arXiv subjects

Dong Xu

Publications and source records attributed to Dong Xu.

At least 181 records · Page 10Linked to original sources

arXiv2021

Human-centric Spatio-Temporal Video Grounding With Visual Transformers

In this work, we introduce a novel task - Humancentric Spatio-Temporal Video Grounding (HC-STVG). Unlike the existing referring expression tasks in images or videos, by focusing on humans, HC-STVG aims to localize a spatiotemporal tube of the target person from an untrimmed video based on a given textural description. This task is useful, especially for healthcare and security-related applications, where the surveillance videos can be extremely long but only a specific person during a specific period of time is concerned. HC-STVG is a video grounding task that requires both spatial (where) and temporal (when) localization. Unfortunately, the existing grounding methods cannot handle this task well. We tackle this task by proposing an effective baseline method named Spatio-Temporal Grounding with Visual Transformers (STGVT), which utilizes Visual Transformers to extract cross-modal representations for video-sentence matching and temporal localization. To facilitate this task, we also contribute an HC-STVG dataset consisting of 5,660 video-sentence pairs on complex multi-person scenes. Specifically, each video lasts for 20 seconds, pairing with a natural query sentence with an average of 17.25 words. Extensive experiments are conducted on this dataset, demonstrating the newly-proposed method outperforms the existing baseline methods.

cs.CV↗

arXiv2021

CBANet: Towards Complexity and Bitrate Adaptive Deep Image Compression using a Single Network

In this paper, we propose a new deep image compression framework called Complexity and Bitrate Adaptive Network (CBANet), which aims to learn one single network to support variable bitrate coding under different computational complexity constraints. In contrast to the existing state-of-the-art learning based image compression frameworks that only consider the rate-distortion trade-off without introducing any constraint related to the computational complexity, our CBANet considers the trade-off between the rate and distortion under dynamic computational complexity constraints. Specifically, to decode the images with one single decoder under various computational complexity constraints, we propose a new multi-branch complexity adaptive module, in which each branch only takes a small portion of the computational budget of the decoder. The reconstructed images with different visual qualities can be readily generated by using different numbers of branches. Furthermore, to achieve variable bitrate decoding with one single decoder, we propose a bitrate adaptive module to project the representation from a base bitrate to the expected representation at a target bitrate for transmission. Then it will project the transmitted representation at the target bitrate back to that at the base bitrate for the decoding process. The proposed bit adaptive module can significantly reduce the storage requirement for deployment platforms. As a result, our CBANet enables one single codec to support multiple bitrate decoding under various computational complexity constraints. Comprehensive experiments on two benchmark datasets demonstrate the effectiveness of our CBANet for deep image compression.

eess.IV↗

arXiv2021

Inception Convolution with Efficient Dilation Search

As a variant of standard convolution, a dilated convolution can control effective receptive fields and handle large scale variance of objects without introducing additional computational costs. To fully explore the potential of dilated convolution, we proposed a new type of dilated convolution (referred to as inception convolution), where the convolution operations have independent dilation patterns among different axes, channels and layers. To develop a practical method for learning complex inception convolution based on the data, a simple but effective search algorithm, referred to as efficient dilation optimization (EDO), is developed. Based on statistical optimization, the EDO method operates in a low-cost manner and is extremely fast when it is applied on large scale datasets. Empirical results validate that our method achieves consistent performance gains for image recognition, object detection, instance segmentation, human detection, and human pose estimation. For instance, by simply replacing the 3x3 standard convolution in the ResNet-50 backbone with inception convolution, we significantly improve the AP of Faster R-CNN from 36.4% to 39.2% on MS COCO.

