Search

Recently, density map regression-based methods have dominated in crowd counting owing to their excellent fitting ability on density distribution. However, further improvement tends to saturate mainly because of the confusing background noise and the large density variation. In this paper, we propose a Hierarchically Decoupled Network (HDNet) to solve the above two problems within a unified framework. Specifically, a background classification sub-task is decomposed from the density map prediction task, which is then assigned to a Density Decoupling Module (DDM) to exploit its highly discriminative ability. For the remaining foreground prediction sub-task, it is further hierarchically decomposed to several density-specific sub-tasks by the DDM, which are then solved by the regression-based experts in a Foreground Density Estimation Module (FDEM). Although the proposed strategy effectively reduces the hypothesis space so as to relieve the optimization for those task-specific experts, the high correlation of these sub-tasks are ignored. Therefore, we introduce three types of interaction strategies to unify the whole framework, which are Feature Interaction, Gradient Interaction, and Scale Interaction. Integrated with the above spirits, HDNet achieves state-of-the-art performance on several popular counting benchmarks., Comment: Accepted by IEEE International Conference on Multimedia and Expo (ICME), 2022

Pedestrian detection in the wild remains a challenging problem especially for scenes containing serious occlusion. In this paper, we propose a novel feature learning method in the deep learning framework, referred to as Feature Calibration Network (FC-Net), to adaptively detect pedestrians under various occlusions. FC-Net is based on the observation that the visible parts of pedestrians are selective and decisive for detection, and is implemented as a self-paced feature learning framework with a self-activation (SA) module and a feature calibration (FC) module. In a new self-activated manner, FC-Net learns features which highlight the visible parts and suppress the occluded parts of pedestrians. The SA module estimates pedestrian activation maps by reusing classifier weights, without any additional parameter involved, therefore resulting in an extremely parsimony model to reinforce the semantics of features, while the FC module calibrates the convolutional features for adaptive pedestrian representation in both pixel-wise and region-based ways. Experiments on CityPersons and Caltech datasets demonstrate that FC-Net improves detection performance on occluded pedestrians up to 10% while maintaining excellent performance on non-occluded instances., Comment: Accepted by IEEE Transactions on Intelligent Transportation Systems (TITS)

Pedestrian detection in the wild remains a challenging problem especially when the scene contains significant occlusion and/or low resolution of the pedestrians to be detected. Existing methods are unable to adapt to these difficult cases while maintaining acceptable performance. In this paper we propose a novel feature learning model, referred to as CircleNet, to achieve feature adaptation by mimicking the process humans looking at low resolution and occluded objects: focusing on it again, at a finer scale, if the object can not be identified clearly for the first time. CircleNet is implemented as a set of feature pyramids and uses weight sharing path augmentation for better feature fusion. It targets at reciprocating feature adaptation and iterative object detection using multiple top-down and bottom-up pathways. To take full advantage of the feature adaptation capability in CircleNet, we design an instance decomposition training strategy to focus on detecting pedestrian instances of various resolutions and different occlusion levels in each cycle. Specifically, CircleNet implements feature ensemble with the idea of hard negative boosting in an end-to-end manner. Experiments on two pedestrian detection datasets, Caltech and CityPersons, show that CircleNet improves the performance of occluded and low-resolution pedestrians with significant margins while maintaining good performance on normal instances., Comment: Accepted by Transactions on Intelligent Transportation Systems (TITS)

