Existing Transformer- or Mamba-based low-light image enhancement (LLIE) methods can capture long-range dependencies in images and achieve global degradation restoration, but suffer from insufficient detail recovery. Besides, these methods do not consider the different illumination levels in various regions or enhance the regional illumination accordingly. Furthermore, existing denoising methods often overfit to single noise distribution and type, showing poor generalization to the noises in low-light images. To address these issues, we propose an Illumination-guided Grouped Attention (IGA) module and a Masked Progressive Denoising (MPD) module for low-light image enhancement. The IGA module first improves the local feature representation through detail recovery operations, and then iteratively groups the image representation based on the illumination levels and conducts grouped attention to achieve both fine detail recovery and adaptive regional illumination optimization. The MPD module explores correlations within and among regions to enhance the texture and structure representations from a local to global perspective, thus achieving both local and global denoising and well denoising generalization capability. Extensive quantitative and qualitative experiments on eight datasets demonstrate that our proposed method outperforms the existing state-of-the-art low-light image enhancement methods. Furthermore, plugging our proposed IGA and MPD modules into existing Transformer- or Mamba-based LLIE methods can significantly improve their performance, further demonstrating the modules' ability to address the common issues in such methods.

Existing low-light image enhancement (LLIE) and joint LLIE and deblurring (LLIE-deblur) models have made strides in addressing predefined degradations, yet they are often constrained by dynamically coupled degradations. To address these challenges, we introduce a Unified Receptance Weighted Key Value (URWKV) model with multi-state perspective, enabling flexible and effective degradation restoration for low-light images. Specifically, we customize the core URWKV block to perceive and analyze complex degradations by leveraging multiple intra- and inter-stage states. First, inspired by the pupil mechanism in the human visual system, we propose Luminance-adaptive Normalization (LAN) that adjusts normalization parameters based on rich inter-stage states, allowing for adaptive, scene-aware luminance modulation. Second, we aggregate multiple intra-stage states through exponential moving average approach, effectively capturing subtle variations while mitigating information loss inherent in the single-state mechanism. To reduce the degradation effects commonly associated with conventional skip connections, we propose the State-aware Selective Fusion (SSF) module, which dynamically aligns and integrates multi-state features across encoder stages, selectively fusing contextual information. In comparison to state-of-the-art models, our URWKV model achieves superior performance on various benchmarks, while requiring significantly fewer parameters and computational resources. Code is available at: https://github.com/FZU-N/URWKV.

Pedestrian attribute recognition (PAR) seeks to predict multiple semantic attributes associated with a specific pedestrian. There are two types of approaches for PAR: unimodal framework and bimodal framework. The former one is to seek a robust visual feature. However, the lack of exploiting semantic feature of linguistic modality is the main concern. The latter one utilizes prompt learning techniques to integrate linguistic data. However, static prompt templates and simple bimodal concatenation cannot to capture the extensive intra-class attribute variability and support active modalities collaboration. In this paper, we propose an Enhanced Visual-Semantic Interaction with Tailored Prompts (EVSITP) framework for PAR. We present an Image-Conditional Dual-Prompt Initialization Module (IDIM) to adaptively generate context-sensitive prompts from visual inputs. Subsequently, a Prompt Enhanced and Regularization Module (PERM) is proposed to strengthen linguistic information from IDIM. We further design a Bimodal Mutual Interaction Module (BMIM) to ensure bidirectional modalities communication. In addition, existing PAR datasets are collected over a short period in limited scenarios, which do not align with real-world scenarios. Therefore, we annotate a long-term person re-identification dataset to create a new PAR dataset, Celeb-PAR. Experiments on several challenging PAR datasets show that our method outperforms state-of-the-art approaches.

Pedestrian Attribute Recognition (PAR) plays a crucial role in various computer vision applications, demanding precise and reliable identification of attributes from pedestrian images. Traditional PAR methods, though effective in leveraging attention mechanisms, often suffer from the lack of direct supervision on attention, leading to potential overfitting and misallocation. This paper introduces a novel and model-agnostic approach, Attention-Aware Regularization (AAR), which rethinks the attention mechanism by integrating causal reasoning to provide direct supervision of attention maps. AAR employs perturbation techniques and a unique optimization objective to assess and refine attention quality, encouraging the model to prioritize attribute-specific regions. Our method demonstrates significant improvement in PAR performance by mitigating the effects of incorrect attention and fostering a more effective attention mechanism. Experiments on standard datasets showcase the superiority of our approach over existing methods, setting a new benchmark for attention-driven PAR models.

