC152K, to verify the superior robustness of our CRCL against synthetic and real-world noisy correspondences.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Are Multimodal Transformers Robust to Missing Modality?

Multimodal data collected from the real world are often imperfect due to missing modalities. Therefore multimodal models that are robust against modal-incomplete data are highly preferred. Recently, Transformer models have shown great success in processing multimodal data. However, existing work has been limited to either architecture designs or pre-training strategies; whether Transformer models are naturally robust against missing-modal data has rarely been investigated. In this paper, we present the first-of-its-kind work to comprehensively investigate the behavior of Transformers in the presence of modal-incomplete data. Unsurprising, we find Transformer models are sensitive to missing modalities while different modal fusion strategies will significantly affect the robustness. What surprised us is that the optimal fusion strategy is dataset dependent even for the same Transformer model; there does not exist a universal strategy that works in general cases. Based on these findings, we propose a principle method to improve the robustness of Transformer models by automatically searching for an optimal fusion strategy regarding input data. Experimental validations on three benchmarks support the superior performance of the proposed method.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Description Logic EL++ Embeddings with Intersectional Closure

Many ontologies, in particular in the biomedical domain, are based on the Description Logic EL++. Several efforts have been made to interpret and exploit EL++ ontologies by distributed representation learning. Specifically, concepts within EL++ theories have been represented as n-balls within an n-dimensional embedding space. However, the intersectional closure is not satisfied when using n-balls to represent concepts because the intersection of two n-balls is not an n-ball. This leads to challenges when measuring the distance between concepts and inferring equivalence between concepts. To this end, we developed EL Box Embedding (ELBE) to learn Description Logic EL++ embeddings using axis-parallel boxes. We generate specially designed box-based geometric constraints from EL++ axioms for model training. Since the intersection of boxes remains as a box, the intersectional closure is satisfied. We report extensive experimental results on three datasets and present a case study to demonstrate the effectiveness of the proposed method.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization

As Deep Neural Networks (DNNs) usually are overparameterized and have millions of weight parameters, it is challenging to deploy these large DNN models on resource-constrained hardware platforms, e.g., smartphones. Numerous network compression methods such as pruning and quantization are proposed to reduce the model size significantly, of which the key is to find suitable compression allocation (e.g., pruning sparsity and quantization codebook) of each layer. Existing solutions obtain the compression allocation in an iterative/manual fashion while finetuning the compressed model, thus suffering from the efficiency issue. Different from the prior art, we propose a novel One-shot Pruning-Quantization (OPQ) in this paper, which analytically solves the compression allocation with pre-trained weight parameters only. During finetuning, the compression module is fixed and only weight parameters are updated. To our knowledge, OPQ is the first work that reveals pre-trained model is sufficient for solving pruning and quantization simultaneously, without any complex iterative/manual optimization at the finetuning stage. Furthermore, we propose a unified channel-wise quantization method that enforces all channels of each layer to share a common codebook, which leads to low bit-rate allocation without introducing extra overhead brought by traditional channel-wise quantization. Comprehensive experiments on ImageNet with AlexNet/MobileNet-V1/ResNet-50 show that our method improves accuracy and training efficiency while obtains significantly higher compression rates compared to the state-of-the-art.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approach

We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training. We propose Meta-Learning based Adversarial Domain Augmentation to solve this Out-of-Domain generalization problem. The key idea is to leverage adversarial training to create "fictitious" yet "challenging" populations, from which a model can learn to generalize with theoretical guarantees. To facilitate fast and desirable domain augmentation, we cast the model training in a meta-learning scheme and use a Wasserstein Auto-Encoder to relax the widely used worst-case constraint. We further improve our method by integrating uncertainty quantification for efficient domain generalization. Extensive experiments on multiple benchmark datasets indicate its superior performance in tackling single domain generalization.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation

We propose a keypoint-based object-level SLAM framework that can provide globally consistent 6DoF pose estimates for symmetric and asymmetric objects alike. To the best of our knowledge, our system is among the first to utilize the camera pose information from SLAM to provide prior knowledge for tracking keypoints on symmetric objects -- ensuring that new measurements are consistent with the current 3D scene. Moreover, our semantic keypoint network is trained to predict the Gaussian covariance for the keypoints that captures the true error of the prediction, and thus is not only useful as a weight for the residuals in the system's optimization problems, but also as a means to detect harmful statistical outliers without choosing a manual threshold. Experiments show that our method provides competitive performance to the state of the art in 6DoF object pose estimation, and at a real-time speed. Our code, pre-trained models, and keypoint labels are available https://github.com/rpng/suo_slam.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Tail Quantile Estimation for Non-preemptive Priority Queues

