Journal of Visual Communication and Image Representation最新文献

{"title":"Visual anomaly detection algorithms: Development and Frontier review","authors":"Jia Huang,&nbsp;Wei Quan,&nbsp;Xiwen Li","doi":"10.1016/j.jvcir.2025.104585","DOIUrl":"10.1016/j.jvcir.2025.104585","url":null,"abstract":"<div><div>Visual anomaly detection includes image anomaly detection and video anomaly detection, focusing on identifying and locating anomalous patterns or events in images or videos. This technology finds widespread applications across multiple domains, including industrial surface defect inspection, medical image lesion analysis, and security surveillance systems. By identifying patterns that do not conform to normal conditions, it helps to detect anomalies in a timely manner and reduce risks and losses. This paper provides a comprehensive review of existing visual anomaly detection algorithms. It introduces a taxonomy of algorithms from a new perspective: statistical-based algorithms, measurement-based algorithms, generative-based algorithms, and representation-based algorithms. Furthermore, this paper systematically introduces datasets for visual anomaly detection and compares the performance of various algorithms on different datasets under typical evaluation metrics. By analyzing existing algorithms, we identify current challenges and suggest promising future research directions.</div></div>","PeriodicalId":54755,"journal":{"name":"Journal of Visual Communication and Image Representation","volume":"112 ","pages":"Article 104585"},"PeriodicalIF":3.1,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inter-image Token Relation Learning for weakly supervised semantic segmentation","authors":"Jingfeng Tang,&nbsp;Keyang Cheng,&nbsp;Liutao Wei,&nbsp;Yongzhao Zhan","doi":"10.1016/j.jvcir.2025.104576","DOIUrl":"10.1016/j.jvcir.2025.104576","url":null,"abstract":"<div><div>In recent years, Vision Transformer-based methods have emerged as promising approaches for localizing semantic objects in weakly supervised semantic segmentation tasks. However, existing methods primarily rely on the attention mechanism to establish relations between classes and image patches, often neglecting the intrinsic interrelations among tokens within datasets. To address this gap, we propose the Inter-image Token Relation Learning (ITRL) framework, which advances weakly supervised semantic segmentation by inter-image consistency. Specifically, the Inter-image Class Token Contrast method is introduced to generate comprehensive class representations by contrasting class tokens in a memory bank manner. Additionally, the Inter-image Patch Token Align approach is presented, which enhances the normalized mutual information among patch tokens, thereby strengthening their interdependencies. Extensive experiments validated the proposed framework, showcasing competitive mean Intersection over Union scores on the PASCAL VOC 2012 and MS COCO 2014 datasets.</div></div>","PeriodicalId":54755,"journal":{"name":"Journal of Visual Communication and Image Representation","volume":"112 ","pages":"Article 104576"},"PeriodicalIF":3.1,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Knowledge NeRF: Few-shot novel view synthesis for dynamic articulated objects","authors":"Wenxiao Cai ,&nbsp;Xinyue Lei ,&nbsp;Xinyu He ,&nbsp;Junming Leo Chen ,&nbsp;Yuzhi Hao ,&nbsp;Yangang Wang","doi":"10.1016/j.jvcir.2025.104586","DOIUrl":"10.1016/j.jvcir.2025.104586","url":null,"abstract":"<div><div>We introduce Knowledge NeRF, a few-shot framework for novel-view synthesis of dynamic articulated objects. Conventional dynamic-NeRF methods learn a deformation field from long monocular videos, yet they degrade sharply when only sparse observations are available. Our key idea is to reuse a high-quality, pose-specific NeRF as a knowledge base and learn a lightweight projection module for each new pose that maps 3-D points in the current state to their canonical counterparts. By freezing the pretrained radiance field and training only this module with five input images, Knowledge NeRF renders novel views whose fidelity matches a NeRF trained with one hundred images. Experimental results demonstrate the effectiveness of our method in reconstructing dynamic 3D scenes with 5 input images in one state. Knowledge NeRF is a new pipeline and a promising solution for novel view synthesis in dynamic articulated objects. The data and implementation will be publicly available at: <span><span>https://github.com/RussRobin/Knowledge_NeRF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":54755,"journal":{"name":"Journal of Visual Communication and Image Representation","volume":"112 ","pages":"Article 104586"},"PeriodicalIF":3.1,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Joint airport runway segmentation and line detection via multi-task learning for intelligent visual navigation","authors":"Lichun Yang ,&nbsp;Jianghao Wu ,&nbsp;Hongguang Li ,&nbsp;Chunlei Liu ,&nbsp;Shize Wei","doi":"10.1016/j.jvcir.2025.104589","DOIUrl":"10.1016/j.jvcir.2025.104589","url":null,"abstract":"<div><div>This paper presents a novel multi-task learning framework for joint airport runway segmentation and line detection, addressing two key challenges in aircraft visual navigation: (1) edge detection for sub-5 %-pixel targets and (2) computational inefficiencies in existing methods. Our contributions include: (i) ENecNet, a lightweight yet powerful encoder that boosts small-target detection IoU by 15.5 % through optimized channel expansion and architectural refinement; (ii) a dual-decoder design with task-specific branches for area segmentation and edge line detection; and (iii) a dynamically weighted multi-task loss function to ensure balanced training. Extensive evaluations on the RDD5000 dataset show state-of-the-art performance with 0.9709 segmentation IoU and 0.6256 line detection IoU at 38.4 FPS. The framework also demonstrates robust performance (0.9513–0.9664 IoU) across different airports and challenging conditions such as nighttime, smog, and mountainous terrain, proving its suitability for real-time onboard navigation systems.</div></div>","PeriodicalId":54755,"journal":{"name":"Journal of Visual Communication and Image Representation","volume":"112 ","pages":"Article 104589"},"PeriodicalIF":3.1,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A non-extended 3D mesh secret sharing scheme adapted for FPGA processing","authors":"Hao Kong ,&nbsp;Zi-Ming Wu ,&nbsp;Bin Yan ,&nbsp;Jeng-Shyang Pan ,&nbsp;Hong-Mei Yang","doi":"10.1016/j.jvcir.2025.104580","DOIUrl":"10.1016/j.jvcir.2025.104580","url":null,"abstract":"<div><div>The existing meaningful secret sharing schemes for 3D model face the issue of model extension. To address this problem, we propose a non-extended secret 3D mesh sharing scheme. Considering the large amount of data that needs to be shared in a 3D model, we designed a circuit structure to accelerate the computation during sharing. In the sharing stage, vertex data is encoded and converted to integer data from floating-point data. This is more conducive to handling the computation in FPGA. By adjusting the length of the encoding, multiple secrets can be embedded in the vertex encoding stage. This solves the extension problem of the scheme. Experiments were conducted on a set of 3D meshes to compare the differences between the cover models and the shares. This experimental result shows that the shares maintain high fidelity with the cover meshes. Furthermore, the FPGA implementation achieves a throughput of 675Mbit/s. Simulation results show that the parallel circuit structure is 30 times faster than the serial structure. In terms of resource consumption, the circuit structure designed in this scheme occupies less than 5% of the on-chip resources.</div></div>","PeriodicalId":54755,"journal":{"name":"Journal of Visual Communication and Image Representation","volume":"112 ","pages":"Article 104580"},"PeriodicalIF":3.1,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145121127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Defending against adversarial attacks via an Adaptive Guided Denoising Diffusion model","authors":"Yanlei Wei ,&nbsp;Yongping Wang ,&nbsp;Xiaolin Zhang ,&nbsp;Jingyu Wang ,&nbsp;Lixin Liu","doi":"10.1016/j.jvcir.2025.104584","DOIUrl":"10.1016/j.jvcir.2025.104584","url":null,"abstract":"<div><div>The emergence of a large number of adversarial samples has exposed the vulnerabilities of Deep Neural Networks (DNNs). With the rise of diffusion models, their powerful denoising capabilities have made them a popular strategy for adversarial defense. The defense capability of diffusion models is effective against simple adversarial attacks; however, their effectiveness diminishes when facing more sophisticated and complex attacks. To address this issue, this paper proposes a method called Adaptive Guided Denoising Diffusion (AGDD), which can effectively defend against adversarial attacks. Specifically, we first apply a small