检索结果-内蒙古大学图书馆

ieee workshop on applications of computer vision (WACV)

作者： Qian Xie Ta-Ying Cheng Jia-Xing Zhong Kaichen Zhou Andrew Markham Niki Trigoni Department of Computer Science University of Oxford Oxford UK

Pedestrian detection is a fundamental task for many downstream applications. visible and thermal images, as the two most important data types, are usually used to detect pedestrians under various environmental conditions. Many state-of-the-art works have been proposed to use two-stream (i.e., two-branch) architectures to combine visible and thermal information to improve detection performance. However, conventional visible-thermal fusion-based methods have no ability to obtain useful information from the visible branch under poor visibility conditions. The visible branch could even sometimes bring noise into the combined features. In this paper, we present a novel thermal and visible fusion architecture for pedestrian detection. Instead of simply using two branches to separately extract thermal and visible features and then fusing them, we introduce a hallucination branch to learn the mapping from the thermal to the visible domain, forming a novel three-branch feature extraction module. We then adaptively fuse feature maps from all three branches (i.e., thermal, visible, and hallucination). With this new integrated hallucination branch, our network can still get relatively good visible feature maps under challenging low-visibility conditions, thus boosting the overall detection performance. Finally, we experimentally demonstrate the superiority of the proposed architecture over conventional fusion methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

beyond the visible spectrum: Is Person Identity Well Preserved in Thermal Cameras? 1

引用

14th International Conference on Computational Collective Intelligence (ICCCI)

作者： Ben Said, Afef Fradi, Hajer Lamouchi, Dorra Marnissi, Mohamed Amine Univ Sousse Inst Super Sci Appl & Technol Sousse LATIS Lab Adv Technol & Intelligent Syst Sousse 4023 Tunisia Univ Sousse Ecole Natl Ingn Sousse LATIS Lab Adv Technol & Intelligent Syst Sousse 4023 Tunisia Univ Sfax Ecole Natl Ingn Sfax Sfax 3038 Tunisia

ISBN: (数字)9783031160141

ISBN: (纸本)9783031160141;9783031160134

Face recognition is a well investigated problem in the computer vision community. beyond the visible spectrum, it is identified as an active-oriented and attractive research area. In particular, thermal cameras have recently emerged as increasingly important sensors for visual surveillance applications. In addition to the fact that these cameras operate well in challenging environments such as adverse weather and lighting conditions, they are commonly known as keystone biometric solution that preserves person identity. In this paper, we intend to prove that faces could be highly recognized from thermal cameras using a powerful generative adversarial model. This model is employed to deal with the domain shift between thermal and visible sensors. Extensive experiments of different generative models and face recognition systems demonstrate the effectiveness of the proposed pipeline to reveal the person identity even though it is acquired by different sensing modalities, with significant facial variations.

关键词： Generative Adversarial Network Thermal visible Face recognition Cross-spectral

来源：评论

学校读者我要写书评

暂无评论

beyond Grids: Exploring Elastic Input Sampling for vision Transformers

Beyond Grids: Exploring Elastic Input Sampling for Vision Tr...

引用

ieee workshop on applications of computer vision (WACV)

作者： Adam Pardyl Grzegorz Kurzejamski Jan Olszewski Tomasz Trzciński Bartosz Zieliński IDEAS NCBR Faculty of Mathematics and Computer Science Jagiellonian University Jagiellonian University Doctoral School of Exact and Natural Sciences University of Warsaw Warsaw University of Technology Tooploox

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

vision transformers have excelled in various computer vision tasks but mostly rely on rigid input sampling using a fixed-size grid of patches. It limits their applicability in real-world problems, such as active visual exploration, where patches have various scales and positions. Our paper addresses this limitation by formalizing the concept of input elasticity for vision transformers and introducing an evaluation protocol for measuring this elasticity. Moreover, we propose modifications to the transformer architecture and training regime, which increase its elasticity. Through extensive experimentation, we spotlight opportunities and challenges associated with such architecture.

关键词： Training computer vision Adaptation models Visualization Protocols Perturbation methods computer architecture Elasticity Transformers Standards

来源：评论

学校读者我要写书评

暂无评论

MvAV-pix2pixHD: Multi-view Aerial View Image Translation

MvAV-pix2pixHD: Multi-view Aerial View Image Translation

引用

ieee computer Society Conference on computer vision and Pattern Recognition workshops (CVPRW)

作者： Jun Yu Keda Lu Shenshen Du Lin Xu Peng Chang Houde Liu Bin Lan Tianyu Liu University of Science and Technology of China Ping An Technology Co. Ltd China PAII Inc. Tsinghua Shenzhen International Graduate School Jianghuai Advance Technology Center

