检索结果-内蒙古大学图书馆

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yaning Wang, Tianyi Yu, Zitong Gao, Zan Shen, Linlin Chen, Shengyong Jinan250353 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Jinan250014 China The Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

FDC: Feature Dropout Consistency for unsupervised domain adaptation semantic segmentation

学校读者我要写书评

暂无评论

Neural Networks 2025年 189卷 107527页

作者： Rao, Chaoyu Fan, Wanshu Wang, Cong Yang, Xin Wei, Xiaopeng Zhou, Dongsheng National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University China Department of Computing The Hong Kong Polytechnic University Hong Kong School of Computer Science and Technology Dalian University of Technology China

In Unsupervised Domain Adaptation Semantic Segmentation (UDASS), while self-training techniques have become one of the most effective methods to date, the absence of target labels makes models susceptible to overfitting. To address this problem, consistency techniques regularize the model by perturbing the target domain and enforcing consistent pixel predictions before and after the perturbation. Consistency techniques are based on the idea that a well-performing model should yield consistent predictions for the target data stream before and after perturbations. In this paper, we introduce the Feature Dropout Consistency (FDC) module, a novel approach that instigates perturbations at the feature level. This is achieved by implementing random feature dropout between the encoder and decoder of the student network. Subsequently, a feature dropout consistency loss is applied to minimize discrepancies in predictions between the perturbed student network and its teacher counterpart. Notably, FDC seamlessly integrates with existing self-training methodologies and, when paired with input perturbation, delves into an even broader perturbation spectrum. Through rigorous experimentation in standard UDA settings — training with synthetic labeled and real unlabeled data — FDC consistently outperforms baseline models, establishing new benchmarks on GTAV → Cityscapes and SYNTHIA → Cityscapes. © 2025

关键词： Semantic Segmentation

Conditional Generative Modeling for Amorphous Multi-Element Materials

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Honglin Liu, Chuhao Guo, Yongfeng Luo, Xiaoshan Chen, Yijie Liu, Guangsheng Li, Yu Wang, Ruoyu Wang, Zhenyu Wu, Jianzhuo Ma, Cheng Xie, Zhuohang Lv, Jian Ding, Yufei Zhang, Huabin Luo, Jian Zhong, Zhicheng Li, Mufan Wang, Yanchao Li, Wan-Lu Key Laboratory of Material Simulation Methods and Software Ministry of Education College of Physics Jilin University Changchun China Aiiso Yufeng Li Family Department of Chemical and Nano Engineering University of California La Jolla San DiegoCA United States Institute of Molecular Engineering Plus College of Chemistry Fuzhou University Fuzhou China College of Chemistry and Molecular Engineering Peking University Beijing China School of Physics Nankai University Tianjin China Institute of Modern Physics Fudan University Shanghai China Program in Materials Science and Engineering University of California La Jolla San DiegoCA United States School of Artificial Intelligence and Data Science University of Science and Technology of China Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China International Center of Future Science Jilin University Changchun China Department of Computer Science and Engineering University of California La Jolla San DiegoCA United States Center for Renewable Energy and Storage Technologies Physical Science and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Suzhou Lab Suzhou215123 China

Amorphous multi-element materials offer unprecedented tunability in composition and properties, yet their rational design remains challenging due to the lack of predictive structure-property relationships and the vast configurational space. Traditional modeling struggles to capture the intricate short-range order that dictates their stability and functionality. We here introduce ApolloX, a pioneering predictive framework for amorphous multi-element materials, establishing a new paradigm by integrating physics-informed generative modeling with particle swarm optimization, using chemical short-range order as an explicit constraint. By systematically navigating the disordered energy landscape, ApolloX enables the targeted design of thermodynamically stable amorphous configurations. It accurately predicts atomic-scale arrangements, including composition-driven metal clustering and amorphization trends, which are well-validated by experiments, while also guiding synthesis by leveraging sluggish diffusion to control elemental distribution and disorder. The resulting structural evolution, governed by composition, directly impacts catalytic performance, leading to improved activity and stability with increasing amorphization. This predictive-experimental synergy transforms the discovery of amorphous materials, unlocking new frontiers in catalysis, energy storage, and functional disordered systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Amorphization

EVOH in situ fibrillation and its effect of strengthening, toughening and hydrophilic modification on PVDF hollow fiber microfiltration membrane via TIPS process