cs.CV↗

arXiv2021

VoxelContext-Net: An Octree based Framework for Point Cloud Compression

In this paper, we propose a two-stage deep learning framework called VoxelContext-Net for both static and dynamic point cloud compression. Taking advantages of both octree based methods and voxel based schemes, our approach employs the voxel context to compress the octree structured data. Specifically, we first extract the local voxel representation that encodes the spatial neighbouring context information for each node in the constructed octree. Then, in the entropy coding stage, we propose a voxel context based deep entropy model to compress the symbols of non-leaf nodes in a lossless way. Furthermore, for dynamic point cloud compression, we additionally introduce the local voxel representations from the temporal neighbouring point clouds to exploit temporal dependency. More importantly, to alleviate the distortion from the octree construction procedure, we propose a voxel context based 3D coordinate refinement method to produce more accurate reconstructed point cloud at the decoder side, which is applicable to both static and dynamic point cloud compression. The comprehensive experiments on both static and dynamic point cloud benchmark datasets(e.g., ScanNet and Semantic KITTI) clearly demonstrate the effectiveness of our newly proposed method VoxelContext-Net for 3D point cloud geometry compression.

cs.CV↗

arXiv2021

Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds

3D object detection in point clouds is a challenging vision task that benefits various applications for understanding the 3D visual world. Lots of recent research focuses on how to exploit end-to-end trainable Hough voting for generating object proposals. However, the current voting strategy can only receive partial votes from the surfaces of potential objects together with severe outlier votes from the cluttered backgrounds, which hampers full utilization of the information from the input point clouds. Inspired by the back-tracing strategy in the conventional Hough voting methods, in this work, we introduce a new 3D object detection method, named as Back-tracing Representative Points Network (BRNet), which generatively back-traces the representative points from the vote centers and also revisits complementary seed points around these generated points, so as to better capture the fine local structural features surrounding the potential objects from the raw point clouds. Therefore, this bottom-up and then top-down strategy in our BRNet enforces mutual consistency between the predicted vote centers and the raw surface points and thus achieves more reliable and flexible object localization and class prediction results. Our BRNet is simple but effective, which significantly outperforms the state-of-the-art methods on two large-scale point cloud datasets, ScanNet V2 (+7.5% in terms of mAP@0.50) and SUN RGB-D (+4.7% in terms of mAP@0.50), while it is still lightweight and efficient. Code will be available at https://github.com/cheng052/BRNet.

cs.CV↗

arXiv2021

VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation

Domain adaptation aims to leverage a label-rich domain (the source domain) to help model learning in a label-scarce domain (the target domain). Most domain adaptation methods require the co-existence of source and target domain samples to reduce the distribution mismatch, however, access to the source domain samples may not always be feasible in the real world applications due to different problems (e.g., storage, transmission, and privacy issues). In this work, we deal with the source data-free unsupervised domain adaptation problem, and propose a novel approach referred to as Virtual Domain Modeling (VDM-DA). The virtual domain acts as a bridge between the source and target domains. On one hand, we generate virtual domain samples based on an approximated Gaussian Mixture Model (GMM) in the feature space with the pre-trained source model, such that the virtual domain maintains a similar distribution with the source domain without accessing to the original source data. On the other hand, we also design an effective distribution alignment method to reduce the distribution divergence between the virtual domain and the target domain by gradually improving the compactness of the target domain distribution through model learning. In this way, we successfully achieve the goal of distribution alignment between the source and target domains by training deep networks without accessing to the source domain data. We conduct extensive experiments on benchmark datasets for both 2D image-based and 3D point cloud-based cross-domain object recognition tasks, where the proposed method referred to Domain Adaptation with Virtual Domain Modeling (VDM-DA) achieves the state-of-the-art performances on all datasets.

