Although data-driven methods have achieved success in 3D human pose estimation, they often suffer from domain gaps and exhibit limited generalization. In contrast, optimization-based methods excel in fine-tuning for specific cases but are generally inferior to data-driven methods in overall performance. We observe that previous optimization-based methods commonly rely on projection constraint, which only ensures alignment in 2D space, potentially leading to the overfitting problem. To address this, we propose an Uncertainty-Aware testing-time Optimization (UAO) framework, which keeps the prior information of pre-trained model and alleviates the overfitting problem using the uncertainty of joints. Specifically, during the training phase, we design an effective 2D-to-3D network for estimating the corresponding 3D pose while quantifying the uncertainty of each 3D joint. For optimization during testing, the proposed optimization framework freezes the pre-trained model and optimizes only a latent state. Projection loss is then employed to ensure the generated poses are well aligned in 2D space for high-quality optimization. Furthermore, we utilize the uncertainty of each joint to determine how much each joint is allowed for optimization. The effectiveness and superiority of the proposed framework are validated through extensive experiments on challenging datasets: Human3.6M, MPI-INF-3DHP, and 3DPW. Notably, our approach outperforms the previous best result by a large margin of 5.5% on Human3.6M.

In video-based emotion recognition, effective multi-modal fusion techniques are essential to leverage the complementary relationship between audio and visual modalities. Recent attention-based fusion methods are widely leveraged for capturing modal-shared properties. However, they often ignore the modal-specific properties of audio and visual modalities and the unalignment of model-shared emotional semantic features. In this paper, an Attention Aggregation Network (AttA-NET) is proposed to address these challenges. An attention aggregation module is proposed to get modal-shared properties effectively. This module comprises similarity-aware enhancement blocks and a contrastive loss that facilitates aligning audio and visual semantic features. Moreover, an auxiliary uni-modal classifier is introduced to obtain modal-specific properties, in which intra-modal discriminative features are fully extracted. Under joint optimization of uni-modal and multi-modal classification loss, modal-specific information can be infused. Extensive experiments on RAVDESS and PKU-ER datasets validate the superiority of AttA-NET. The code is available at: https://github.com/NariFan2002/AttA-NET.

Due to the challenging propagation characteristics, 5G positioning signal will be significantly affected when encountering obstacles or reflectors during propagation, resulting in a heavy degradation in positioning accuracy. This paper proposes an enhanced Time Difference of Arrival (TDoA) method for 5G real-time indoor localization with clustering. This unsupervised method can achieve reliable and precise positioning through time alignment error (TAE) calibration, combinational data expansion, two-stage filtering and clustering. An empirical evaluation is conducted using an open dataset generated in a real-world office scenario. Experimental results demonstrate that the proposed method can perform well in environments containing obvious Non-Line-of-Sight (NLoS) conditions. The best algorithm achieves an average accuracy of 0.763 m, which improves 58.3% compared with the classical multi-base station localization algorithm-Weighted Least Squares.

Human Mesh Reconstruction (HMR) from monocular video plays an important role in human-robot interaction and collaboration. However, existing video-based human mesh reconstruction methods face a trade-off between accurate reconstruction and smooth motion. These methods design networks based on either RNNs or attention mechanisms to extract local temporal correlations or global temporal dependencies, but the lack of complementary long-term information and local details limits their performance. To address this problem, we propose a Dual-branch Graph Transformer network for 3D human mesh Reconstruction from video, named DGTR. DGTR employs a dual-branch network including a Global Motion Attention (GMA) branch and a Local Details Refine (LDR) branch to par-allelly extract long-term dependencies and local crucial information, helping model global human motion and local human details (e.g., local motion, tiny movement). Specifically, GMA utilizes a global transformer to model long-term human motion. LDR combines modulated graph convolutional networks and the transformer framework to aggregate local information in adjacent frames and extract crucial information of human details. Experiments demonstrate that our DGTR outperforms state-of-the-art video-based methods in reconstruction accuracy and maintains competitive motion smoothness. Moreover, DGTR utilizes fewer parameters and FLOPs, which validate the effectiveness and efficiency of the proposed DGTR. Code is publicly available at https://github.com/TangTao-PKU/DGTR.

Although existing video-based 3D human mesh recovery methods have made significant progress, simultaneously estimating human pose and shape from low-resolution image features limits their performance. These image features lack sufficient spatial information about the human body and contain various noises (e.g., background, lighting, and clothing), which often results in inaccurate pose and inconsistent motion. Inspired by the rapid advance in human pose estimation, we discover that compared to image features, skeletons inherently contain accurate human pose and motion. Therefore, we propose a novel semiAnalytical Regressor using disenTangled Skeletal representations for human mesh recovery from videos, called ARTS. Specifically, a skeleton estimation and disentanglement module is proposed to estimate the 3D skeletons from a video and decouple them into disentangled skeletal representations (i.e., joint position, bone length, and human motion). Then, to fully utilize these representations, we introduce a semi-analytical regressor to estimate the parameters of the human mesh model. The regressor consists of three modules: Temporal Inverse Kinematics (TIK), Bone-guided Shape Fitting (BSF), and Motion-Centric Refinement (MCR). TIK utilizes joint position to estimate initial pose parameters and BSF leverages bone length to regress bone-aligned shape parameters. Finally, MCR combines human motion representation with image features to refine the initial human model parameters. Extensive experiments demonstrate that our ARTS surpasses existing state-of-the-art video-based methods in both per-frame accuracy and temporal consistency on popular benchmarks: 3DPW, MPI-INF-3DHP, and Human3.6M. Code is available at https://github.com/TangTao-PKU/ARTS.