学校读者我要写书评

暂无评论

Journal of Materials science 2019年第7期54卷 5971-5987页

作者： Cui, Zhenyu Tang, Xiuxiu Li, Wei Liu, Haonan Zhang, Jing Wang, Hong Li, Jianxin State Key Laboratory of Separation Membranes and Membrane Processes National Center for International Joint Research on Separation Membranes School of Material Science and Engineering Tianjin Polytechnic University Tianjin 300387 China School of Computer Science and Software Engineering Tianjin Polytechnic University Tianjin 300387 China

In order to enhance the strength and overcome the poor antifouling capacity of poly(vinylidene fluoride) (PVDF) membrane used in water treatment, herein, poly(ethylene-co-vinyl alcohol) (EVOH) was selected and the PVDF/EVOH blend hollow fiber microfiltration membrane was prepared via the thermally induced phase separation (TIPS) technique. The morphology for the pristine and blend membrane was compared, and the distribution of EVOH on outer surface and within matrix was explored. The fibrous-shaped EVOH enhanced the breaking strength of the membrane markedly (up to 13.63 MPa) due to the in situ fibrillation;especially, when the blend membrane was immersed into water, the internal plasticization of water molecular enhanced the toughness of the membrane and the elongation at break increased up to 86.39% compared with 27.63% for the corresponding dry membrane and 36.62% for the pristine membrane, respectively. The addition of EVOH introduced hydroxyl group into the bulk and thus endowed the membrane with a better hydrophilicity (the contact angle is as low as 43°) and higher pure water flux (up to 449.11 L m⁻² h⁻¹) compared with pristine PVDF membrane. Moreover, the blend membrane showed a better rejection of carbonic particle (nearly 100%) and higher flux recovery rate (up to 87.30%). The present investigation offers an effective and simple pattern to regulate microstructure and enhance mechanical strength, flux and hydrophilicity of the polymeric microfiltration membrane via the TIPS process for water treatment. © 2019, Springer science+Business Media, LLC, part of Springer Nature.

关键词：

Mobile Collocated Gaming: Collaborative Play and Meaning-Making on a university Campus

学校读者我要写书评

暂无评论

Mobile Collocated Gaming: Collaborative Play and Meaning-Mak...

Proceedings of the ACM on Human-computer Interaction

作者： Zhang, Xun Gui, Xinning Kou, Yubo Li, Yukun School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Pennsylvania State University University ParkPA16802 United States Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China

Many mobile games are designed to be placeless, so that mobile device owners could play anytime, anywhere. But does such design erase the sense of place in mobile gaming? To investigate the spatiality of mobile gaming, we conducted an ethnographic study of mobile gaming in a Chinese university. We found mobile gaming as a form of collocated interaction, where participants collectively created meanings around distinctive places on the campus including dormitory, classroom, and laboratory, and engaged in collaborative play. Their mobile collocated gaming was shaped by the social, organizational, and cultural contexts of places. The spatiality of mobile collocated gaming entails both appropriation of the norms and expectations of places and creation of new meanings to negotiate tensions between mobile gaming and places. We further discuss the spatiality of mobile collocated gaming and broader social and cultural conditions. © 2020 ACM.

关键词： Human computer interaction User interfaces Chinese universities Collaborative play Collocated interactions Cultural conditions Cultural context Ethnographic study Meaning makings university campus

Unsupervised domain adaptation with dual-scheme fusion network for medical image segmentation 29

学校读者我要写书评

暂无评论

Unsupervised domain adaptation with dual-scheme fusion netwo...

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Zou, Danbing Zhu, Qikui Yan, Pingkun School of Computer Science Institute of Artificial Intelligence National Engineering Research Center for Multimedia Software Wuhan University China Rensselaer Polytechnic Institute Department of Biomedical Engineering TroyNY United States

ISBN: (纸本)9780999241165

Domain adaptation aims to alleviate the problem of retraining a pre-trained model when applying it to a different domain, which requires large amount of additional training data of the target domain. Such an objective is usually achieved by establishing connections between the source domain labels and target domain data. However, this imbalanced source-to-target one way pass may not eliminate the domain gap, which limits the performance of the pre-trained model. In this paper, we propose an innovative Dual-Scheme Fusion Network (DSFN) for unsupervised domain adaptation. By building both source-to-target and target-to-source connections, this balanced joint information flow helps reduce the domain gap to further improve the network performance. The mechanism is further applied to the inference stage, where both the original input target image and the generated source images are segmented with the proposed joint network. The results are fused to obtain more robust segmentation. Extensive experiments of unsupervised cross-modality medical image segmentation are conducted on two tasks - brain tumor segmentation and cardiac structures segmentation. The experimental results show that our method achieved significant performance improvement over other state-of-the-art domain adaptation methods. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Image segmentation