Multi-label image classification, which can be categorized into label-dependency and region-based methods, is a challenging problem due to the complex underlying object layouts. Although region-based methods are less likely to encounter issues with model generalizability than label-dependency methods, they often generate hundreds of meaningless or noisy proposals with non-discriminative information, and the contextual dependency among the localized regions is often ignored or over-simplified. This paper builds a unified framework to perform effective noisy-proposal suppression and to interact between global and local features for robust feature learning. Specifically, we propose category-aware weak supervision to concentrate on non-existent categories so as to provide deterministic information for local feature learning, restricting the local branch to focus on more high-quality regions of interest. Moreover, we develop a cross-granularity attention module to explore the complementary information between global and local features, which can build the high-order feature correlation containing not only global-to-local, but also local-to-local relations. Both advantages guarantee a boost in the performance of the whole network. Extensive experiments on two large-scale datasets (MS-COCO and VOC 2007) demonstrate that our framework achieves superior performance over state-of-the-art methods., Comment: 12 pages, 10 figures, published in ACMMM 2022

In this paper, the problem of non-fragile finite-time stabilization for linear discrete mean-field stochastic systems is studied. The uncertain characteristics in control parameters are assumed to be random satisfying the Bernoulli distribution. A new approach called the ``state transition matrix method" is introduced and some necessary and sufficient conditions are derived to solve the underlying stabilization problem. The Lyapunov theorem based on the state transition matrix also makes a contribution to the discrete finite-time control theory. One practical example is provided to validate the effectiveness of the newly proposed control strategy.

In this paper, a control scheme for stochastic predefined-time stabilization is proposed, which improves the control effect compared with stochastic finite-time or fixed-time stabilization. The stochastic predefined-time stabilization allows the upper bound of the mathematical expectation of the settling-time function below any given positive value. Some Lyapunov-type results for predefined-time stabilization of general stochastic It\^o systems are presented. Moreover, a state feedback control scheme is designed for a class of stochastic nonlinear systems in strict-feedback form. Two simulation examples are supplied to show the usefulness of the proposed stochastic predefined-time stabilization., Comment: 12 pages,2 figures

Polarized X-ray source is an important probe for many fields such as fluorescence imaging, magnetic microscopy, and nuclear physics research. All-optical inverse Compton scattering source (AOCS) based on laser wakefield accelerator (LWFA) has drawn great attention in recent years due to its compact scale and high performance, especially its potential to generate polarized X-rays. Here, polarization-tunable X-rays are generated by a plasma-mirror-based AOCS scheme. The linearly and circularly polarized AOCS pulses are achieved with the mean photon energy of 60($\pm$5)/64($\pm$3) keV and the single-shot photon yield of $\sim$1.1/1.3$\times10^7$. A Compton polarimeter is designed to diagnose the photon polarization states, demonstrating AOCS's polarization-tunable property, and indicating the average polarization degree of the linearly polarized AOCS is 75($\pm$3)%.

This report introduces the technical details of the team FuXi-Fresher for LVIS Challenge 2021. Our method focuses on the problem in following two aspects: the long-tail distribution and the segmentation quality of mask and boundary. Based on the advanced HTC instance segmentation algorithm, we connect transformer backbone(Swin-L) through composite connections inspired by CBNetv2 to enhance the baseline results. To alleviate the problem of long-tail distribution, we design a Distribution Balanced method which includes dataset balanced and loss function balaced modules. Further, we use a Mask and Boundary Refinement method composed with mask scoring and refine-mask algorithms to improve the segmentation quality. In addition, we are pleasantly surprised to find that early stopping combined with EMA method can achieve a great improvement. Finally, by using multi-scale testing and increasing the upper limit of the number of objects detected per image, we achieved more than 45.4% boundary AP on the val set of LVIS Challenge 2021. On the test data of LVIS Challenge 2021, we rank 1st and achieve 48.1% AP. Notably, our APr 47.5% is very closed to the APf 48.0%.