Motivated by applications in computing and telecommunication systems, we investigate the problem of estimating p-quantile of steady-state sojourn times in a single-server multi-class queueing system with non-preemptive priorities for p close to 1. The main challenge in this problem lies in efficient sampling from the tail event. To address this issue, we develop a regenerative simulation algorithm with importance sampling. In addition, we establish a central limit theorem for the estimator to construct the confidence interval. Numerical experiments show that our algorithm outperforms benchmark simulation methods. Our result contributes to the literature on rare event simulation for queueing systems.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

TAR: Neural Logical Reasoning across TBox and ABox

Many ontologies, i.e., Description Logic (DL) knowledge bases, have been developed to provide rich knowledge about various domains. An ontology consists of an ABox, i.e., assertion axioms between two entities or between a concept and an entity, and a TBox, i.e., terminology axioms between two concepts. Neural logical reasoning (NLR) is a fundamental task to explore such knowledge bases, which aims at answering multi-hop queries with logical operations based on distributed representations of queries and answers. While previous NLR methods can give specific entity-level answers, i.e., ABox answers, they are not able to provide descriptive concept-level answers, i.e., TBox answers, where each concept is a description of a set of entities. In other words, previous NLR methods only reason over the ABox of an ontology while ignoring the TBox. In particular, providing TBox answers enables inferring the explanations of each query with descriptive concepts, which make answers comprehensible to users and are of great usefulness in the field of applied ontology. In this work, we formulate the problem of neural logical reasoning across TBox and ABox (TA-NLR), solving which needs to address challenges in incorporating, representing, and operating on concepts. We propose an original solution named TAR for TA-NLR. Firstly, we incorporate description logic based ontological axioms to provide the source of concepts. Then, we represent concepts and queries as fuzzy sets, i.e., sets whose elements have degrees of membership, to bridge concepts and queries with entities. Moreover, we design operators involving concepts on top of fuzzy set representation of concepts and queries for optimization and inference. Extensive experimental results on two real-world datasets demonstrate the effectiveness of TAR for TA-NLR.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

XAI Beyond Classification: Interpretable Neural Clustering

In this paper, we study two challenging problems in explainable AI (XAI) and data clustering. The first is how to directly design a neural network with inherent interpretability, rather than giving post-hoc explanations of a black-box model. The second is implementing discrete $k$-means with a differentiable neural network that embraces the advantages of parallel computing, online clustering, and clustering-favorable representation learning. To address these two challenges, we design a novel neural network, which is a differentiable reformulation of the vanilla $k$-means, called inTerpretable nEuraL cLustering (TELL). Our contributions are threefold. First, to the best of our knowledge, most existing XAI works focus on supervised learning paradigms. This work is one of the few XAI studies on unsupervised learning, in particular, data clustering. Second, TELL is an interpretable, or the so-called intrinsically explainable and transparent model. In contrast, most existing XAI studies resort to various means for understanding a black-box model with post-hoc explanations. Third, from the view of data clustering, TELL possesses many properties highly desired by $k$-means, including but not limited to online clustering, plug-and-play module, parallel computing, and provable convergence. Extensive experiments show that our method achieves superior performance comparing with 14 clustering approaches on three challenging data sets. The source code could be accessed at \url{www.pengxi.me}.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Unsupervised Neural Rendering for Image Hazing

Image hazing aims to render a hazy image from a given clean one, which could be applied to a variety of practical applications such as gaming, filming, photographic filtering, and image dehazing. To generate plausible haze, we study two less-touched but challenging problems in hazy image rendering, namely, i) how to estimate the transmission map from a single image without auxiliary information, and ii) how to adaptively learn the airlight from exemplars, i.e., unpaired real hazy images. To this end, we propose a neural rendering method for image hazing, dubbed as HazeGEN. To be specific, HazeGEN is a knowledge-driven neural network which estimates the transmission map by leveraging a new prior, i.e., there exists the structure similarity (e.g., contour and luminance) between the transmission map and the input clean image. To adaptively learn the airlight, we build a neural module based on another new prior, i.e., the rendered hazy image and the exemplar are similar in the airlight distribution. To the best of our knowledge, this could be the first attempt to deeply rendering hazy images in an unsupervised fashion. Comparing with existing haze generation methods, HazeGEN renders the hazy images in an unsupervised, learnable, and controllable manner, thus avoiding the labor-intensive efforts in paired data collection and the domain-shift issue in haze generation. Extensive experiments show the promising performance of our method comparing with some baselines in both qualitative and quantitative comparisons. The code will be released on GitHub after acceptance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Automatic Health Problem Detection from Gait Videos Using Deep Neural Networks