Real time and highly robust localization is essential for location-based services and autonomous driving. Nevertheless, it is hard to obtain high-quality observations from these vehicle-level positioning sensors because of the uncertainty of urban environment and conditions, which affects the localization performance. In this study, we propose an adaptive optimal selection-robust hybrid adaptive Kalman filter (AOS-RHAKF) method of combination data from BeiDou navigation satellite system (BDS)/the fifth-generation (5G) network to achieve high-accuracy positioning estimation in urban complex environment. The proposed method is mainly composed of three sequential modules, namely, initial positioning estimation, AOS-based 5G base stations (BSs) measurement data optimization and BDS/5G combined positioning. Initial positioning estimation uses the raw measurement data and the basic mathematical model with position estimation to work out the mobile vehicle position. The AOS-based 5G BSs measurement data optimization module achieves better reselection of observation data through the adaptive optimal selection factor. The BDS/5G combined positioning method utilizes the optimized 5G data and BDS to establish a tightly coupled structure model, and then achieves high-precision positioning of mobile vehicles using RHAKF method. Finally, both simulations and actual driving test were carried out. The results show that the proposed AOS-RHAKF method significantly improves the positioning accuracy compared with the BDS, 5G-only, and BDS/5G loose coupling positioning using the raw measurement data.

Despite substantial progress in 3D human pose estimation from a single-view image, prior works rarely explore global and local correlations, leading to insufficient learning of human skeleton representations. To address this issue, we propose a novel Interweaved Graph and Attention Network (IGANet) that allows bidirectional communications between graph convolutional networks (GCNs) and attentions. Specifically, we introduce an IGA module, where attentions are provided with local information from GCNs and GCNs are injected with global information from attentions. Additionally, we design a simple yet effective U-shaped multi-layer perceptron (uMLP), which can capture multi-granularity information for body joints. Extensive experiments on two popular benchmark datasets (i.e. Human3.6M and MPI-INF-3DHP) are conducted to evaluate our proposed method. The results show that IGANet achieves state-of-the-art performance on both datasets. Code is available at https://github.com/xiu-cs/IGANet.

3D human mesh recovery from a 2D pose plays an important role in various applications. However, it is hard for existing methods to simultaneously capture the multiple relations during the evolution from skeleton to mesh, including joint-joint, joint-vertex and vertex-vertex relations, which often leads to implausible results. To address this issue, we propose a novel solution, called GATOR, that contains an encoder of Graph-Aware Transformer (GAT) and a decoder with Motion-Disentangled Regression (MDR) to explore these multiple relations. Specifically, GAT combines a GCN and a graph-aware self-attention in parallel to capture physical and hidden joint-joint relations. Furthermore, MDR models joint-vertex and vertex-vertex interactions to explore joint and vertex relations. Based on the clustering characteristics of vertex offset fields, MDR regresses the vertices by composing the predicted base motions. Extensive experiments show that GATOR achieves state-of-the-art performance on two challenging benchmarks. Code is available at https://github.com/kasvii/GATOR.

Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging. Existing video-based methods generally recover human mesh by estimating the complex pose and shape parameters from coupled image features, whose high complexity and low representation ability often result in inconsistent pose motion and limited shape patterns. To alleviate this issue, we introduce 3D pose as the intermediary and propose a Pose and Mesh Co-Evolution network (PMCE) that decouples this task into two parts: 1) video-based 3D human pose estimation and 2) mesh vertices regression from the estimated 3D pose and temporal image feature. Specifically, we propose a two-stream encoder that estimates mid-frame 3D pose and extracts a temporal image feature from the input image sequence. In addition, we design a co-evolution decoder that performs pose and mesh interactions with the image-guided Adaptive Layer Normalization (AdaLN) to make pose and mesh fit the human body shape. Extensive experiments demonstrate that the proposed PMCE outperforms previous state-of-the-art methods in terms of both per-frame accuracy and temporal consistency on three benchmark datasets: 3DPW, Human3.6M, and MPI-INF-3DHP. Our code is available at https://github.com/kasvii/PMCE.