Pedestrian attribute recognition (PAR) involves accurately identifying multiple attributes present in pedestrian images. There are two main approaches for PAR: part-based method and attention-based method. The former relies on existing segmentation or region detection methods to localize body parts and learn corresponding attribute-specific feature from the corresponding regions, where the performance heavily depends on the accuracy of body region localization. The latter adopts the embedded attention modules or transformer attention to exploit detailed feature. However, it can focus on certain body regions but often provide coarse attention, failing to capture fine-grained details, the learned feature may also be interfered with by irrelevant information. Meanwhile, these methods overlook the global contextual information. This work argues for replacing coarse attention with detailed attention and integrating it with global contextual feature from ViT to jointly represent attribute-specific regions. To tackle this issue, we propose a High-order Diversity Feature Learning (HDFL) method for PAR based on ViT. We utilize a polynomial predictor to design an Attribute-specific Detailed Feature Exploration (ADFE) module, which can construct the high-order statistics and gain more fine-grained feature. Our ADFE module is a parameter-friendly method that provides flexibility in deciding its utilization during the inference phase. A Soft-redundancy Perception Loss (SPLoss) is proposed to adaptively measure the redundancy between feature of different orders, which can promote diverse characterization of features. Experiments on several PAR datasets show that our method achieves a new state-of-the-art (SOTA) performance. On the most challenging PA100K dataset, our method outperforms previous SOTA by 1.69% and achieves the highest mA of 84.92%.

Multi-label Pedestrian Attribute Recognition (PAR) involves identifying a series of semantic attributes in person images. Existing PAR solutions typically rely on CNN as the backbone network to extract pedestrian features. Unfortunately, CNNs process only one adjacent region at a time, resulting in the disappearance of long-range relations between different attribute-specific regions. To address this limitation, we adopt the Vision Transformer (ViT) instead of CNN as the backbone for PAR, aiming to build long-range relations and extract more robust features. However, PAR suffers from an inherent attribute imbalance issue, causing ViT to naturally focus more on attributes that appear frequently in the training set and ignore some pedestrian attributes that appear less. The native features extracted by ViT are not able to tolerate the imbalance attribute distribution issue. To tackle this issue, we propose a novel component and a dual-level loss: the Selective Feature Activation Method (SFAM), the Orthogonal Feature Activation Loss (OFALoss), and Orthogonal Weight Regularization Loss (OWRLoss). SFAM smartly suppresses the more informative attribute-specific features, thus compelling the PAR model to pay greater attention to attribute-specific regions that are often overlooked. The proposed OFALoss enforces an orthogonal constraint on the original feature extracted by ViT and the suppressed features from SFAM, promoting the comprehensiveness of feature representation in each attribute-specific region. Furthermore, OWRLoss is employed for decreasing correlations among entries of the last shared classification layer, which can alleviate the highly correlated of weight vectors caused by non-uniform distribution. This can prevent excessive mutual interference among different attributes during attribute recognition. Our model-agnostic approach is plug-and-play, requiring no additional training parameters in the training process. We conduct experiments on several benchmark PAR datasets, including PETA, PA100K, RAPv1, and RAPv2, demonstrating the effectiveness of our method. Specifically, our method outperforms existing state-of-the-art approaches.

Camouflaged object detection (COD) aims to resolve the tough issue of accurately segmenting objects hidden in the surroundings. However, the existing methods suffer from two major problems: the incomplete interior and the inaccurate boundary of the object. To address these difficulties, we propose a three-stage skeleton-boundary–guided network (SBGNet) for the COD task. Specifically, we design a novel skeleton-boundary label to be complementary to the typical pixel-wise mask annotation, emphasizing the interior skeleton and the boundary of the camouflaged object. Furthermore, the proposed feature guidance module (FGM) leverages the skeleton-boundary feature to guide the model to focus on both the interior and the boundary of the camouflaged object. Besides, we design a bidirectional feature flow path with the information interaction module (IIM) to propagate and integrate the semantic and texture information. Finally, we propose the dual feature distillation module (DFDM) to progressively refine the segmentation results in a fine-grained manner. Comprehensive experiments demonstrate that our SBGNet outperforms 20 state-of-the-art methods on three benchmarks in both qualitative and quantitative comparisons.