The aim of this study is developing an automatic system for detection of gait-related health problems using Deep Neural Networks (DNNs). The proposed system takes a video of patients as the input and estimates their 3D body pose using a DNN based method. Our code is publicly available at https://github.com/rmehrizi/multi-view-pose-estimation. The resulting 3D body pose time series are then analyzed in a classifier, which classifies input gait videos into four different groups including Healthy, with Parkinsons disease, Post Stroke patient, and with orthopedic problems. The proposed system removes the requirement of complex and heavy equipment and large laboratory space, and makes the system practical for home use. Moreover, it does not need domain knowledge for feature engineering since it is capable of extracting semantic and high level features from the input data. The experimental results showed the classification accuracy of 56% to 96% for different groups. Furthermore, only 1 out of 25 healthy subjects were misclassified (False positive), and only 1 out of 70 patients were classified as a healthy subject (False negative). This study presents a starting point toward a powerful tool for automatic classification of gait disorders and can be used as a basis for future applications of Deep Learning in clinical gait analysis. Since the system uses digital cameras as the only required equipment, it can be employed in domestic environment of patients and elderly people for consistent gait monitoring and early detection of gait alterations.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Contrastive Clustering

In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. To be specific, for a given dataset, the positive and negative instance pairs are constructed through data augmentations and then projected into a feature space. Therein, the instance- and cluster-level contrastive learning are respectively conducted in the row and column space by maximizing the similarities of positive pairs while minimizing those of negative ones. Our key observation is that the rows of the feature matrix could be regarded as soft labels of instances, and accordingly the columns could be further regarded as cluster representations. By simultaneously optimizing the instance- and cluster-level contrastive loss, the model jointly learns representations and cluster assignments in an end-to-end manner. Extensive experimental results show that CC remarkably outperforms 17 competitive clustering methods on six challenging image benchmarks. In particular, CC achieves an NMI of 0.705 (0.431) on the CIFAR-10 (CIFAR-100) dataset, which is an up to 19\% (39\%) performance improvement compared with the best baseline.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Heterogeneous Representation Learning: A Review

The real-world data usually exhibits heterogeneous properties such as modalities, views, or resources, which brings some unique challenges wherein the key is Heterogeneous Representation Learning (HRL) termed in this paper. This brief survey covers the topic of HRL, centered around several major learning settings and real-world applications. First of all, from the mathematical perspective, we present a unified learning framework which is able to model most existing learning settings with the heterogeneous inputs. After that, we conduct a comprehensive discussion on the HRL framework by reviewing some selected learning problems along with the mathematics perspectives, including multi-view learning, heterogeneous transfer learning, Learning using privileged information and heterogeneous multi-task learning. For each learning task, we also discuss some applications under these learning problems and instantiates the terms in the mathematical framework. Finally, we highlight the challenges that are less-touched in HRL and present future research directions. To the best of our knowledge, there is no such framework to unify these heterogeneous problems, and this survey would benefit the community.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge

Cross-modal knowledge distillation deals with transferring knowledge from a model trained with superior modalities (Teacher) to another model trained with weak modalities (Student). Existing approaches require paired training examples exist in both modalities. However, accessing the data from superior modalities may not always be feasible. For example, in the case of 3D hand pose estimation, depth maps, point clouds, or stereo images usually capture better hand structures than RGB images, but most of them are expensive to be collected. In this paper, we propose a novel scheme to train the Student in a Target dataset where the Teacher is unavailable. Our key idea is to generalize the distilled cross-modal knowledge learned from a Source dataset, which contains paired examples from both modalities, to the Target dataset by modeling knowledge as priors on parameters of the Student. We name our method "Cross-Modal Knowledge Generalization" and demonstrate that our scheme results in competitive performance for 3D hand pose estimation on standard benchmark datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning to Learn Single Domain Generalization