Convergence of 5G with internet of things for enhanced privacy

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Batool, Amreen Sun, Baoshan Saleem, Ali Ali, Jawad School of Computer Science and Software Engineering Tiangong University Tianjin China Department of Computer Science COMSATS University Islamabad Lahore Pakistan Malaysian Institute of Information Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia

In this paper, we address the issue of privacy in 5th generation (5G) driven Internet of Things (IoT) and related technologies while presenting a comparison with previous technologies for communication and unaddressed issues in 5G. Initially, an overview of 5G driven IoT is presented with details about both technologies and eventually leading to problems that 5th generation will face. Details about 5G are also presented while comparing them with previous technologies. The architecture of 5G is presented hence explaining layers of 5G and technologies like SDN, NFV and cloud computing that compose these layers. The architecture for 5g based IoT is also presented for providing visual understanding as well as explained based on how this addresses the issues present in 4G. Privacy is highlighted in 5G driven IoT while providing details about how SDN, NFV and cloud computing helps in elimination of this issue. The issues presented will be compared with 4G based IoT and solutions are provided about mitigation of these issues particularly bandwidth and security. Moreover, techniques used by 4G and 5G technologies for handling the issues of privacy in IoT are presented in a nutshell as a table. Paper also presents a detailed overview of technologies making 5G possible meanwhile giving an explanation about how these technologies resolve privacy issues in 5G. © 2021, CC BY.

关键词： Internet of things

NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Xiaoning Wu, Zongwei Li, Ao Vasluianu, Florin Zhang, Yulun Gu, Shuhang Zhang, Le Zhu, Ce Timofte, Radu Jin, Zhi Wu, Hongjun Wang, Chenxi Ling, Haitao Cai, Yuanhao Bian, Hao Zheng, Yuxin Lin, Jing Yuille, Alan Shao, Ben Guo, Jin Liu, Tianli Wu, Mohao Feng, Yixu Hou, Shuo Lin, Haotian Zhu, Yu Wu, Peng Dong, Wei Sun, Jinqiu Zhang, Yanning Yan, Qingsen Zou, Wenbin Yang, Weipeng Li, Yunxiang Wei, Qiaomu Ye, Tian Chen, Sixiang Zhang, Zhao Zhao, Suiyi Wang, Bo Luo, Yan Zuo, Zhichao Wang, Mingshen Wang, Junhu Wei, Yanyan Sun, Xiaopeng Gao, Yu Huang, Jiancheng Chen, Hongming Chen, Xiang Tang, Hui Chen, Yuanbin Zhou, Yuanbo Dai, Xinwei Qiu, Xintao Deng, Wei Gao, Qinquan Tong, Tong Li, Mingjia Hu, Jin He, Xinyu Guo, Xiaojie Sabarinathan Uma, K. Sasithradevi, A. Sathya Bama, B. Mohamed Mansoor Roomi, S. Srivatsav, V. Wang, Jinjuan Sun, Long Chen, Qiuying Shao, Jiahong Zhang, Yizhi Conde, Marcos V. Feijoo, Daniel Benito, Juan C. García, Alvaro Lee, Jaeho Kim, Seongwan Sharif, S.M.A. Khujaev, Nodirkhuja Tsoy, Roman Murtaza, Ali Khairuddin, Uswah Faudzi, Ahmad'Athif Mohd Malagi, Sampada Joshi, Amogh Akalwadi, Nikhil Desai, Chaitra Tabib, Ramesh Ashok Mudenagudi, Uma Lian, Wenyi Lian, Wenjing Kalyanshetti, Jagadeesh Aralikatti, Vijayalaxmi Ashok Yashaswini, Palani Upasi, Nitish Hegde, Dikshit Patil, Ujwala Sujata, C. Yan, Xingzhuo Hao, Wei Fu, Minghan Choksy, Pooja Sarvaiya, Anjali Upla, Kishor Raja, Kiran Yan, Hailong Zhang, Yunkai Li, Baiang Zhang, Jingyi Zheng, Huan University of Electronic Science and Technology of China China Computer Vision Lab University of Würzburg Germany Shanghai Jiao Tong University China Computer Vision Lab ETH Zurich Switzerland School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen Campus Guangdong Shenzhen518107 China Guangdong Provincial Key Laboratory of Fire Science and Technology Guangzhou510006 China Johns Hopkins University United States Tsinghua University China Zhejiang Dahua Technology Co. Ltd. China School of Computer Science Northwestern Polytechnical University China School of Software Northwestern Polytechnical University China School of Computer Science Xi'an University of Architecture and Technology China South China University of Technology China Fuzhou University China Chengdu University of Information Technology China Hong Kong University of Science and Technology Guangzhou China Hefei University of Technology China Individual Researcher Shenyang Aerospace University China Nanjing University of Science and Technology China Fuzhou University Fuzhou China Imperial Vision Technology Fuzhou China Tianjin University China Couger Inc Japan Sasi Institute of Technology & Engineering India Vellore Institute of Technology India Thiagarajar college of engineering India Coventry University United Kingdom Cidaut AI CVLab University of Wuerzburg Germany Opt-AI University Teknologi Malaysia Kuala Lumpur Malaysia Universiti Teknologi Malaysia Kuala Lumpur Malaysia KLE Technological University Karnataka Hubballi India School of Electronics and Communication Engineering KLE Technological University Karnataka Hubballi India School of Computer Science and Engineering KLE Technological University Karnataka Hubballi India Uppsala University Sweden Northeastern University United States Bosch Investment Ltd. China Fortinet Inc. University of Saskatchewan Canada Sardar Vallabhbhai National Institute of Technology India Norwegian University of Science and Technolog