cs.CV↗

arXiv2021

Sketchy Empirical Natural Gradient Methods for Deep Learning

In this paper, we develop an efficient sketchy empirical natural gradient method (SENG) for large-scale deep learning problems. The empirical Fisher information matrix is usually low-rank since the sampling is only practical on a small amount of data at each iteration. Although the corresponding natural gradient direction lies in a small subspace, both the computational cost and memory requirement are still not tractable due to the high dimensionality. We design randomized techniques for different neural network structures to resolve these challenges. For layers with a reasonable dimension, sketching can be performed on a regularized least squares subproblem. Otherwise, since the gradient is a vectorization of the product between two matrices, we apply sketching on the low-rank approximations of these matrices to compute the most expensive parts. A distributed version of SENG is also developed for extremely large-scale applications. Global convergence to stationary points is established under some mild assumptions and a fast linear convergence is analyzed under the neural tangent kernel (NTK) case. Extensive experiments on convolutional neural networks show the competitiveness of SENG compared with the state-of-the-art methods. On the task ResNet50 with ImageNet-1k, SENG achieves 75.9\% Top-1 testing accuracy within 41 epochs. Experiments on the distributed large-batch training show that the scaling efficiency is quite reasonable.

math.OC↗

arXiv2021

Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods

In this paper, we consider stochastic second-order methods for minimizing a finite summation of nonconvex functions. One important key is to find an ingenious but cheap scheme to incorporate local curvature information. Since the true Hessian matrix is often a combination of a cheap part and an expensive part, we propose a structured stochastic quasi-Newton method by using partial Hessian information as much as possible. By further exploiting either the low-rank structure or the kronecker-product properties of the quasi-Newton approximations, the computation of the quasi-Newton direction is affordable. Global convergence to stationary point and local superlinear convergence rate are established under some mild assumptions. Numerical results on logistic regression, deep autoencoder networks and deep convolutional neural networks show that our proposed method is quite competitive to the state-of-the-art methods.

math.OC↗

arXiv2021

Active Stabilization of Terahertz Semiconductor Dual-Comb Laser Sources Employing a Phase Locking Technique

Dual-comb sources with equally spaced and low phase noise frequency lines are of great importance for high resolution spectroscopy and metrology. In the terahertz frequency range, electrically pumped semiconductor quantum cascade lasers (QCLs) are suitable candidates for frequency comb and dual-comb operation. For a single laser frequency comb, the repetition rate can be locked using a microwave injection locking and the carrier frequency can be locked to a highly stable source. However, for the locking of two laser combs, four frequencies (two repetition rates and two carrier offset frequencies) should be simultaneously locked; If one only refers to the dual-comb signal, two relative frequencies, i.e., the offset frequency and repetition frequency of one laser against those of the other laser, should be locked. Although the locking techniques that have been successfully used for a single laser comb can be, in principle, applied to a dual-comb laser source, the complete locking considerably complicates the implementation of such a system. Here, we propose a method to stabilize a terahertz QCL dual-comb source by phase locking one of the dual-comb lines to a radio frequency (RF) synthesizer. This technique forces one of the lasers to follow the tone of the other one (keeping the sum of the carrier offset frequency difference and repetition frequency difference between the two laser combs as a constant) by exploiting a laser self-detection that avoids the use of an external detector. Through the demonstration of this locking technique, we demonstrate that the dual-comb can generate periodic pulses over a 2 us time scale, showing that the terahertz QCL comb without a control of the repetition rate can produce pulsed-type waveforms.

physics.app-ph↗

arXiv2020

Deep Learning Analysis and Age Prediction from Shoeprints

Human walking and gaits involve several complex body parts and are influenced by personality, mood, social and cultural traits, and aging. These factors are reflected in shoeprints, which in turn can be used to predict age, a problem not systematically addressed using any computational approach. We collected 100,000 shoeprints of subjects ranging from 7 to 80 years old and used the data to develop a deep learning end-to-end model ShoeNet to analyze age-related patterns and predict age. The model integrates various convolutional neural network models together using a skip mechanism to extract age-related features, especially in pressure and abrasion regions from pair-wise shoeprints. The results show that 40.23% of the subjects had prediction errors within 5-years of age and the prediction accuracy for gender classification reached 86.07%. Interestingly, the age-related features mostly reside in the asymmetric differences between left and right shoeprints. The analysis also reveals interesting age-related and gender-related patterns in the pressure distributions on shoeprints; in particular, the pressure forces spread from the middle of the toe toward outside regions over age with gender-specific variations on heel regions. Such statistics provide insight into new methods for forensic investigations, medical studies of gait-pattern disorders, biometrics, and sport studies.

