We investigate a new task in human motion prediction, which aims to forecast future body poses from historically observed sequences while accounting for arbitrary latency. This differs from existing works that assume an ideal scenario where future motions can be "instantaneously" predicted, thereby neglecting time delays caused by network transmission and algorithm execution. Addressing this task requires tackling two key challenges: The length of latency period can vary significantly across samples; the prediction model must be efficient. In this paper, we propose ALIEN, which treats the motion as a continuous function parameterized by a neural network, enabling predictions under any latency condition. By incorporating Mamba-like linear attention as a hyper-network and designing subsequent low-rank modulation, ALIEN efficiently learns a set of implicit neural representation weights from the observed motion to encode instance-specific information. Additionally, our model integrates the primary motion prediction task with an extra-designed variable-delay pose reconstruction task in a unified multi-task learning framework, enhancing its ability to capture richer motion patterns. Extensive experiments demonstrate that our approach outperforms state-of-the-art baselines adapted for our new task, while maintaining competitive performance in traditional prediction setting.

Making accurate prediction of human motions based on the historical observation is a crucial technology for robots to collaborate with humans. Existing human motion prediction methods are all built under an ideal assumption that robots can instantaneously react, which ignores the time delay introduced during data processing & analysis and future reaction planning – jointly known as "response latency". Consequently, the predictions made within this latency period become meaningless for practical use, as part of the time has passed and the corresponding real motions have already occurred before robot deliver its reaction. In this paper, we argue that the seemingly meaningless prediction period, however, can be leveraged to enhance prediction accuracy significantly. We propose LAL, a Latency-aware Auxiliary Learning framework, which shifts the existing "reaction instantaneous" convention into a new motion prediction paradigm with both latency compatibility and utility. The framework consists of two branches handling different tasks: the primary branch learns to directly predict the valid target (excluding the beginning latency period) based on observation; while the auxiliary branch learns the same target, but based on the reformed observation with additional latency data incorporated. A direct and effective way of auxiliary feature sharing is forced by our tailored consistency loss, to gradually integrate auxiliary latency insights into the primary prediction branch. Estimated feature statistics-based alignment method is presented as optional step for primary branch refinement. Experiments show that LAL achieves significant improvement on prediction accuracy, without additional time consumption during testing.

Mobile Edge Computing (MEC) is an emerging computing paradigm that offloads cloud center functions to the edge server. In a MEC environment, edge servers' limited storage and processing capacity require selective service caching, where only a part of required content can be placed directly upon the destination edge server and the remaining at remote cloud end. A primary challenge in this context is the creation of an effective and responsive service caching algorithm that improves the Quality of Service (QoS) perceived by users while reducing operational costs. This study applies an$M$/ G /1 queuing model as the foundational framework and transforms the service caching problem as an adversarial semi-bandit problem. We propose a delay-aware Genetic-Follow-the-Regularized-Leader (GFRL) algorithm, which is capable of guiding decentralized caching decisions. Experimental results indicate that GFRL outperforms traditional methods across various performance metrics.

Mobile edge computing is an emerging computing paradigm boosting resource-demanding and delay-sensitive applications through deploying computing infrastructures at the edge of the Internet nearby mobile requesters and users. In an Internet of Vehicles (IoV) environment, Vehicular Edge Computing (VEC) is capable of exploiting network edge devices, in terms of, e.g., Roadside Units (RSUs), for predictive content caching for optimizing quality-of-experience (QoE) of nearby content requesters based on content popularity analysis, it remains a great challenge to accurately predict content popularity of mobile requesters and appropriately cache required content with low miss rate accordingly in a VEC environment with high user mobility and dynamics. To address this challenge mentioned above, in this paper, we propose predictive content popularity-aware approach, i.e., KM_SVD++, to edge caching in an VEC environment. The proposed approach is capable of achieving high hit rate of mobile content requestors in VEC and low latency of content delivery by leveraging a Kalman filtering model for predicting locations of vehicles and a SVD++ one for yielding decisions for cache deployment and replacement. We conduct extensive simulations as well to prove its effectiveness.

