Advances in image editing models have enabled intelligent, rapid fashion customization. Vision-guided editing models, in particular, offer more precise and flexible control over fine-grained garment attributes. However, existing methods are limited to coarse-grained edits and fail to achieve attribute-level manipulation, thereby restricting the flexibility and composability required in fashion customization. To address these issues, this paper proposes a Vision-Guided Fashion Fine-Grained Attribute Editing (VFFAE) framework, which leverages visual references to achieve customized editing of both style and structure in fine-grained garment regions. The VFFAE framework involves three key components: (1) a text-driven fashion fine-grained attribute segmenter that incorporates garment keypoints as spatial priors and applies deformable attention to enhance spatial perception, with CLIP-based multimodal alignment for accurate segmentation; (2) a clothing attribute disentanglement module based on orthogonal subspace projection of CLIP embeddings, enabling zero-shot explicit separation of style and structure attributes; and (3) a conditional diffusion pipeline that leverages disentangled representations of segmented regions to fine-tune a pretrained Stable Diffusion model under classifier-free guidance, enabling controllable attribute editing. Experiments on multiple public datasets show that VFFAE surpasses state-of-the-art methods, and ablation analyses confirm the effectiveness of its segmentation and disentanglement modules, establishing it as a practical solution for high-fidelity attribute-level fashion customization.

Enhancing large language models (LLMs) with external knowledge base retrieval in the fashion manufacturing industry can provide more reliable technical support and decision-making assistance, significantly improving process control and boosting intelligent production efficiency. However, the field of fashion manufacturing involves highly specialized terminology, logically complex technical knowledge, and intricate query tasks. Existing simple query-matching techniques often return a large number of contextually loose and redundant document chunks, severely impacting the model's understanding and response quality. To address this issue, this article proposes a retrieval optimization framework based on a dynamic capsule routing network with embedded semantic graph (SGDCR), which models semantic relations among multiple retrieved documents by simulating a team collaboration mechanism. Specifically, the framework consists of two steps: filtering and reranking. First, a capsule routing mechanism embedded in a semantic association graph dynamically captures complex contextual relationships among coarse-grained document blocks, learns contribution scores for multiple documents, and filters irrelevant or redundant documents based on ranking. Subsequently, the filtered documents are matched with the query through deep semantic similarity measurement, and the documents are reranked by integrating relevance scores and contribution scores and generating efficient, accurate, and contextually coherent document prompts. Experimental results on publicly available dense open-domain QA datasets and a constructed fashion manufacturing process QA dataset demonstrate the effectiveness and superiority of the proposed method over existing reranking approaches in the fashion manufacturing knowledge QA system.

This article presents a comprehensive theoretical analysis of the resilience demonstrated by the three-stage Doherty power amplifier (DPA) when operating under load mismatch conditions. Additionally, a novel reconfigurable three-stage DPA architecture is introduced, with the aim of enhancing resilience to load mismatch using exceptionally simple circuits and a one-dimensional (1D) control method. To validate the efficacy of this proposed architecture and control approach, a DPA prototype employing commercial gallium nitride (GaN) active devices has been designed and meticulously fabricated at 2 GHz. With a matched 50 Ω load, the fabricated three-stage DPA achieves a high-efficiency range of 9.5 dB with larger than 51% back-off drain efficiency (DE). Through the proposed 1D control, the DPA presents 47.0%–55.1% back-off efficiency with ≤ 2 dB power fluctuation at a 2:1 voltage standing wave ratio (VSWR) over a 360° phase span. When driven by a 20 MHz long-term evolution (LTE) signal with an 8 dB peak-to-average power ratio (PAPR), the DPA achieves 46.2%–53.9% average efficiency and better than −21 dBc adjacent channel power ratio (ACPR) without digital pre-distortion (DPD) under load mismatch conditions.

Software deployment misconfiguration often happens and has been one of the major causes of deployment failures that give rise to service interruptions. However, there is currently no existing approach to automatically repairing deployment failures. We propose DeployFix, which automatically repairs software deployment failures via constraint solving in the dynamic-changing deployment environments. DeployFix first defines DeployIR as a unified intermediate representation to achieve the translation of heterogeneous specifications from different schedulers with different syntaxes. By reducing the root-cause analysis of deployment failures to the conflict resolution in propositional logic, DeployFix uses off-the-shelf constraint solvers to achieve automatic localization and diagnosis of conflicting constraints, which are the root causes of deployment failures. DeployFix finally resolves the conflicting constraints and generates repaired deployment configurations in terms of practical requirements. We evaluate DeployFix in both simulation and production environments with tens of thousands of nodes at Alibaba, on which tens of thousands of applications are running guided by hundreds of thousands of deployment constraints. Experimental results demonstrate that DeployFix outperforms the state of the art and it correctly repairs the deployment failures in minutes, even in a large production data center.