cs.CV↗

arXiv2020

A Method of Generating Measurable Panoramic Image for Indoor Mobile Measurement System

This paper designs a technique route to generate high-quality panoramic image with depth information, which involves two critical research hotspots: fusion of LiDAR and image data and image stitching. For the fusion of 3D points and image data, since a sparse depth map can be firstly generated by projecting LiDAR point onto the RGB image plane based on our reliable calibrated and synchronized sensors, we adopt a parameter self-adaptive framework to produce 2D dense depth map. For image stitching, optimal seamline for the overlapping area is searched using a graph-cuts-based method to alleviate the geometric influence and image blending based on the pyramid multi-band is utilized to eliminate the photometric effects near the stitching line. Since each pixel is associated with a depth value, we design this depth value as a radius in the spherical projection which can further project the panoramic image to the world coordinate and consequently produces a high-quality measurable panoramic image. The purposed method is tested on the data from our data collection platform and presents a satisfactory application prospects.

cs.CV↗

arXiv2020

A Simple and Efficient Registration of 3D Point Cloud and Image Data for Indoor Mobile Mapping System

Registration of 3D LiDAR point clouds with optical images is critical in the combination of multi-source data. Geometric misalignment originally exists in the pose data between LiDAR point clouds and optical images. To improve the accuracy of the initial pose and the applicability of the integration of 3D points and image data, we develop a simple but efficient registration method. We firstly extract point features from LiDAR point clouds and images: point features is extracted from single-frame LiDAR and point features from images using classical Canny method. Cost map is subsequently built based on Canny image edge detection. The optimization direction is guided by the cost map where low cost represents the the desired direction, and loss function is also considered to improve the robustness of the the purposed method. Experiments show pleasant results.

cs.CV↗

arXiv2020

Formal Language Constraints for Markov Decision Processes

In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned (RL) controllers require exploration, which can be hazardous in safety critical situations. We study the benefits of giving structure to the constraints of a constrained Markov decision process by specifying them in formal languages as a step towards using safety methods from software engineering and controller synthesis. We instantiate these constraints as finite automata to efficiently recognise constraint violations. Constraint states are then used to augment the underlying MDP state and to learn a dense cost function, easing the problem of quickly learning joint MDP/constraint dynamics. We empirically evaluate the effect of these methods on training a variety of RL algorithms over several constraints specified in Safety Gym, MuJoCo, and Atari environments.

cs.LG↗

arXiv2020

A Hybrid Simulation-based Duopoly Game Framework for Analysis of Supply Chain and Marketing Activities

A hybrid simulation-based framework involving system dynamics and agent-based simulation is proposed to address duopoly game considering multiple strategic decision variables and rich payoff, which cannot be addressed by traditional approaches involving closed-form equations. While system dynamics models are used to represent integrated production, logistics, and pricing determination activities of duopoly companies, agent-based simulation is used to mimic enhanced consumer purchasing behavior considering advertisement, promotion effect, and acquaintance recommendation in the consumer social network. The payoff function of the duopoly companies is assumed to be the net profit based on the total revenue and various cost items such as raw material, production, transportation, inventory and backorder. A unique procedure is proposed to solve and analyze the proposed simulation-based game, where the procedural components include strategy refinement, data sampling, gaming solving, and performance evaluation. First, design of experiment and estimated conformational value of information techniques are employed for strategy refinement and data sampling, respectively. Game solving then focuses on pure strategy equilibriums, and performance evaluation addresses game stability, equilibrium strictness, and robustness. A hypothetical case scenario involving soft-drink duopoly on Coke and Pepsi is considered to illustrate and demonstrate the proposed approach. Final results include P-values of statistical tests, confidence intervals, and simulation steady state analysis for different pure equilibriums.