Self-supervised 3D skeleton representation learning has recently shown great potential for action recognition via contrastive learning. However, existing methods suffer from limited learning efficiency and the unreliability of representations, which is not conducive to action recognition. To this end, we propose an Active Sampling and Adaptive Relabeling (ASAR) contrastive learning method to achieve efficient and reliable learning of 3D skeleton representations. Specifically, the active sampling strategy is used to build a dictionary with informative samples for efficient representation learning. Additionally, the adaptive relabeling strategy is proposed to automatically modify the confidence scores of the extra positive samples and alleviate the unreliability of representations. Extensive experiments on NTU-60, NTU-120, and PKU-MMD datasets demonstrate the superiority of our approach.

Traffic flow prediction is an essential task in constructing smart cities and is a typical Multivariate Time Series (MTS) Problem. Recent research has abandoned Gated Recurrent Units (GRU) and utilized dilated convolutions or temporal slicing for feature extraction, and they have the following drawbacks: (1) Dilated convolutions fail to capture the features of adjacent time steps, resulting in the loss of crucial transitional data. (2) The connections within the same temporal slice are strong, while the connections between different temporal slices are too loose. In light of these limitations, we emphasize the importance of analyzing a complete time series repeatedly and the crucial role of GRU in MTS. Therefore, we propose SGRU: Structured Gated Recurrent Units, which involve structured GRU layers and non-linear units, along with multiple layers of time embedding to enhance the model’s fitting performance. We evaluate our approach on four publicly available California traffic datasets: PeMS03, PeMS04, PeMS07, and PeMS08 for regression prediction. Experimental results demonstrate that our model outperforms baseline models with average improvements of 11.7%, 18.6%, 18.5%, and 12.0% respectively.

Abstract As a promising service paradigm, cloud computing has attracted lots of enterprises and individuals to outsource big data to public cloud. To facilitate secure data using and sharing, ciphertext-policy attribute-based encryption (CP-ABE) is a suitable solution, which can provide fine-grained access control and encryption functionalities simultaneously. However, some serious challenges are still remaining toward achieving flexible and controllable access policy update in CP-ABE, which essentially impede the powerful access control ability of CP-ABE from long-term and large-scale deployment in real systems. In this work, we propose a novel scheme named policy updatable CP-ABE for encrypted data sharing scenes. The proposed scheme features the following achievements: (i) it supports fine-grained update algorithms with no restriction on update time; (ii) the cloud server can effectively verify update ciphertexts, so the integrity of original data would not be compromised intentionally or accidentally during the update and (iii) most operations of encryption and policy update are securely outsourced to cloud servers, leaving extremely low overheads for data owners and users. We formally define its security model and prove it is adaptively secure. Also, we implement the proposed scheme using the Charm framework. The experiment results demonstrate that it is efficient and practical.

Many enterprises and individuals prefer to outsource data to public cloud via various pricing approaches. One of the most widely-used approaches is the pay-as-you-go model, where the data owner hires public cloud to share data with data consumers, and only pays for the actually consumed services. To realize controllable and secure data sharing, ciphertext-policy attribute-based encryption (CP-ABE) is a suitable solution, which can provide fine-grained access control and encryption functionalities simultaneously. But there are some serious challenges when applying CP-ABE in pay-as-you-go. First, the decryption cost in ABE is too heavy for data consumers. Second, ABE ciphertexts probably suffer distributed denial of services (DDoS) attacks, but there is no solution that can eliminate the security risk. At last, the data owner should audit resource consumption to guarantee the transparency of charge, while the existing method is inefficient. In this work, we propose a general construction named fully accountable ABE (FA-ABE), which simultaneously solves all the challenges by supporting all-sided accountability in the pay-as-you-go model. We formally define the security model and prove the security in the standard model. Also, we implement an instantiate construction with the self-developed library$\mathsf{ libabe}$. The experiment results indicate the efficiency and practicality of our construction.

This paper presents a mobile solution for the management of chronic diseases, i.e. hypertension and diabetes. This solution facilitates the exchange of health information between patients and pharmacists, supports wellness decision making, and assists behavioral interventions for enhanced self-management and healthcare delivery. Since the beginning of 2015, we have deployed the Software as a Service (SaaS) solution in 3,000 drug stores around China. The one-year trial demonstrated significant improvements in the real-world evidence outcome.

Image segmentation can be used in non-destructive testing, tracking and recognition. Level set method for image segmentation has poor performance on efficiency. In this paper, we propose to use max-flow algorithm to optimize a locally improved Chan-Vese model for image segmentation in the presence of intensity inhomogeneity. The energy function of local Chan-Vese model is introduced firstly. This model consists of global term, local term and penalty term and the local term contributes the segmentation for images with intensity inhomogeneity. Then, we convert this energy function to the frame of Graph Cut whose energy function can be efficiently minimized by max-flow algorithm. As a result, the process of optimization of local Chan-Vese model can be accelerated by using max-flow algorithm. The experiments demonstrate that the proposed method can achieve satisfactory segmentation for images with intensity inhomogeneity as well as very high efficiency.