Existing weakly-supervised camouflaged object detection (WSCOD) methods have much difficulty in detecting accurate object boundaries due to insufficient and imprecise boundary supervision in scribble annotations. Drawing inspiration from human perception that discerns camouflaged objects by incorporating both object region and boundary information, we propose a novel Mutual Interaction Network (MiNet) for scribble-based WSCOD to alleviate the detection difficulty caused by insufficient scribbles. The proposed MiNet facilitates mutual reinforcement between region and edge cues, thereby integrating more robust priors to enhance detection accuracy. In this paper, we first construct an edge cue refinement net, featuring a core region-aware guidance module (RGM) aimed at leveraging the extracted region feature as a prior to generate the discriminative edge map. By considering both object semantic and positional relationships between edge feature and region feature, RGM highlights the areas associated with the object in the edge feature. Subsequently, to tackle the inherent similarity between camouflaged objects and the surroundings, we devise a region-boundary refinement net. This net incorporates a core edge-aware guidance module (EGM), which uses the enhanced edge map from the edge cue refinement net as guidance to refine the object boundaries in an iterative and multi-level manner. Experiments on CAMO, CHAMELEON, COD10K, and NC4K datasets demonstrate that the proposed MiNet outperforms the state-of-the-art methods.

Low-light image enhancement is a challenging task due to the limited visibility in dark environments. While recent advances have shown progress in integrating CNNs and Transformers, the inadequate local-global perceptual interactions still impedes their application in complex degradation scenarios. To tackle this issue, we propose BiFormer, a lightweight framework that facilitates local-global collaborative perception via bilateral interaction. Specifically, our framework introduces a core CNN-Transformer collaborative perception block (CPB) that combines local-aware convolutional attention (LCA) and global-aware recursive Transformer (GRT) to simultaneously preserve local details and ensure global consistency. To promote perceptual interaction, we adopt bilateral interaction strategy for both local and global perception, which involves local-to-global second-order interaction (SoI) in the dual-domain, as well as a mixed-channel fusion (MCF) module for global-to-local interaction. The MCF is also a highly efficient feature fusion module tailored for degraded features. Extensive experiments conducted on low-level and high-level tasks demonstrate that BiFormer achieves state-of-the-art performance. Furthermore, it exhibits a significant reduction in model parameters and computational cost compared to existing Transformer-based low-light image enhancement methods.

In order to provide more efficient and reliable power services than the traditional grid, it is necessary for the smart grid to accurately predict the electric load. Recently, recurrent neural networks (RNNs) have attracted increasing attention in this task because it can discover the temporal correlation between current load data and those long-ago through the self-connection of the hidden layer. Unfortunately, the traditional RNN is prone to the vanishing or exploding gradient problem with the increase of memory depth, which leads to the degradation of predictive accuracy. Many RNN architectures address this problem at the expense of complex internal structures and increased network parameters. Motivated by this, this article proposes two adaptive modularized RNNs to tackle the challenge, which can not only solve the gradient problem effectively with a simple architecture, but also achieve better performance with fewer parameters than other popular RNNs.

Community detection is an important research direction in complex network analysis that can help us discover valuable network structures. The community detection algorithms based on multiobjective particle swarm optimization encode community membership of nodes in particles and employ evolutionary strategies to search for the optimal community division. Existing algorithms face two challenges: (1) they are inapplicable to large networks because the evolution process is time-consuming; (2) they are easy to fall into local optima. In this paper, we propose a novel algorithm that combines a label-propagation-based multiobjective particle swarm optimization algorithm with a graph attention variational autoencoder to realize community detection. On the one hand, the label propagation strategy is involved in the update of a swarm's particles to speed up its evolution. The optimal solutions found by the particle swarm optimization algorithm are embedded into the objective of the autoencoder to improve the embedding vectors’ quality. On the other hand, the embedding vectors are used to improve the solutions of the particle swarm optimization algorithm to avoid its early convergence. The experiments on artificial and real-world networks demonstrate the feasibility and effectiveness of our algorithm compared with some state-of-the-art algorithms.