With the increasing demand for openness, flexibility, and monetization the Network Function Virtualization (NFV) of mobile network functions has become the embracing factor for most mobile network operators. Early reported field deployments of virtualized Evolved Packet Core (EPC) - the core network component of 4G LTE and 5G non-standalone mobile networks - reflect this growing trend. To best meet the requirements of power management, load balancing, and fault tolerance in the cloud environment, the need for live migration for these virtualized components cannot be shunned. Virtualization platforms of interest include both Virtual Machines (VMs) and Containers, with the latter option offering more lightweight characteristics. The first contribution of this paper is the implementation of a number of custom functions that enable migration of Containers supporting virtualized EPC components. The current CRIU-based migration of Docker Container does not fully support the mobile network protocol stack. CRIU extensions to support the mobile network protocol stack are therefore required and described in the paper. The second contribution is an experimental-based comprehensive analysis of live migration in two backhaul network settings and two virtualization technologies. The two backhaul network settings are the one provided by CloudLab and one based on a programmable optical network testbed that makes use of OpenROADM dense wavelength division multiplexing (DWDM) equipment. The paper compares the migration performance of the proposed implementation of OpenAirInterface (OAI) based containerized EPC components with the one utilizing VMs, running in OpenStack. The presented experimental comparison accounts for a number of system parameters and configurations, image size of the virtualized EPC components, network characteristics, and signal propagation time across the OpenROADM backhaul network.

The temporal evolution of the magnetic field associated with electron thermal Weibel instability in optical-field ionized plasmas is measured using ultrashort (1.8 ps), relativistic (45 MeV) electron bunches from a linear accelerator. The self-generated magnetic fields are found to self-organize into a quasi-static structure consistent with a helicoid topology within a few ps and such a structure lasts for tens of ps in underdense plasmas. The measured growth rate agrees well with that predicted by the kinetic theory of plasmas taking into account collisions. Magnetic trapping is identified as the dominant saturation mechanism., Comment: Accepted for publication in Physical Review Letters

Micro-focus computed tomography (CT), enabling the reconstruction of hyperfine structure within objects, is a powerful nondestructive testing tool in many fields. Current X-ray sources for micro-focus CT are typically limited by their relatively low photon energy and low flux. An all-optical inverse Compton scattering source (AOCS) based on laser wakefield accelerator (LWFA) can generate intense quasi-monoenergetic X/gamma-ray pulses in the keV-MeV range with micron-level source size, and its potential application for micro-focus CT has become very attractive in recent years due to the fast pace progress made in LWFA. Here we report the first experimental demonstration of high-fidelity micro-focus CT using AOCS (~70 keV) by imaging and reconstructing a test object with complex inner structures. A region-of-interest (ROI) CT method is adopted to utilize the relatively small field-of-view (FOV) of AOCS to obtain high-resolution reconstruction. This demonstration of the ROI micro-focus CT based on AOCS is a key step for its application in the field of hyperfine nondestructive testing.

Classification and localization are two pillars of visual object detectors. However, in CNN-based detectors, these two modules are usually optimized under a fixed set of candidate (or anchor) bounding boxes. This configuration significantly limits the possibility to jointly optimize classification and localization. In this paper, we propose a Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector. Our approach, referred to as Multiple Anchor Learning (MAL), constructs anchor bags and selects the most representative anchors from each bag. Such an iterative selection process is potentially NP-hard to optimize. To address this issue, we solve MAL by repetitively depressing the confidence of selected anchors by perturbing their corresponding features. In an adversarial selection-depression manner, MAL not only pursues optimal solutions but also fully leverages multiple anchors/features to learn a detection model. Experiments show that MAL improves the baseline RetinaNet with significant margins on the commonly used MS-COCO object detection benchmark and achieves new state-of-the-art detection performance compared with recent methods.