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Multi-modal aerial view image translation involves converting aerial images from one modality to another while preserving basic details and features. These modalities encompass Synthetic Aperture Radar (SAR), Infrared (IR), visible Light (RGB), Electro-Optical (EO), and other image types. Recently, various methods have been proposed to tackle this task, but the focus tends to be on paired image research, overlooking the discrepancies found in aerial images of the same location captured at different times and angles, termed incomplete matching or multi-view image translation. Consequently, we propose MvAV-pix2pixHD to address this issue. For multi-view data sampling, we propose two methods: random sampling and time-priority sampling. Additionally, within the pix2pixHD framework, we introduce an inverse generator to ensure the basic semantic features of the generated images and incorporate three robust loss functions to constrain the authenticity of the generated images. We conduct extensive experiments on two multi-view image translation tasks in the Multi-modal Aerial View Imagery Challenge: Translation (MAVIC-T). Experimental results demonstrate the superiority of our proposed method, and we achieved second place in the MAVIC-T competition in the 20th ieee workshop on Perception beyond the visible spectrum of the CVPR 2024.

关键词： computer vision Image resolution Conferences Computational modeling Semantics computer architecture Generators

来源：评论

学校读者我要写书评

暂无评论

SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models

SODA: Spectral Orthogonal Decomposition Adaptation for Diffu...

引用

ieee workshop on applications of computer vision (WACV)

作者： Xinxi Zhang Song Wen Ligong Han Felix Juefei-Xu Akash Srivastava Junzhou Huang Vladimir Pavlovic Hao Wang Molei Tao Dimitris Metaxas Rutgers University New York University MIT-IBM Watson AI Lab UT Arlington Georgia Tech

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by imposing constraints but may not be optimal for tasks requiring high representation capacity. We propose a novel spectrum-aware adaptation framework for generative models. Our method adjusts both singular values and their basis vectors of pretrained weights. Using the Kronecker product and efficient Stiefel optimizers, we achieve parameter-efficient adaptation of orthogonal matrices. Specifically, we introduce Spectral Orthogonal Decomposition Adaptation (SODA), which balances computational efficiency and representation capacity. Extensive evaluations on text-to-image diffusion models demonstrate SODA's effectiveness, offering a spectrum-aware alternative to existing fine-tuning methods.

关键词： Adaptation models computer vision Computational modeling Text to image Diffusion models Vectors Computational efficiency Matrix decomposition

来源：评论

学校读者我要写书评

暂无评论

ORFormer: Occlusion-Robust Transformer for Accurate Facial Landmark Detection

ORFormer: Occlusion-Robust Transformer for Accurate Facial L...

引用

ieee workshop on applications of computer vision (WACV)

作者： Jui-Che Chiang Hou-Ning Hu Bo-Syuan Hou Chia-Yu Tseng Yu-Lun Liu Min-Hung Chen Yen-Yu Lin National Yang Ming Chiao Tung University NVIDIA MediaTek Inc.

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Although facial landmark detection (FLD) has gained significant progress, existing FLD methods still suffer from performance drops on partially non-visible faces, such as faces with occlusions or under extreme lighting conditions or poses. To address this issue, we introduce ORFormer, a novel transformer-based method that can detect non-visible regions and recover their missing features from vis-ible parts. Specifically, ORFormer associates each image patch token with one additional learnable token called the messenger token. The messenger token aggregates features from all but its patch. This way, the consensus between a patch and other patches can be assessed by referring to the similarity between its regular and messenger embeddings, enabling non-visible region identification. Our method then recovers occluded patches with features aggregated by the messenger tokens. Leveraging the recovered features, OR-Former compiles high-quality heatmaps for the downstream FLD task. Extensive experiments show that our method generates heatmaps resilient to partial occlusions. By inte-grating the resultant heatmaps into existing FLD methods, our method performs favorably against the state of the arts on challenging datasets such as WFLWand COFW.

关键词： computer vision Accuracy Aggregates Lighting computer architecture Transformers Feature extraction Faces Heat recovery

来源：评论

学校读者我要写书评

暂无评论

CrossFuse: Learning Infrared and visible Image Fusion by Cross-Sensor Top-K vision Alignment and beyond

引用

ieee Transactions on Circuits and Systems for Video Technology 2025年

作者： Shi, Yukai Shi, Cidan Weng, Zhipeng Tian, Yin Xian, Xiaoyu Lin, Liang Guangdong University of Technology School of Information Engineering Guangzhou510006 China Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Hefei230601 China CRRC Academy Co. Ltd Beijing China Sun Yat-sen University School of Computer Science Guangzhou510006 China