This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results. The aim of this challenge is to discover an effective network design or solution capable of generating brighter, clearer, and visually appealing results when dealing with a variety of conditions, including ultra-high resolution (4K and beyond), non-uniform illumination, backlighting, extreme darkness, and night scenes. A notable total of 428 participants registered for the challenge, with 22 teams ultimately making valid submissions. This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field. © 2024, CC BY.

关键词： Image enhancement

PhenoProfiler: Advancing Phenotypic Learning for Image-based Drug Discovery

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Bo Zhang, Bob Zhang, Chengyang Zhou, Minghao Huang, Weiliang Wang, Shihang Wang, Qing Li, Mengran Zhang, Yong Song, Qianqian PAMI Research Group Department of Computer and Information Science University of Macau Taipa China Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing China Department of Health Outcomes and Biomedical Informatics College of Medicine University of Florida Florida United States Faculty of Applied Sciences Macao Polytechnic University Taipa China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong China Department of Cancer Biology Wake Forest School of Medicine Winston SalemNC United States

In the field of image-based drug discovery, capturing the phenotypic response of cells to various drug treatments and perturbations is a crucial step. This process involves transforming high-throughput cellular images into quantitative representations for downstream analysis. However, existing methods require computationally extensive and complex multi-step procedures, which can introduce inefficiencies, limit generalizability, and increase potential errors. To address these challenges, we present PhenoProfiler, an innovative model designed to efficiently and effectively extract morphological representations, enabling the elucidation of phenotypic changes induced by treatments. PhenoProfiler is designed as an end-to-end tool that processes whole-slide multi-channel images directly into low-dimensional quantitative representations, eliminating the extensive computational steps required by existing methods. It also includes a multi-objective learning module to enhance robustness, accuracy, and generalization in morphological representation learning. PhenoProfiler is rigorously evaluated on large-scale publicly available datasets, including over 230,000 whole-slide multi-channel images in end-to-end scenarios and more than 8.42 million single-cell images in non-end-to-end settings. Across these benchmarks, PhenoProfiler consistently outperforms state-of-the-art methods by up to 20%, demonstrating substantial improvements in both accuracy and robustness. Furthermore, PhenoProfiler uses a tailored phenotype correction strategy to emphasize relative phenotypic changes under treatments, facilitating the detection of biologically meaningful signals. UMAP visualizations of treatment profiles demonstrate PhenoProfiler’s ability to effectively cluster treatments with similar biological annotations, thereby enhancing interpretability. These findings establish PhenoProfiler as a scalable, generalizable, and robust tool for phenotypic learning, offering transformative advancement

关键词： Benchmarking