The Gamma-Ray Integrated Detectors (GRID) is a space mission concept dedicated to monitoring the transient gamma-ray sky in the energy range from 10 keV to 2 MeV using scintillation detectors onboard CubeSats in low Earth orbits. The primary targets of GRID are the gamma-ray bursts (GRBs) in the local universe. The scientific goal of GRID is, in synergy with ground-based gravitational wave (GW) detectors such as LIGO and VIRGO, to accumulate a sample of GRBs associated with the merger of two compact stars and study jets and related physics of those objects. It also involves observing and studying other gamma-ray transients such as long GRBs, soft gamma-ray repeaters, terrestrial gamma-ray flashes, and solar flares. With multiple CubeSats in various orbits, GRID is unaffected by the Earth occultation and serves as a full-time and all-sky monitor. Assuming a horizon of 200 Mpc for ground-based GW detectors, we expect to see a few associated GW-GRB events per year. With about 10 CubeSats in operation, GRID is capable of localizing a faint GRB like 170817A with a 90% error radius of about 10 degrees, through triangulation and flux modulation. GRID is proposed and developed by students, with considerable contribution from undergraduate students, and will remain operated as a student project in the future. The current GRID collaboration involves more than 20 institutes and keeps growing. On August 29th, the first GRID detector onboard a CubeSat was launched into a Sun-synchronous orbit and is currently under test., Comment: accepted for publication in Experimental Astronomy

This paper studies the mixed $H_-/H_{\infty}$ fault detection filtering of It\^o-type nonlinear stochastic systems. Mixed $H_-/H_{\infty}$ filtering combines the system robustness to the external disturbance and the sensitivity to the fault of the residual signal. Firstly, for It\^o-type affine nonlinear stochastic systems, some sufficient criteria are obtained for the existence of $H_-/H_{\infty}$ filter in terms of Hamilton-Jacobi inequalities (HJIs). Secondly, for a class of quasi-linear It\^o systems, a sufficient condition is given for the existence of $H_-/H_{\infty}$ filter by means of linear matrix inequalities (LMIs). Finally, a numerical example is presented to illustrate the effectiveness of the proposed results.

This paper mainly discusses the $H_{\infty}$ filtering of general nonlinear discrete time-varying stochastic systems. A nonlinear discrete-time stochastic bounded real lemma (SBRL) is firstly obtained by means of the smoothness of the conditional mathematical expectation, and then, based on the given SBRL and a stochastic LaSalle-type theorem, a sufficient condition for the existence of the $H_\infty$ filtering of general nonlinear discrete time-varying stochastic systems is presented via a new introduced Hamilton-Jacobi inequality (HJI), which is easily verified. When the worst-case disturbance $\{v^*_k\}_{k\in {\mathcal N}}$ is considered, the suboptimal $H_2/H_\infty$ filtering is studied. Two examples including a practical engineering example show the effectiveness of our main results.

This paper studies the finite-time stability and stabilization of linear discrete time-varying stochastic systems with multiplicative noise. Firstly, necessary and sufficient conditions for finite-time stability are presented via state transition matrix approach. Secondly, this paper also develops the Lyapunov function method to study finite-time stability and stabilization of discrete time-varying stochastic systems based on matrix inequalities and linear matrix inequalities (LMIs), so as to Matlab LMI Toolbox can be used. Two numerical examples are given to illustrate the effectiveness of the proposed results.

In this paper, a new approach based on convex analysis is introduced to solve the $H_\infty$ problem for discrete-time nonlinear stochastic systems. A stochastic version of bounded real lemma is proved and the state feedback $H_\infty$ control is studied. Two examples are presented to show the effectiveness of our developed theory., Comment: 29 pages, 4 figures, 36 references

In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved. The self-learning approach is deployed as progressive steps of object discovery, object enforcement, and label propagation. In the learning procedure, object locations in each frame are treated as latent variables that are solved with a progressive latent model (PLM). Compared with conventional latent models, the proposed PLM incorporates a spatial regularization term to reduce ambiguities in object proposals and to enforce object localization, and also a graph-based label propagation to discover harder instances in adjacent frames. With the difference of convex (DC) objective functions, PLM can be efficiently optimized with a concave-convex programming and thus guaranteeing the stability of self-learning. Extensive experiments demonstrate that even without annotation the proposed self-learning approach outperforms weakly supervised learning approaches, while achieving comparable performance with transfer learning and fully supervised approaches.