IEEE Transactions on Image Processing最新文献

Hierarchical Multimodal Knowledge Matching for Training-Free Open-Vocabulary Object Detection. 面向无训练开放词汇目标检测的分层多模态知识匹配。

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-10-14 DOI: 10.1109/tip.2025.3618408

Qisen Ma,Yan Huang,Zikun Liu,Hyunhee Park,Liang Wang

{"title":"Hierarchical Multimodal Knowledge Matching for Training-Free Open-Vocabulary Object Detection.","authors":"Qisen Ma,Yan Huang,Zikun Liu,Hyunhee Park,Liang Wang","doi":"10.1109/tip.2025.3618408","DOIUrl":"https://doi.org/10.1109/tip.2025.3618408","url":null,"abstract":"Open-Vocabulary Object Detection (OVOD) aims to leverage the generalization capabilities of pre-trained vision-language models for detecting objects beyond the trained categories. Existing methods mostly focus on supervised learning strategies based on available training data, which might be suboptimal for data-limited novel categories. To tackle this challenge, this paper presents a Hierarchical Multimodal Knowledge Matching method (HMKM) to better represent novel categories and match them with region features. Specifically, HMKM includes a set of object prototype knowledge that is obtained using limited category-specific images, acting as off-the-shelf category representations. In addition, HMKM also includes a set of attribute prototype knowledge to represent key attributes of categories at a fine-grained level, with the goal to distinguish one category from its visually similar ones. During inference, two sets of object and attribute prototype knowledge are adaptively combined to match categories with region features. The proposed HMKM is training-free and can be easily integrated as a plug-and-play module into existing OVOD models. Extensive experiments demonstrate that our HMKM significantly improves the performance when detecting novel categories across various backbones and datasets.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"117 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145288508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

UniUIR: Considering Underwater Image Restoration as An All-in-One Learner UniUIR：考虑水下图像恢复作为一个一体化的学习者

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-10-14 DOI: 10.1109/tip.2025.3618377

Xu Zhang, Huan Zhang, Guoli Wang, Qian Zhang, Lefei Zhang, Bo Du

引用次数: 0

Physically Consistent Image Augmentation for Deep Learning in Mueller Matrix Polarimetry Mueller矩阵偏振法中深度学习的物理一致图像增强

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-10-13 DOI: 10.1109/tip.2025.3618390

Christopher Hahne, Omar Rodríguez-Núñez, Éléa Gros, Théotim Lucas, Ekkehard Hewer, Tatiana Novikova, Theoni Maragkou, Philippe Schucht, Richard McKinley

引用次数: 0

Delving into the Training Dynamics for Image Classification 图像分类的训练动力学研究

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-10-13 DOI: 10.1109/tip.2025.3618395

Mengyang Li, Xiaoling Zhou, Ou Wu

引用次数: 0

Hierarchical Semantic Compression for Consistent Image Semantic Restoration 基于层次语义压缩的一致性图像语义恢复

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-10-13 DOI: 10.1109/tip.2025.3618379

Shengxi Li, Zifu Zhang, Mai Xu, Lai Jiang, Yufan Liu, Ce Zhu

引用次数: 0

ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning ChartX & ChartVLM：复杂图表推理的通用基准和基础模型

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-10-13 DOI: 10.1109/tip.2025.3607618

Renqiu Xia, Hancheng Ye, Xiangchao Yan, Qi Liu, Hongbin Zhou, Zijun Chen, Botian Shi, Junchi Yan, Bo Zhang

引用次数: 0

Cross-domain Few-shot Medical Image Segmentation via Dynamic Semantic Matching 基于动态语义匹配的医学图像分割

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-10-13 DOI: 10.1109/tip.2025.3618396

Yazhou Zhu, Shidong Wang, Tao Zhou, Zechao Li, Haofeng Zhang, Ling Shao

引用次数: 0

Improving Robustness of Point Cloud Analysis Through Perturbation Simulation and Distortion-Guided Feature Augmentation 通过摄动模拟和畸变引导特征增强提高点云分析的鲁棒性

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-10-13 DOI: 10.1109/tip.2025.3618411

Jingming He, Chongyi Li, Shiqi Wang, Sam Kwong

引用次数: 0

Space-Time Video Super-resolution with Neural Operator 基于神经算子的时空视频超分辨率

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-10-09 DOI: 10.1109/tip.2025.3616609

Yuantong Zhang, Hanyou Zheng, Daiqin Yang, Zhenzhong Chen, Haichuan Ma, Wenpeng Ding

引用次数: 0

Rethinking the Low-Light Video Enhancement: Benchmark Datasets and Methods. 低光视频增强的再思考：基准数据集和方法。

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-10-08 DOI: 10.1109/tip.2025.3616639

Jiaxuan Wang,Huiyuan Fu,Wenkai Zheng,Xicong Wang,Xin Wang,Heng Zhang,Huadong Ma

{"title":"Rethinking the Low-Light Video Enhancement: Benchmark Datasets and Methods.","authors":"Jiaxuan Wang,Huiyuan Fu,Wenkai Zheng,Xicong Wang,Xin Wang,Heng Zhang,Huadong Ma","doi":"10.1109/tip.2025.3616639","DOIUrl":"https://doi.org/10.1109/tip.2025.3616639","url":null,"abstract":"Low-light video enhancement is a critical task in computer vision with a wide range of applications. However, there is a lack of high-quality benchmark datasets in this field. To address this issue, we collect a high-quality low-light video dataset using a well-designed camera system. The videos in our dataset feature apparent camera motion and strict spatial alignment. In order to achieve general low-light video enhancement, we propose a Retinex-based method called Light Adjustable Network (LAN). LAN iteratively adjusts the brightness and adapts to different lighting conditions in various real-world scenarios, producing visually appealing results. We further develop a new dataset capture method and low-light video enhancement method to address the limitation of our previous dataset in capturing dynamic scenes and previous method. The new camera setup and capture method enable the recording of real continuous videos and generate the new dataset. Our new low-light video enhancement method, LAN++, leverages a new inter-frame relationship, difference images. It utilizes the texture information contained in the difference images of dynamic scenes to supplement the high-frequency details of the original features, which produce sharper and more realistic output images. The extensive experiments demonstrate the superiority of our low-light video dataset and enhancement method. Our dataset and code will be publicly available.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"7 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0