This article presents a theoretical analysis and circuit design for an enhanced dual-mode reciprocal Doherty power amplifier (DM-RDPA). To achieve bandwidth enhancement, an improved combining load design strategy is proposed, providing more accurate back-off impedance across a wider target bandwidth. Additionally, a sweeping analysis method is developed to determine optimal design parameters. The enhanced combining load design space of the proposed DM-RDPA is visualized, providing an intuitive view of the appropriate impedance solution space. To validate this enhanced DM-RDPA architecture and the corresponding design analysis method, a prototype PA was designed and fabricated using commercial GaN transistors. The implemented PA achieves two different Doherty operation bands: 0.95-1.9 GHz (66.7% fractional bandwidth) in Mode I and 0.67-0.93 GHz (32.5% fractional bandwidth) in Mode II. Drain efficiency of 47.3%-62.2% and 44.7%-62.1% is obtained by the fabricated DPA at 6 dB back-off in Mode I and Mode II, respectively. When driven by a 20 MHz modulated signal with 8 dB peak to average power ratio (PAPR), the fabricated DPA presents higher than 42% average efficiency in both Mode I and Mode II.

Deepfakes is a branch of malicious techniques that transplant a target face to the original one in videos, resulting in serious problems such as infringement of copyright, confusion of information, or even public panic. Previous efforts for Deepfakes videos detection mainly focused on appearance features, which have a risk of being bypassed by sophisticated manipulation, also resulting high model complexity and sensitiveness to noise. Besides, how to mine the temporal features of manipulated videos and exploit them is still an open question. We propose an efficient and robust framework named LRNet for detecting Deepfakes videos through temporal modeling on precise geometric features. A novel calibration module is devised to enhance the precision of geometric features, making it more discriminative, and a two-stream Recurrent Neural Network (RNN) is constructed for sufficient exploitation of temporal features. Compared to previous methods, our proposed method is lighter-weighted and easier to train. Moreover, our method has shown robustness in detecting highly compressed or noise corrupted videos. Our model achieved 0.999 AUC on FaceForensics+ + dataset. Meanwhile, it has a graceful decline in performance (-0.042 AUC) when faced with highly compressed videos.1

The joint design of the multi-stream in MIMO relay sigle/multiple user system is investigated. Under the inter-stream interference, a constrained optimization problem with respect to the unknown relay precoder matrix is formulated with a goal of minimizing the total relay transmit power subject to quality of service (QoS) requirement on each data stream. As the original opitimization problem is non-convex, the matrix expression of the cost function and constrained requirement is converting to a scalar optimization problem and the optimal relay precoder and receive filter are obtained. The optimal design of the multiple user relay system under QoS requirement is also provided. By using a reasonable approximation and converting to the generalized Rayleigh form for the cost function, a suboptimal relay precoder matrix for QoS optimization with relay transmit power constraint is obtained. Simulation results demonstrate that for single user model, the minimize relay power will increase with Signal to Interference plus Noise Ratio(SINR) constraint value becoming larger, and for multiple users model, more users in our algorithm will make the MSE gain more obvious as increasing transmitting SNR.

This paper derives an asymptotic average symbol error rate (SER) expression for multiple-input multiple-output (MIMO) amplify-and-forward (AF) relay selection systems with optimal beamforming. The analysis at high SNR quantifies the diversity order and array gain, which are valid for any antenna numbers of the terminals and arbitrary channel fading models. It is also proved that the system performance is not only dominated by the number of relays and also by the weak hop with the smallest diversity. Our results based on the closed-form expressions provide valuable insights into the performance and practical design considerations of MIMO AF relay networks.

In this paper, the channel estimation related issues in FBMC systems are discussed. A single-symbol preamble structure is proposed and the corresponding channel estimation methods are provided for filter bank multicarrier (FBMC) systems. The simulation results show that compared with the existing methods, the proposed scheme achieves impressive performance gains (up to 4.0dB) with much smaller preamble resource overhead. This is obtained through effective channel filtering for the intrinsic imaginary interference and additive noise exploiting the sparse property of the channel response in delay domain. With the proposed solution, the FBMC system can even save half resources for pilots compared with OFDM systems.

By employing the amplify-and-forward relaying strategy, a relay selection method with simplified precoding is proposed for two-hop multi-relay channels. The proposed method consists of two parts. In the first part, the authors present an optimal beamforming scheme with full channel state information (CSI) and derive a simplified and analytic expression for the output SNR through each relay, thereby selecting the best relay. The second part considers the transmiit precoding problem with the CSI known to the receiver only and provide a selection strategy with Grassmannian beamforming. The new algorithm chooses only one relay based on the maximal received SNR to assist in transmission. It can significantly reduce the system consumption, achieve excellent bit-error-rate and average throughput and maintain full diversity order. Simulation results demonstrate that the performance of the proposed schemes with low complexity approaches towards the optimal iteration method. For practical situations with a distance attenuation factor, the performance gain of the authors schemes is also evident.