We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training. We propose a new method named adversarial domain augmentation to solve this Out-of-Distribution (OOD) generalization problem. The key idea is to leverage adversarial training to create "fictitious" yet "challenging" populations, from which a model can learn to generalize with theoretical guarantees. To facilitate fast and desirable domain augmentation, we cast the model training in a meta-learning scheme and use a Wasserstein Auto-Encoder (WAE) to relax the widely used worst-case constraint. Detailed theoretical analysis is provided to testify our formulation, while extensive experiments on multiple benchmark datasets indicate its superior performance in tackling single domain generalization.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Propagation dynamics of the circular Airy Gaussian vortex beams in the fractional nonlinear Schrödinger equation

We have investigated the propagation dynamics of the circular Airy Gaussian vortex beams (CAGVBs) in a (2+1)-dimesional optical system discribed by fractional nonlinear Schrödinger equation (FNSE). By combining fractional diffraction with nonlinear effects, the abruptly autofocusing effect becomes weaker, the radius of the focusing beams becomes bigger and the autofocusing length will be shorter with increase of fractional diffraction Lévy index. It has been found that the abruptly autofocusing effect becomes weaker and the abruptly autofocusing length becomes longer if distribution factor of CAGVBs increases for fixing the Lévy index. The roles of the input power and the topological charge in determining the autofocusing properties are also discussed. Then, we have found the CAGVBs with outward acceleration and shown the autodefocusing properties. Finally, the off-axis CAGVBs with positive vortex pairs in the FNSE optical system have shown interesting features during propagation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Semantic Graph Convolutional Networks for 3D Human Pose Regression

In this paper, we study the problem of learning Graph Convolutional Networks (GCNs) for regression. Current architectures of GCNs are limited to the small receptive field of convolution filters and shared transformation matrix for each node. To address these limitations, we propose Semantic Graph Convolutional Networks (SemGCN), a novel neural network architecture that operates on regression tasks with graph-structured data. SemGCN learns to capture semantic information such as local and global node relationships, which is not explicitly represented in the graph. These semantic relationships can be learned through end-to-end training from the ground truth without additional supervision or hand-crafted rules. We further investigate applying SemGCN to 3D human pose regression. Our formulation is intuitive and sufficient since both 2D and 3D human poses can be represented as a structured graph encoding the relationships between joints in the skeleton of a human body. We carry out comprehensive studies to validate our method. The results prove that SemGCN outperforms state of the art while using 90% fewer parameters.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Stabilization of single- and multi-peak solitons in the fractional nonlinear Schroedinger equation with a trapping potential

We address the existence and stability of localized modes in the framework of the fractional nonlinear Schroedinger equation (FNSE) with the focusing cubic or focusing-defocusing cubic-quintic nonlinearity and a confining harmonic-oscillator (HO) potential. Approximate analytical solutions are obtained in the form of Hermite-Gauss modes. The linear stability analysis and direct simulations reveal that, under the action of the cubic self-focusing, the single-peak ground state and dipole mode are stabilized by the HO potential at values of the Levy index (the fractionality degree) alpha = 1 and alpha < 1, which lead, respectively, to the critical or supercritical collapse in free space. In addition to that, the inclusion of the quintic self-defocusing provides stabilization of higher-order modes, with the number of local peaks up to seven, at least.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Structured Graph Learning for Clustering and Semi-supervised Classification

Graphs have become increasingly popular in modeling structures and interactions in a wide variety of problems during the last decade. Graph-based clustering and semi-supervised classification techniques have shown impressive performance. This paper proposes a graph learning framework to preserve both the local and global structure of data. Specifically, our method uses the self-expressiveness of samples to capture the global structure and adaptive neighbor approach to respect the local structure. Furthermore, most existing graph-based methods conduct clustering and semi-supervised classification on the graph learned from the original data matrix, which doesn't have explicit cluster structure, thus they might not achieve the optimal performance. By considering rank constraint, the achieved graph will have exactly $c$ connected components if there are $c$ clusters or classes. As a byproduct of this, graph learning and label inference are jointly and iteratively implemented in a principled way. Theoretically, we show that our model is equivalent to a combination of kernel k-means and k-means methods under certain condition. Extensive experiments on clustering and semi-supervised classification demonstrate that the proposed method outperforms other state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network

