Online action detection and anticipation aim to understand current or upcoming actions in video streams. In industry, current artificial neural network (ANN)-based methods suffer from prohibitive energy consumption, fundamentally limiting their deployment on resource-constrained industrial devices. To bridge the gap between theory and application practice of informatics in industrial environments, we propose a novel knowledge distillation-based spiking neural network (KDSNN), which synergistically integrates bioinspired spike-driven processing with knowledge distillation, significantly reducing the energy consumption. Specifically, KDSNN includes a pioneering spiking neural network (SNN) architecture for online action detection and anticipation, which combines well-designed hierarchical spike convolutional neural network (CNN) block and spike Transformer block to capture spike-driven information. To further improve the performance of our SNN while maintaining low energy consumption, we introduce the knowledge distillation paradigm, which aims to utilize an expert-level ANN as a teacher to guide our SNN. Based on this, we propose a novel distillation loss, which consists of feature distillation and logit distillation. Notably, to address the cross-domain feature alignment in feature distillation, the optimal transport theory is employed to realize cross-domain knowledge transfer for the first time by minimizing the Wasserstein distance between continuous features (ANNs) and discrete features (SNNs). Through extensive evaluations on THUMOS14 and EPIC-Kitchen-100 datasets, the energy consumption of our KDSNN is only 27.1% and 10.0% of the state-of-the-art ANN-based method MAT. Equally importantly, the parameter count of our KDSNN is only 37.0% and 27.7% of MAT on THUMOS14 and EPIC-Kitchen-100, respectively.

Unsupervised person re-identification (ReID) aims to learn identity-discriminative representations without manual annotations, which is challenging due to noisy pseudo labels, background clutter, and large appearance variations. Recent studies have shown that exploiting fine-grained local cues is crucial for improving robustness in unsupervised ReID. In this context, random masking has emerged as a simple and annotation-free way to encourage the model to focus on informative regions. However, existing masking-based unsupervised ReID methods still suffer from two limitations: (1) Underused masked views: masked views are treated as degraded auxiliaries rather than exploited as fine-grained supervisory signals; (2) Weak cross-view alignment: feature alignment is restricted to mini-batch pairs, lacking explicit global alignment between masked and unmasked views across clusters. To address these issues, we propose the Mask-guided Asymmetric Contrastive and Semantic Alignment (ACSA) framework. Specifically, we introduce an Asymmetric Contrastive Learning (ACL) module with a dual-memory mechanism to separately encode masked and unmasked features, allowing masked views to serve as informative and discriminative supervision. In parallel, a Semantic Alignment Learning (SAL) module conducts multi-granularity distribution alignment by aligning both cluster-level prototypes and randomly sampled instance-level features, thereby preserving semantic consistency and intra-cluster diversity. Furthermore, to provide more reliable semantic anchors for SAL under noisy pseudo labels, we introduce a Progressive Refinement Module (PRM), which refines prototypes and features via exponential moving averaging for more stable semantic alignment. Extensive experiments validate the superiority of our method, even outperforming certain supervised counterparts. Code is available at https://github.com/Trangle12/ACSA.

Unsupervised person re-identification (USL-ReID) typically relies on clustering to generate pseudo-labels, but significant cross-view appearance variations often cause images of the same identity to be split into different clusters. Training on such noisy pseudo-labels severely degrades the learned representations. Therefore, learning robust view-invariant features is paramount. Data augmentation provides a direct way to enhance invariance, yet its trade-offs in USL-ReID remain under-explored: weak augmentations usually preserve identity semantics but lack diversity, whereas strong augmentations provide richer appearance diversity at the cost of partially corrupting identity-consistent semantic cues. To address this challenge, we propose Invariant Representation learning with Progressive Prototype Refinement (IRPP), a unified framework that learns invariant and discriminative features from noisy pseudo-labels. IRPP consists of three synergistic components. First, an Augmented Dual-Contrastive Learning (ADCL) module performs dataset-level prototype-guided invariant learning by contrasting weakly and strongly augmented views against cluster-derived prototypes. Second, an Alignment and Uniformity Learning (AUL) module regularizes the mini-batch-level weak-strong feature geometry, leading to more stable feature distributions under data augmentation. Third, a Progressive Prototype Refinement (PPR) mechanism progressively optimizes cluster centroids into cleaner prototypes, thereby mitigating the influence of noisy pseudo-labels and further strengthening invariant representation learning. This closed-loop design enables prototype-guided contrastive learning, weak-strong regularization, and prototype refinement to mutually reinforce each other. Extensive experiments on standard USL-ReID benchmarks demonstrate that IRPP achieves state-of-the-art performance with a simple and efficient training pipeline. Code is available at https://github.com/Trangle12/IRPP.