The emergence of text-driven motion synthesis technique provides animators with great potential to create efficiently. However, in most cases, textual expressions only contain general and qualitative motion descriptions, while lack fine depiction and sufficient intensity, leading to the synthesized motions that either (a) semantically compliant but uncontrollable over specific pose details, or (b) even deviates from the provided descriptions, bringing animators with undesired cases. In this paper, we propose DiffKFC, a conditional diffusion model for text-driven motion synthesis with KeyFrames Collaborated, enabling realistic generation with collaborative and efficient dual-level control: coarse guidance at semantic level, with only few keyframes for direct and fine-grained depiction down to body posture level. Unlike existing inference-editing diffusion models that incorporate conditions without training, our conditional diffusion model is explicitly trained and can fully exploit correlations among texts, keyframes and the diffused target frames. To preserve the control capability of discrete and sparse keyframes, we customize dilated mask attention modules where only partial valid tokens participate in local-to-global attention, indicated by the dilated keyframe mask. Additionally, we develop a simple yet effective smoothness prior, which steers the generated frames towards seamless keyframe transitions at inference. Extensive experiments show that our model not only achieves state-of-the-art performance in terms of semantic fidelity, but more importantly, is able to satisfy animator requirements through fine-grained guidance without tedious labor.

In the academic field, the research on human motion pre-diction tasks mainly focuses on exploiting the observed in-formation to forecast human movements accurately in the near future horizon. However, a significant gap appears when it comes to the application field, as current models are all trained offline, with fixed parameters that are inher-ently suboptimal to handle the complex yet ever-changing nature of human behaviors. To bridge this gap, in this pa-per, we introduce the task of online meta adaptation for hu-man motion prediction, based on the insight that finding “smart weights” capable of swift adjustments to suit dif-ferent motion contexts along the time is a key to improving predictive accuracy. We propose MoML, which ingeniously borrows the bilevel optimization spirit of model-agnostic meta-learning, to transform previous predictive mistakes into strong inductive biases to guide online adaptation. This is achieved by our MoAdapter blocks that can learn er-ror information by facilitating efficient adaptation via a few gradient steps, which fine-tunes our meta-learned “smart” initialization produced by the generic predictor. Considering real-time requirements in practice, we further propose Fast-MoML, a more efficient variant of MoML that features a closed-form solution instead of conventional gradient up-date. Experimental results show that our approach can ef-fectively bring many existing offline motion prediction mod-els online, and improves their predictive accuracy.

Generating realistic human motions with high framerate is an underexplored task, due to the varied framerates of training data, huge memory burden brought by high framerates and slow sampling speed of generative models. Recent advances make a compromise for training by downsampling high-framerate details away and discarding low-framerate samples, which suffer from severe information loss and restricted-framerate generation. In this paper, we found that the recent emerging paradigm of Implicit Neural Representations (INRs) that encode a signal into a continuous function can effectively tackle this challenging problem. To this end, we introduce NeRM, a generative model capable of taking advantage of varied-size data and capturing variational distribution of motions for high-framerate motion synthesis. By optimizing latent representation and a auto-decoder conditioned on temporal coordinates, NeRM learns continuous motion fields of sampled motion clips that ingeniously avoid explicit modeling of raw varied-size motions. This expressive latent representation is then used to learn a diffusion model that enables both unconditional and conditional generation of human motions. We demonstrate that our approach achieves competitive results with state-of-the-art methods, and can generate arbitrary framerate motions. Additionally, we show that NeRM is not only memory-friendly, but also highly efficient even when generating high-framerate motions.

Mobile edge computing(MEC) is an innovative technology that deploys computing resources around the demand side to provide near-request and responsiveness-guaranteed computing and storage services. A major attention paid by related works in this direction is mobility, where mobile traces of both edge users and servers are analyzed and exploited for accommodating offloading and migration requests for computation resources in a highly dynamic MEC environment. Our research in this work suggests that information of user interests, in terms of points of interest (POI), can be exploited in conjunction with mobility as well and proposes a hybrid method for for interest-informed and mobility-aware service migration path selection(HIMS). It synthesizes a trajectory prediction model and user interests prediction one for selecting target servers and reliable service migration paths. Experimental results demonstrate that our approach outperforms traditional methods across multiple performance metrics, especially those with sole input of mobility.