In this paper, we study two challenging and less-touched problems in single image dehazing, namely, how to make deep learning achieve image dehazing without training on the ground-truth clean image (unsupervised) and a image collection (untrained). An unsupervised neural network will avoid the intensive labor collection of hazy-clean image pairs, and an untrained model is a ``real'' single image dehazing approach which could remove haze based on only the observed hazy image itself and no extra images is used. Motivated by the layer disentanglement idea, we propose a novel method, called you only look yourself (\textbf{YOLY}) which could be one of the first unsupervised and untrained neural networks for image dehazing. In brief, YOLY employs three jointly subnetworks to separate the observed hazy image into several latent layers, \textit{i.e.}, scene radiance layer, transmission map layer, and atmospheric light layer. After that, these three layers are further composed to the hazy image in a self-supervised manner. Thanks to the unsupervised and untrained characteristics of YOLY, our method bypasses the conventional training paradigm of deep models on hazy-clean pairs or a large scale dataset, thus avoids the labor-intensive data collection and the domain shift issue. Besides, our method also provides an effective learning-based haze transfer solution thanks to its layer disentanglement mechanism. Extensive experiments show the promising performance of our method in image dehazing compared with 14 methods on four databases.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

A Recurrent Encoder-Decoder Network for Sequential Face Alignment

We propose a novel recurrent encoder-decoder network model for real-time video-based face alignment. Our proposed model predicts 2D facial point maps regularized by a regression loss, while uniquely exploiting recurrent learning at both spatial and temporal dimensions. At the spatial level, we add a feedback loop connection between the combined output response map and the input, in order to enable iterative coarse-to-fine face alignment using a single network model. At the temporal level, we first decouple the features in the bottleneck of the network into temporal-variant factors, such as pose and expression, and temporal-invariant factors, such as identity information. Temporal recurrent learning is then applied to the decoupled temporal-variant features, yielding better generalization and significantly more accurate results at test time. We perform a comprehensive experimental analysis, showing the importance of each component of our proposed model, as well as superior results over the state-of-the-art in standard datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Cache Size Allocation in Backhaul Limited Wireless Networks

Caching popular content at base stations is a powerful supplement to existing limited backhaul links for accommodating the exponentially increasing mobile data traffic. Given the limited cache budget, we investigate the cache size allocation problem in cellular networks to maximize the user success probability (USP), taking wireless channel statistics, backhaul capacities and file popularity distributions into consideration. The USP is defined as the probability that one user can successfully download its requested file either from the local cache or via the backhaul link. We first consider a single-cell scenario and derive a closed-form expression for the USP, which helps reveal the impacts of various parameters, such as the file popularity distribution. More specifically, for a highly concentrated file popularity distribution, the required cache size is independent of the total number of files, while for a less concentrated file popularity distribution, the required cache size is in linear relation to the total number of files. Furthermore, we study the multi-cell scenario, and provide a bisection search algorithm to find the optimal cache size allocation. The optimal cache size allocation is verified by simulations, and it is shown to play a more significant role when the file popularity distribution is less concentrated.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Mobility-Aware Caching for Content-Centric Wireless Networks: Modeling and Methodology

As mobile services are shifting from "connection-centric" communications to "content-centric" communications, content-centric wireless networking emerges as a promising paradigm to evolve the current network architecture. Caching popular content at the wireless edge, including base stations (BSs) and user terminals (UTs), provides an effective approach to alleviate the heavy burden on backhaul links, as well as lowering delays and deployment costs. In contrast to wired networks, a unique characteristic of content-centric wireless networks (CCWNs) is the mobility of mobile users. While it has rarely been considered by existing works in caching design, user mobility contains various helpful side information that can be exploited to improve caching efficiency at both BSs and UTs. In this paper, we present a general framework on mobility-aware caching in CCWNs. Key properties of user mobility patterns that are useful for content caching will be firstly identified, and then different design methodologies for mobility-aware caching will be proposed. Moreover, two design examples will be provided to illustrate the proposed framework in details, and interesting future research directions will be identified.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Track Facial Points in Unconstrained Videos

Tracking Facial Points in unconstrained videos is challenging due to the non-rigid deformation that changes over time. In this paper, we propose to exploit incremental learning for person-specific alignment in wild conditions. Our approach takes advantage of part-based representation and cascade regression for robust and efficient alignment on each frame. Unlike existing methods that usually rely on models trained offline, we incrementally update the representation subspace and the cascade of regressors in a unified framework to achieve personalized modeling on the fly. To alleviate the drifting issue, the fitting results are evaluated using a deep neural network, where well-aligned faces are picked out to incrementally update the representation and fitting models. Both image and video datasets are employed to valid the proposed method. The results demonstrate the superior performance of our approach compared with existing approaches in terms of fitting accuracy and efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Backhaul-Aware Caching Placement for Wireless Networks