noise perturbation to the given adversarial samples, performing the forward diffusion process. Then, in the reverse denoising phase, the diffusion model is guided by the adaptive guided formula <span><math><msub><mrow><mi>g</mi></mrow><mrow><mi>A</mi><mi>G</mi></mrow></msub></math></span> to perform denoising. At the same time, the adaptive guided formula <span><math><msub><mrow><mi>g</mi></mrow><mrow><mi>A</mi><mi>G</mi></mrow></msub></math></span> is adjusted according to the adaptive matrix <span><math><msub><mrow><mi>G</mi></mrow><mrow><mi>t</mi></mrow></msub></math></span> and the residual <span><math><msub><mrow><mi>r</mi></mrow><mrow><mi>t</mi></mrow></msub></math></span>. Additionally, we introduced a momentum factor <span><math><mi>m</mi></math></span> to further optimize the denoising process, reduce the oscillations caused by gradient variations, and enhance the stability and convergence of the optimization process. Through AGDD, the denoised images accurately reconstruct the characteristics of the original observations (i.e., the unperturbed images) and exhibit strong robustness and adaptability across diverse noise conditions. Extensive experiments on the ImageNet dataset using Convolutional Neural Networks (CNN) and Vision Transformer (ViT) architectures demonstrate that the proposed method exhibits superior robustness against adversarial attacks, with classification accuracy reaching 87.4% for CNN and 85.9% for ViT, surpassing other state-of-the-art defense techniques.</div></div>","PeriodicalId":54755,"journal":{"name":"Journal of Visual Communication and Image Representation","volume":"112 ","pages":"Article 104584"},"PeriodicalIF":3.1,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145121128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Energy-aware and dynamic training of deep neural networks (EADTrain) for sustainable AI","authors":"Pulkit Dwivedi ,&nbsp;Mansi Kajal","doi":"10.1016/j.jvcir.2025.104582","DOIUrl":"10.1016/j.jvcir.2025.104582","url":null,"abstract":"<div><div>The growing complexity of deep neural networks, particularly in the domain of computer vision, has led to increasing concerns regarding their energy consumption and environmental impact. To tackle these issues, we propose EADTrain, an innovative training framework that emphasizes energy-conscious learning. EADTrain integrates live energy monitoring within the training cycle, enabling dynamic adjustments to data augmentation strategies and selective fine-tuning based on ongoing energy consumption and model performance feedback. This responsive training mechanism helps achieve an optimal trade-off between computational efficiency and predictive accuracy. We assess EADTrain across several visual recognition tasks using benchmark datasets including CIFAR-10, ImageNet, and a custom satellite imagery dataset. The experimental results show that EADTrain reduces energy usage by up to 35% compared to leading methods, without compromising classification accuracy or F1-score. These findings position EADTrain as a scalable and environmentally efficient framework for training deep learning models in energy-constrained settings.</div></div>","PeriodicalId":54755,"journal":{"name":"Journal of Visual Communication and Image Representation","volume":"112 ","pages":"Article 104582"},"PeriodicalIF":3.1,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145105187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced visible light detail and infrared thermal radiation for dual-mode imaging system via multi-information interaction","authors":"Xiaosong Liu,&nbsp;Huaibin Qiu,&nbsp;Zhuolin Ou,&nbsp;Jiazhen Dou,&nbsp;Jianglei Di,&nbsp;Yuwen Qin","doi":"10.1016/j.jvcir.2025.104583","DOIUrl":"10.1016/j.jvcir.2025.104583","url":null,"abstract":"<div><div>In the field of dual-mode optical imaging, image fusion techniques offer significant advantages such as improved spatial resolution and the suppression of redundant information, particularly for visible and infrared image. However, existing fusion methods often overlook the interaction between multiple feature information during the extraction and fusion stages, resulting in the inability to extract both visible light detail and infrared thermal radiation effectively. To address this challenge, we construct a dual-mode imaging system and propose an image fusion method that incorporates Convolution-Swin-Transformer Blocks (CSTBs). The block combines Convolution and Shifted Window Transformer to improve the