Heatmap regression has dominated human pose estimation due to its superior performance and strong generalization. To meet the requirements of traditional explicit neural networks for output form, existing heatmap-based methods discretize the originally continuous heatmap representation into 2D pixel arrays, which leads to performance degradation due to the introduction of quantization errors. This problem is significantly exacerbated as the size of the input image decreases, which makes heatmap-based methods not much better than coordinate regression on low-resolution images. In this paper, we propose a novel neural representation for human pose estimation called NerPE to achieve continuous heatmap regression. Given any position within the image range, NerPE regresses the corresponding confidence scores for body joints according to the surrounding image features, which guarantees continuity in space and confidence during training. Thanks to the decoupling from spatial resolution, NerPE can output the predicted heatmaps at arbitrary resolution during inference without retraining, which easily achieves sub-pixel localization precision. To reduce the computational cost, we design progressive coordinate decoding to cooperate with continuous heatmap regression, in which localization no longer requires the complete generation of high-resolution heatmaps. The code is available at https://github.com/hushengxiang/NerPE.

Previous works on human motion prediction follow the pattern of building an extrapolation mapping between the sequence observed and the one to be predicted. However, the inherent difficulty of time-series extrapolation and complexity of human motion data still result in many failure cases. In this paper, we explore a longer horizon of sequence with more poses following behind, which breaks the limit in extrapolation problems that data/information on the other side of the predictive target is completely unknown. As these poses are unavailable for testing, we regard them as a privileged sequence, and propose a Two-stage Privileged Knowledge Distillation framework that incorporates privileged information in the forecasting process while avoiding direct use of it. Specifically, in the first stage, both the observed and privileged sequence are encoded for interpolation, with Privileged-sequence-Encoder (Priv-Encoder) learning privileged knowledge (PK) simultaneously. Then, in the second stage where privileged sequence is not observable, a novel PK-Simulator distills PK by approximating the behavior of Priv-Encoder, but only taking as input the observed sequence, to enable a PK-aware prediction pattern. Moreover, we present a One-stage version of this framework, using Shared Encoder that integrates the observation encoding in both interpolation and prediction branches to realize parallel training, which helps produce the most conducive PK to prediction pipeline. Experimental results show that our frameworks are model-agnostic, and can be applied to existing motion prediction models with encoder-decoder architecture to achieve improved performance.

Vehicle Edge Computing (VEC) is the deployment of applications close to edge servers to provide low latency and highly responsive services to users. However, due to the complexity and dynamics of the VEC environment, it is prone to errors and failures, and the reliability of edge service migration may be compromised if no measures are taken to cope with different levels of failures. To address this issue, this paper proposes an modified (m, n)-fault tolerance strategy (M-MNFT). Unlike the traditional one, which only considers ES failures, M-MNFT additionally selects redundant edge base stations to ensure task reliability during task migration, and takes into account the fact that the relative distance between the request and the base station is as small as possible when the request is sent, so as to avoid the impact of the edge base station failure on the Quality of Service (QoS) during task migration. In addition, we have performed extensive simulations to show that M-MNFT outperforms existing methods in terms of the number of delayed requests, on-time finish rate, and average waiting time.