Casual stereoscopic photography allows ordinary users to create a stereoscopic photo using two photos taken casually by a monocular camera. The visual comfort of a casual stereoscopic photo can greatly affect its visual experience. In this paper, we present a novel visual comfort enhancement method for casual stereoscopic photography via reinforcement learning based on continuous transformation superposition. We consider the transformation, in a continuous transformation space, to transform each view as superpositions of several basic continuous transformations, enabling more subtle and flexible image transformation operations to approach better solutions. To achieve the continuous transformation superposition, we prepare a collection of continuous transformation models for translation, rotation, and perspective transformations. Then we train a policy model to determine an optimal transformation chain to recurrently handle both the geometric constraints and disparity adjustment, and thereby enhance the visual comfort of casual stereoscopic images. We further propose an attention-based stereo feature fusion module that enhances and integrates the binocular information between the left and right views. Experimental results on three datasets demonstrate that our proposed method achieves superior performance to state-of-the-art methods.

Synthetic aperture radar (SAR) image ship detection has important applications in marine surveillance. There are two limitations when applying advanced detection methods naively for SAR ship detection. First, most detectors construct the model as an encoder and rely on the feature pyramid network (FPN) head for accurate prediction, which may lead to high computational costs. Second, the background noises in the ground truth (annotated as rectangular bounding boxes) of angular ships bring difficulties for model training. To meet these challenges, we propose an efficient encoder–decoder network with estimated direction for ship detection in SAR images. First, we present an anchor-free encoder–decoder model that can efficiently extract multiple-level features. Second, we formulate ship detection as a multitask learning problem, including a bounding box prediction and a ship direction regression. The estimated ship direction can weakly supervise and benefit ship detection. Furthermore, we develop a center-weighted labeling method for overlapped annotations. Comprehensive experiments on SAR-Ship-Detection and SSDD datasets show that our method achieves state-of-the-art performance with a high running speed.

Complex networks in real world are always in the state of evolution and composed of numerous overlapping communities. The discovery of overlapping communities in dynamic networks plays an important role in community detection research. In recent years, methods based on incremental clustering have become increasingly popular owing to their high efficiency. However, few of them can deal with communities that are both overlapping and dynamic. In this article, we propose an incremental clustering algorithm for discovering overlapping communities in dynamic networks. In the initial snapshot of a dynamic network, a degree-based seed selection strategy with concise and effective rules is employed to obtain stable and high-quality overlapping communities, in which the degree of nodes is the number of their neighboring nodes in the subgraph composed of free nodes. In the subsequent snapshots, a four-staged framework based on cascade information diffusion is proposed to update the communities incrementally. In this framework, a cascade information diffusion model is used to simulate the evolution of communities and then the fitness of nodes to the communities they belong to is updated based on node similarity. Experiments conducted on both real-world and artificial datasets show that the proposed algorithm can discover overlapping communities in dynamic networks effectively and outperform to the state-of-art baseline algorithms.

With the development of cloud computing, the coexistence of multiple cloud service providers appears in the current cloud market. Due to heterogeneous instance types, different bandwidths and various price models among multiple clouds, it is a challenging issue to schedule a deadline-constrained scientific workflow across multiple clouds. Existing research for workflow scheduling are mostly in the traditional distributed computing environment (such as grid), and only a few primal contributions are made in the cloud environment. This paper proposes a scheduling strategy for a deadline-constrained scientific workflow across multiple clouds. In order to minimize the execution cost of the workflow while meeting its deadline, our strategy utilizes the discrete particle swarm optimization technique, and adopts randomly two-point crossover operator and randomly single point mutation operator of the genetic algorithm. Besides, the strategy optimizes the performance for both computation cost and data transfer cost across multiple clouds. Our strategy is evaluated through well-known workflows, and experimental results show that it performs better than other state-of-the-art strategies.