Unsupervised Domain Adaptation (UDA) person search aims to adapt models trained on labeled source data to unlabeled target domains. Existing approaches typically rely on clustering-based proxy learning, but their performance is often undermined by unreliable pseudo-supervision. This unreliability mainly stems from two challenges: (i) spectral shift bias, where low- and high-frequency components behave differently under domain shifts but are rarely considered, degrading feature stability; and (ii) static proxy updates, which make clustering proxies highly sensitive to noise and less adaptable to domain shifts. To address these challenges, we propose the Reliable Pseudo-supervision in UDA Person Search (RPPS) framework. At the feature level, a Dual-branch Wavelet Enhancement Module (DWEM) embedded in the backbone applies discrete wavelet transform (DWT) to decompose features into low- and high-frequency components, followed by differentiated enhancements that improve cross-domain robustness and discriminability. At the proxy level, a Dynamic Confidence-weighted Clustering Proxy (DCCP) employs confidence-guided initialization and a two-stage online-offline update strategy to stabilize proxy optimization and suppress proxy noise. Extensive experiments on the CUHK-SYSU and PRW benchmarks demonstrate that RPPS achieves state-of-the-art performance and strong robustness, underscoring the importance of enhancing pseudo-supervision reliability in UDA person search. Our code is accessible at https://github.com/zqx951102/RPPS.

Translating brain activity into meaningful visual content has long been recognized as a fundamental challenge in neuroscience and brain-computer interface research. Recent advances in EEG-based neural decoding have shown promise, yet two critical limitations remain in this area: poor generalization across subjects and constraints to specific visual tasks. We introduce NEED, the first unified framework achieving zero-shot cross-subject and cross-task generalization for EEG-based visual reconstruction. Our approach addresses three fundamental challenges: (1) cross-subject variability through an Individual Adaptation Module pretrained on multiple EEG datasets to normalize subject-specific patterns, (2) limited spatial resolution and complex temporal dynamics via a dual-pathway architecture capturing both low-level visual dynamics and high-level semantics, and (3) task specificity constraints through a unified inference mechanism adaptable to different visual domains. For video reconstruction, NEED achieves better performance than existing methods. Importantly, Our model maintains 93.7% of within-subject classification performance and 92.4% of visual reconstruction quality when generalizing to unseen subjects, while achieving an SSIM of 0.352 when transferring directly to static image reconstruction without fine-tuning, demonstrating how neural decoding can move beyond subject and task boundaries toward truly generalizable brain-computer interfaces.

The federated Fuzzy C-means (federated FCM) extends the traditional Fuzzy C-means (FCM) to the federated learning (FL) scenario, aiming to address the data privacy preservation issue of soft clustering in distributed environments. However, a significant challenge persists with existing federated FCM algorithms, i.e., they struggle to converge effectively in complex heterogeneous scenarios, leading to unstable clustering outcomes. Here the complex heterogeneous scenarios stem from the combination of non-independently and identically distributed (non-IID) data across different clients (statistical heterogeneity), coupled with the involvement of only some clients in each iteration (systematic heterogeneity). While prior research has attempted to address the impact of statistical heterogeneity in FL scenarios, it has overlooked the issue of system heterogeneity. In response, this paper proposes a novel federated FCM algorithm (SC-FFCM) that remains robust even in such complex heterogeneous scenarios. Firstly, the client-side clustering module of SC-FFCM adopts a Gradient-Based FCM algorithm, facilitating corrections to the direction of local optimization. Secondly, the algorithm introduces a control variates technique to rectify update bias during the iteration process, thereby mitigating the adverse effects of random client sampling and non-IID data distribution on the algorithm convergence. Finally, the proposed algorithm approximates the ideal federated FCM algorithm. Experimental studies verify the effectiveness of the proposed method. The source code of the proposed SC-FFCM algorithm is available from the following website https://github.com/Creazy-MR/SC-FFCM.

Satellite communication plays an important role in the ubiquitous global communication. However, for a long time, the communication provided by satellite suffers from serious signal attenuation and transmission delay. Conventional techniques such as HARQ couldn't provide timely service unless powerful channel codes are used. Once channel code fails, retransmission will be inevitable, and unbearable delay may be incurred. Fortunately, things started to change when Luby proposed the landmark LT code. As a practical implementation of fountain code, LT code avoids frequent feedback during the transmission. However, due to the high packet error rate (PER), the original LT code couldn't work stably in satellite communication. In this paper, we propose a novel hybrid decoding scheme for LT code. It consists of two decoding procedures: normal decoding using BP algorithm and mining decoding. The idea behind mining decoding is to release as many corrupted original packets as possible and combine the "identical" ones as in HARQ. Actually we develop three types of packet mining techniques to make a tradeoff between performance and computation complexity. The final simulation shows that, the proposed hybrid decoding scheme makes LT code work more stably, and achieves significant advantages over HARQ in terms of delay.