Stochastic human motion prediction aims to forecast multiple plausible future motions given a single pose sequence from the past. Most previous works focus on designing elaborate losses to improve the accuracy, while the diversity is typically characterized by randomly sampling a set of latent variables from the latent prior, which is then decoded into possible motions. This joint training of sampling and decoding, however, suffers from posterior collapse as the learned latent variables tend to be ignored by a strong decoder, leading to limited diversity. Alternatively, inspired by the diffusion process in nonequilibrium thermodynamics, we propose MotionDiff, a diffusion probabilistic model to treat the kinematics of human joints as heated particles, which will diffuse from original states to a noise distribution. This process not only offers a natural way to obtain the "whitened'' latents without any trainable parameters, but also introduces a new noise in each diffusion step, both of which facilitate more diverse motions. Human motion prediction is then regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence. Specifically, MotionDiff consists of two parts: a spatial-temporal transformer-based diffusion network to generate diverse yet plausible motions, and a flexible refinement network to further enable geometric losses and align with the ground truth. Experimental results on two datasets demonstrate that our model yields the competitive performance in terms of both diversity and accuracy.

Let us rethink the real-world scenarios that require human motion prediction techniques, such as human-robot collaboration. Current works simplify the task of predicting human motions into a one-off process of forecasting a short future sequence (usually no longer than 1 second) based on a historical observed one. However, such simplification may fail to meet practical needs due to the neglect of the fact that motion prediction in real applications is not an isolated “observe then predict” unit, but a consecutive process composed of many rounds of such unit, semi-overlapped along the entire sequence. As time goes on, the predicted part of previous round has its corresponding ground truth observable in the new round, but their deviation in-between is neither exploited nor able to be captured by existing isolated learning fashion. In this paper, we propose DeFeeNet, a simple yet effective network that can be added on existing one-off prediction models to realize deviation perception and feedback when applied to consecutive motion prediction task. At each prediction round, the deviation generated by previous unit is first encoded by our DeFeeNet, and then incorporated into the existing predictor to enable a deviation-aware prediction manner, which, for the first time, allows for information transmit across adjacent prediction units. We design two versions of DeFeeNet as MLP-based and GRU-based, respectively. On Human3.6M and more complicated BABEL, experimental results indicate that our proposed network improves consecutive human motion prediction performance regardless of the basic model.

Motion capture (MoCap) technology aims to provide an accurate record of human motion, with specific potentials in activity analysis, human behavior understanding, as well as multimedia industries of animation production and special effects movies. However, because of joint occlusion and limitation of equipment precision, the raw motion data are often damaged, which severely hinders its downstream applications. The latest method relies on deep neural networks to reconstruct the underlying complete motion from the degraded observation, achieving remarkable results. Unfortunately, due to the non-enumerability of human motion, the trained model from large-scale training data often fails to comprehensively cover incomputable action categories, which may lead to a sharp decline in the performance of deep learning-based methods. To handle these limitations, we propose an untrained deep generative model, in which Graph Convolutional Networks (GCNs) are utilized to efficiently capture complicated topological relationships of human joints. We show that the untrained GCN architecture with randomly-initialized weights is sufficient to extract some low-level statistics for human motion reconstruction without any training process. Notably, the performance of our approach is comparable to that of those trained models, while its application is not restricted by the availability of training data or a pre-trained network. Moreover, the proposed model even surpasses the state-of-the-art methods when encountering unprecedented samples in the human action database, regardless of the tasks of human motion recovery and gap-filling problem.

Most existing researches on cloud workflow systems have focused on resource scheduling with the aims to minimize system delay under budget constraints or optimize system cost under deadline constraints. However, cloud providers cannot guarantee a failure-free cloud environment, a compact scheduling plan is prone to failure, thus, workflow system reliability has been identified as a critical and challenging issue in the volatile cloud environment. With the ability of cloud, it is easy for users to implement the active fault tolerance schemes, e.g., Scale-Out. However, it will lead to issues like security problem and extra management cost. In this paper, we first investigate Scale-Up and Scale-Hybrid schemes to fully explore the possibilities offered by the ability of cloud. We formally model the problem of optimizing the reliability of a cloud workflow system under budget constraints with these three fault-tolerance schemes. These optimization problems are discrete and non-convex. Thus, we propose a genetic algorithm based method for workflow fault tolerance (GA4WFT). Finally, we evaluate the effectiveness and efficiency of proposed GA4WFT with three different fault-tolerance schemes through experiments conducted on Amazon EC2 data.