As the capacity demand of mobile applications keeps increasing, the backhaul network is becoming a bottleneck to support high quality of experience (QoE) in next-generation wireless networks. Content caching at base stations (BSs) is a promising approach to alleviate the backhaul burden and reduce user-perceived latency. In this paper, we consider a wireless caching network where all the BSs are connected to a central controller via backhaul links. In such a network, users can obtain the required data from candidate BSs if the data are pre-cached. Otherwise, the user data need to be first retrieved from the central controller to local BSs, which introduces extra delay over the backhaul. In order to reduce the download delay, the caching placement strategy needs to be optimized. We formulate such a design problem as the minimization of the average download delay over user requests, subject to the caching capacity constraint of each BS. Different from existing works, our model takes BS cooperation in the radio access into consideration and is fully aware of the propagation delay on the backhaul links. The design problem is a mixed integer programming problem and is highly complicated, and thus we relax the problem and propose a low-complexity algorithm. Simulation results will show that the proposed algorithm can effectively determine the near-optimal caching placement and provide significant performance gains over conventional caching placement strategies.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Fast Low-rank Representation based Spatial Pyramid Matching for Image Classification

Spatial Pyramid Matching (SPM) and its variants have achieved a lot of success in image classification. The main difference among them is their encoding schemes. For example, ScSPM incorporates Sparse Code (SC) instead of Vector Quantization (VQ) into the framework of SPM. Although the methods achieve a higher recognition rate than the traditional SPM, they consume more time to encode the local descriptors extracted from the image. In this paper, we propose using Low Rank Representation (LRR) to encode the descriptors under the framework of SPM. Different from SC, LRR considers the group effect among data points instead of sparsity. Benefiting from this property, the proposed method (i.e., LrrSPM) can offer a better performance. To further improve the generalizability and robustness, we reformulate the rank-minimization problem as a truncated projection problem. Extensive experimental studies show that LrrSPM is more efficient than its counterparts (e.g., ScSPM) while achieving competitive recognition rates on nine image data sets.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Inductive Sparse Subspace Clustering

Sparse Subspace Clustering (SSC) has achieved state-of-the-art clustering quality by performing spectral clustering over a $\ell^{1}$-norm based similarity graph. However, SSC is a transductive method which does not handle with the data not used to construct the graph (out-of-sample data). For each new datum, SSC requires solving $n$ optimization problems in O(n) variables for performing the algorithm over the whole data set, where $n$ is the number of data points. Therefore, it is inefficient to apply SSC in fast online clustering and scalable graphing. In this letter, we propose an inductive spectral clustering algorithm, called inductive Sparse Subspace Clustering (iSSC), which makes SSC feasible to cluster out-of-sample data. iSSC adopts the assumption that high-dimensional data actually lie on the low-dimensional manifold such that out-of-sample data could be grouped in the embedding space learned from in-sample data. Experimental results show that iSSC is promising in clustering out-of-sample data.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Learning Locality-Constrained Collaborative Representation for Face Recognition

The model of low-dimensional manifold and sparse representation are two well-known concise models that suggest each data can be described by a few characteristics. Manifold learning is usually investigated for dimension reduction by preserving some expected local geometric structures from the original space to a low-dimensional one. The structures are generally determined by using pairwise distance, e.g., Euclidean distance. Alternatively, sparse representation denotes a data point as a linear combination of the points from the same subspace. In practical applications, however, the nearby points in terms of pairwise distance may not belong to the same subspace, and vice versa. Consequently, it is interesting and important to explore how to get a better representation by integrating these two models together. To this end, this paper proposes a novel coding algorithm, called Locality-Constrained Collaborative Representation (LCCR), which improves the robustness and discrimination of data representation by introducing a kind of local consistency. The locality term derives from a biologic observation that the similar inputs have similar code. The objective function of LCCR has an analytical solution, and it does not involve local minima. The empirical studies based on four public facial databases, ORL, AR, Extended Yale B, and Multiple PIE, show that LCCR is promising in recognizing human faces from frontal views with varying expression and illumination, as well as various corruptions and occlusions.

0 citations0 reviewsNo code linkedOpen access