cs.GT↗

arXiv2020

Dynamic Scheduling and Workforce Assignment in Open Source Software Development

A novel modeling framework is proposed for dynamic scheduling of projects and workforce assignment in open source software development (OSSD). The goal is to help project managers in OSSD distribute workforce to multiple projects to achieve high efficiency in software development (e.g. high workforce utilization and short development time) while ensuring the quality of deliverables (e.g. code modularity and software security). The proposed framework consists of two models: 1) a system dynamic model coupled with a meta-heuristic to obtain an optimal schedule of software development projects considering their attributes (e.g. priority, effort, duration) and 2) an agent based model to represent the development community as a social network, where development managers form an optimal team for each project and balance the workload among multiple scheduled projects based on the optimal schedule obtained from the system dynamic model. To illustrate the proposed framework, a software enhancement request process in Kuali foundation is used as a case study. Survey data collected from the Kuali development managers, project managers and actual historical enhancement requests have been used to construct the proposed models. Extensive experiments are conducted to demonstrate the impact of varying parameters on the considered efficiency and quality.

cs.SE↗

arXiv2020

Improving Deep Video Compression by Resolution-adaptive Flow Coding

In the learning based video compression approaches, it is an essential issue to compress pixel-level optical flow maps by developing new motion vector (MV) encoders. In this work, we propose a new framework called Resolution-adaptive Flow Coding (RaFC) to effectively compress the flow maps globally and locally, in which we use multi-resolution representations instead of single-resolution representations for both the input flow maps and the output motion features of the MV encoder. To handle complex or simple motion patterns globally, our frame-level scheme RaFC-frame automatically decides the optimal flow map resolution for each video frame. To cope different types of motion patterns locally, our block-level scheme called RaFC-block can also select the optimal resolution for each local block of motion features. In addition, the rate-distortion criterion is applied to both RaFC-frame and RaFC-block and select the optimal motion coding mode for effective flow coding. Comprehensive experiments on four benchmark datasets HEVC, VTL, UVG and MCL-JCV clearly demonstrate the effectiveness of our overall RaFC framework after combing RaFC-frame and RaFC-block for video compression.

cs.CV↗

arXiv2020

GWOPS: A VO-technology Driven Tool to Search for the Electromagnetic Counterpart of Gravitational Wave Event

The search and follow-up observation of electromagnetic (EM) counterparts of gravitational waves (GW) is a current hot topic of GW cosmology. Due to the limitation of the accuracy of the GW observation facility at this stage, we can only get a rough sky-localization region for the GW event, and the typical area of the region is between 200 and 1500 square degrees. Since GW events occur in or near galaxies, limiting the observation target to galaxies can significantly speedup searching for EM counterparts. Therefore, how to efficiently select host galaxy candidates in such a large GW localization region, how to arrange the observation sequence, and how to efficiently identify the GW source from observational data are the problems that need to be solved. International Virtual Observatory Alliance has developed a series of technical standards for data retrieval, interoperability and visualization. Based on the application of VO technologies, we construct the GW follow-up Observation Planning System (GWOPS). It consists of three parts: a pipeline to select host candidates of GW and sort their priorities for follow-up observation, an identification module to find the transient from follow-up observation data, and a visualization module to display GW-related data. GWOPS can rapidly respond to GW events. With GWOPS, the operations such as follow-up observation planning, data storage, data visualization, and transient identification can be efficiently coordinated, which will promote the success searching rate for GWs EM counterparts.

astro-ph.IM↗

arXiv2020

Deep Learning Detection of Inaccurate Smart Electricity Meters: A Case Study

Detecting inaccurate smart meters and targeting them for replacement can save significant resources. For this purpose, a novel deep-learning method was developed based on long short-term memory (LSTM) and a modified convolutional neural network (CNN) to predict electricity usage trajectories based on historical data. From the significant difference between the predicted trajectory and the observed one, the meters that cannot measure electricity accurately are located. In a case study, a proof of principle was demonstrated in detecting inaccurate meters with high accuracy for practical usage to prevent unnecessary replacement and increase the service life span of smart meters.

eess.SP↗