interaction and extraction between local and global information within the images. On the other hand, our proposed method strengthens the comprehensive interaction and fusion between shallow pixel-level information and deeper semantic representation by fusing local and global feature information at various layers. Furthermore, we introduce a multi-component loss function that balances the complementary features extracted from the source images, with a particular focus on enhancing edge texture, structure, and brightness information. Experimental results demonstrate that our method achieves superior performance in simultaneously enhancing both texture details and thermal radiation. This is evidenced by results on two publicly available datasets, as well as the Target_GDUT dataset captured using our dual-mode optical imaging system.</div></div>","PeriodicalId":54755,"journal":{"name":"Journal of Visual Communication and Image Representation","volume":"112 ","pages":"Article 104583"},"PeriodicalIF":3.1,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145105188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Random gray patch and adaptive graph channel attention for visible-infrared person re-identification","authors":"Hongkai Hu ,&nbsp;Qiang Liu ,&nbsp;Jing Peng ,&nbsp;Fei Li ,&nbsp;Yuyan Huang ,&nbsp;Lupin Liu","doi":"10.1016/j.jvcir.2025.104579","DOIUrl":"10.1016/j.jvcir.2025.104579","url":null,"abstract":"<div><div>The widespread deployment of video surveillance systems has made person recognition technology essential across various fields, including smart surveillance, law enforcement, and criminal investigation. However, person re-identification (Re-ID) using single-modal images struggles in low-light or nighttime conditions. To address the cross-modal matching challenge between visible and infrared images, we propose a novel method. We introduce a random gray patch (RGP) module that simulates infrared images by converting visible image regions to grayscale, reducing modality discrepancy. Additionally, a non_local adaptive graph channel (NAGC) attention module captures long-range dependencies and adjusts feature channel importance. Finally, we introduce a cross-modal contrast loss, which optimizes feature distances between samples of the same identity across different modalities, further improving cross-modal matching performance. Experimental results on SYSU-MM01 and RegDB datasets show that our method significantly outperforms existing approaches.</div></div>","PeriodicalId":54755,"journal":{"name":"Journal of Visual Communication and Image Representation","volume":"112 ","pages":"Article 104579"},"PeriodicalIF":3.1,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145121129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimized spatial relation-aware graph neural network based facial emotion recognition for reducing video conferencing fatigue","authors":"Arti Ranjan ,&nbsp;M. Ravinder","doi":"10.1016/j.jvcir.2025.104581","DOIUrl":"10.1016/j.jvcir.2025.104581","url":null,"abstract":"<div><div>Human emotions can be identified from facial expressions recorded in videos. This provides very low accuracy in real-world uncontrolled environments where various challenges such as variations in lighting and individual appearance must be addressed. Therefore, an Optimized Spatial Relation-aware Graph Neural Network based Facial Emotion Recognition for Reducing Video conferencing Fatigue (FER-SRAGNN-POA-RVF) is proposed in this paper. Here, the input data are collected from Ryerson Emotion dataset. The collected data are pre-processed utilizing Adaptive Multi-Scale Gaussian Co-Occurrence Filtering (AMGCF) to clean up the recorded video. The pre-processed image is given into Modified Spline-Kernelled Chirplet Transform (MSKCT) to extract the geometric features. Then, the extracted features are fed into the Spatial Relation-aware Graph Neural Network (SRAGNN) for facial emotion recognition. Finally, Puzzle Optimization Algorithm (POA) is employed to optimize the SRAGNN parameters. The proposed FER-SRAGNN-POA-RVF method is implemented and the performance metrics attains higher accuracy when compared with existing models.</div></div>","PeriodicalId":54755,"journal":{"name":"Journal of Visual Communication and Image Representation","volume":"112 ","pages":"Article 104581"},"PeriodicalIF":3.1,"publicationDate":"2025-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145105272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}