This work presents a novel robust image compressive sensing reconstruction approach. In contrast to the existing work, we employ the truncated Cauchy loss function to measure the errors induced during the measurement, showing strong robustness to impulsive noise and outliers. To ensure high quality reconstructed images, we utilize a non-local low rank regularizer - with truncated Schatten-p norm being the surrogate function of rank - to capture the self-similar property inherent in most natural images. Considering the fact that the whole optimization model is neither convex nor smooth, to solve it effectively, we firstly use the half-quadratic strategy to transform the loss function into a quadratic objective by introducing some auxiliary variables, and then iteratively and alternatively optimize different groups of variables. Extensive experimental results demonstrate its effectiveness in terms of both quantitative indexes of Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity (SSIM), and visual quality under impulsive noise.

At present, a growing number of web applications especially cloud computing systems employ representational state transfer (REST) API as the interface to expose their services for simplicity and clarity. For security purposes, service providers prefer to control the access to the provided interface based on the principle of least privilege. However, how to divide the administrative privileges remains a difficulty in practice. In this work, we simplify the privilege partitioning problem into a classification problem of RESTful functions, so the permission to call a category of functions can be granted to a specific administrator. We propose a RESTful API classification approach called RestSep based on genetic algorithm. A classification is represented as a 2-dimensional matrix, which is used as the chromosome. Customized operators of selection, mutation and crossover are designed. The fitness function is designed to balance parameters such as number of categories, test case coverage, function overlapping, etc. Experiments on popular clouds like OpenStack and Kubernetes indicate RestSep can generate a self-explanatory classification result, which can serve as a guideline for privilege partitioning. The overhead of test generation is at most 13.1% and the overhead of genetic algorithm is at most 183.29s, which are acceptable for practical use.

The OWL-based Web Service ontology is one of the most important standards for semantic service composition. Performance analysis of composite service processes specified in OWL-S enables us to understand whether the process meet the SLA requirements. In this work, we propose a Petri-net-based formal framework for OWL-S processes using non-markovian-stochastic-petri-nets (NMSPN) as the intermediate representation. The main innovation of this research includes a translation from OWL-S to non-markovian-stochastic-petri-nets and a well-defined control flow model for composite services built on OWL-S.

Polarization imaging has advantages to reveal objective characteristics in foggy conditions. Quality assessment of polarization analysis images in imaging is rarely reported. A quality assessment method suitable to polarization analysis images in foggy conditions is proposed. Firstly, polarization characteristics in foggy conditions are analyzed. Three types of quality factors are selected, which are contrast factor based on brightness, the moment of inertia factor based on structure, and MSCN (Mean Subtracted Contrast Normalized) factor based on Stokes parameters. Corresponding assessment model is constructed, and pooling strategies are designed to map quality score of intensity of polarization image I and degree of polarization image P. Experiments on images captured by polarization camera in simulation foggy environment and generated by fog simulation of Photoshop. Results show that the proposed method is well consistent with subjective observation and analysis.

This paper uses multiple approximation model ensembles to solve a multi-input multi-output learning task. An ensemble is on behalf of a specified class, and composed of several multi-input single-output (MISO) approximation models. An MISO model may be either a multivariable cubic polynomial, or a multi-variable quartic polynomial, or a single-hidden-layer perceptron. The number of ensembles is equal to that of the existing classes, and all the members in an ensemble are trained only by the samples from the represented category. The ensemble in which all the members have the most identical viewpoint finally determines the label and position of one sample. The "most identical viewpoint" can be scaled by the corrected relative standard deviation. The proposed method is verified to be effective by a synthetic dataset.

Multiple factors combine to affect end users' success in learning to program. The goal of this research is to empirically investigate several factors that may predict learning to program in an introductory programming course for end users. The findings showed that software self-efficacy, programming self-efficacy, and computer playfulness were not direct predictors of successful programming; however, together they influenced computer interest, which in turn affected performance. The contribution of this paper is a model of the joint effects of a set of factors for end-user success in learning to program in a formal course setting.