This paper treats the kinematic control of manipulators with redundant degrees of freedom. We derive an analytical solution for the inverse kinematics that provides a means for accommodating joint velocity constraints in real time. We define the motion optimizability measure and use it to develop an efficient method for the optimization of joint trajectories subject to multiple criteria. An implementation of the method for a 7-dof experimental redundant robot is present.

Grasping robotic hands is classified into three categories based on the object connectivity. We decompose the space of contact forces into four subspaces and develop a method to determine the dimensions of the subspaces with respect to the connectivity of the grasped object. The relationships we obtain reveal the kinematic and static characteristics of three categories of grasps. It indicates how contact forces can be decomposed corresponding to each type of grasp. The technique also provides a guideline for determining the distribution of contact forces on grasped objects. We analyze how power grasps are identified from the object connectivity and used to synthesize hand configurations for grasping and manipulation tasks. A physical interpretation of the subspaces and the determination of their dimensions are illustrated by examples.

This system is mainly composed of an industrial robot, dexterous hand (BH-3), graphic simulation and planning module, 6-DOF teleoperated mechanical arm (BH-TMA) and data glove with 5-fingered 11-DOF (BHG-3), etc. It consists of vision, force, torque, fiber, angle, and fingertip tactile sensors. In order to implement some complex operations in the integrated system, we propose a task-oriented hierarchical control share model. Moreover, we also express our viewpoints about share control in the teleoperated system. Finally, the experimental and simulative results are given to show that the share control construction is highly efficiency and effective.

This paper introduces the research on robot assisted, minimally invasive neurosurgery. The prototype system developed is composed of a preoperative image-guided planning, the minimal-invasive and noninvasive calibration between the virtual and actual environments, and a surgical robot for location and remote-controlled procedures based on the preoperative strategy. Finally, results of the clinical application are given to show that the robotic system is effective.

To realize control of robotic manipulators with redundant degrees of freedom, the concept of a motion optimizability measure is introduced. We derive an optimal solution technique for the inverse kinematics of a redundant robot that achieves real-time control with multiple performance criteria. Using this technique, we propose an efficient method for kinematic control. Experimental results are presented for a 7 DOF manipulator.

The stability and the end-task self-motion are important and difficult points. To solve these difficulties that exist in dynamic optimization of redundant manipulators, the paper researches the inner relation and contradictory conflict between the dynamic optimization and the joint velocities, and a new idea to raise the general quality of dynamic optimization by means of optimizing joint velocities is presented. A scheme resulting from adjusting an homogeneous joint velocity item in real-time is developed to effectively improve stability and joint velocities at end of motion to be near zero. Computer simulation verified the proposed approach to be very useful and efficient.

Redundant robots are characterized by dexterity, to overcome the difficulty of calculation when traditional manipulability is used for dexterity control, the paper researches the inner relation and contradictory conflict of the unity which consists of joint geometrical positions, orientations and joint velocities. A new idea to improve the weighted manipulability ellipsoid by optimizing joint velocities is presented thus geometrical position and orientation of the robot may be indirectly optimized by means of the feedback of joint velocities. Simulation verifies this scheme is very useful for real time control because of its simple arithmetic.

To realize the control of redundant manipulators, the concept of the motion optimizability measure is introduced. We derive an analytical solution technique for the inverse kinematics of a redundant robot that reduces the computational complexity and does not require the pseudoinverse Jacobian. Based on this technique, we propose an efficient, kinematic optimal control scheme. We show how to incorporate multiple criteria in the formulation. An online implementation of the system that ensures stable operation is presented.>

This research concerns the relationship between distance accuracy and positioning accuracy for robotic manipulators. We propose an approach for calibration and verification of the positioning accuracy based on a polynomial approximation to the workspace. Utilizing singular value decomposition a method is developed for distance error compensation. Computed results show that the distance accuracy and positioning accuracy of the robot can be improved by use of the proposed technique. The technique is illustrated for a PUMA 560 industrial robot.>

A fast and simple algorithm for determining optimal grasps of a planar multifingered robotic hand is presented. Using a representation for the stiffness of a planar grasp system, the authors derive conditions for static equilibrium, task-oriented grasping, and stability. An optimization model for determining optimal grasps of a planar multifingered hand is established using a quality measure which includes the effect of the external disturbing forces and moments. A constrained gradient descent technique is used to compute the optimal grasps. An example demonstrates the applicability and effectiveness of the theory.>