Infrared and visible image fusion (IVIF) is increasingly applied in critical fields such as video surveillance and autonomous driving systems. Significant progress has been made in deep learning-based fusion methods. However, these models frequently encounter out-of-distribution (OOD) scenes in real-world applications, which severely impact their performance and reliability. Therefore, addressing the challenge of OOD data is crucial for the safe deployment of these models in open-world environments. Unlike existing research, our focus is on the challenges posed by OOD data in real-world applications and on enhancing the robustness and generalization of models. In this paper, we propose an infrared-visible fusion framework based on Multi-View Augmentation. For external data augmentation, Top-k Selective vision Alignment is employed to mitigate distribution shifts between datasets by performing RGB-wise transformations on visible images. This strategy effectively introduces augmented samples, enhancing the adaptability of the model to complex real-world scenarios. Additionally, for internal data augmentation, self-supervised learning is established using Weak-Aggressive Augmentation. This enables the model to learn more robust and general feature representations during the fusion process, thereby improving robustness and generalization. Extensive experiments demonstrate that the proposed method exhibits superior performance and robustness across various conditions and environments. Our approach significantly enhances the reliability and stability of IVIF tasks in practical applications. © 1991-2012 ieee.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

VIIS: visible and Infrared Information Synthesis for Severe Low-Light Image Enhancement

VIIS: Visible and Infrared Information Synthesis for Severe ...

引用

ieee workshop on applications of computer vision (WACV)

作者： Chen Zhao Mengyuan Yu Fan Yang Peiguang Jing Tianjin University Tianjin China Southeast University Nanjing China

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Images captured in severe low-light circumstances often suffer from significant information absence. Existing singular modality image enhancement methods struggle to restore image regions lacking valid information. By leveraging light-impervious infrared images, visible and infrared image fusion methods have the potential to reveal information hidden in darkness. However, they primarily emphasize inter-modal complementation but neglect intra-modal enhancement, limiting the perceptual quality of output images. To address these limitations, we propose a novel task, dubbed visible and infrared information synthesis (VIIS), which aims to achieve both information enhancement and fusion of the two modalities. Given the difficulty in obtaining ground truth in the VIIS task, we design an information synthesis pretext task (ISPT) based on image augmentation. We employ a diffusion model as the framework and design a sparse attention-based dual-modalities residual (SADMR) conditioning mechanism to enhance information interaction between the two modalities. This mechanism enables features with prior knowledge from both modalities to adaptively and iteratively attend to each modality's information during the denoising process. Our extensive experiments demonstrate that our model qualitatively and quantitatively outperforms not only the state-of-the-art methods in relevant fields but also the newly designed baselines capable of both information enhancement and fusion. The code is available at https://***/Chenz418/VIIS.

关键词： computer vision Limiting Fuses Computational modeling Noise reduction Diffusion models Image augmentation Image restoration Image enhancement Image fusion

来源：评论

学校读者我要写书评

暂无评论

Multispectral Imaging for Differential Face Morphing Attack Detection: A Preliminary Study

Multispectral Imaging for Differential Face Morphing Attack ...

引用

ieee workshop on applications of computer vision (WACV)

作者： Raghavendra Ramachandra Sushma Venkatesh Naser Damer Narayan Vetrekar R. S. Gad Norwegian University of Science and Technology (NTNU) Gjøvik Norway AiBA AS Gjøvik Norway Fraunhofer Institute for Computer Graphics Research Germany School of Physical and Applied Sciences Goa University Goa India

Face morphing attack detection is emerging as an increasingly challenging problem owing to advancements in high-quality and realistic morphing attack generation. Reliable detection of morphing attacks is essential because these attacks are targeted for border control applications. This paper presents a multispectral framework for differential morphing-attack detection (D-MAD). The D-MAD methods are based on using two facial images that are captured from the ePassport (also called the reference image) and the trusted device (for example, Automatic Border Control (ABC) gates) to detect whether the face image presented in ePassport is morphed. The proposed multi-spectral D-MAD framework introduce a multispectral image captured as a trusted capture to acquire seven different spectral bands to detect morphing attacks. Extensive experiments were conducted on the newly created Multispectral Morphed Datasets (MSMD) with 143 unique data subjects that were captured using both visible and multispectral cameras in multiple sessions. The results indicate the superior performance of the proposed multispectral framework compared to visible images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Multi-Step Domain Generalization for visible-Infrared Person Re-Identification

Bidirectional Multi-Step Domain Generalization for Visible-I...

引用

ieee workshop on applications of computer vision (WACV)

作者： Mahdi Alehdaghi Pourya Shamsolmoali Rafael M. O. Cruz Eric Granger Dept. of Systems Engineering ETS LIVIA ILLS Montreal Canada Dept. of Computer Science University of York UK

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

A key challenge in visible-infrared person re-identification (V-I ReID) is training a backbone model capable of effectively addressing the significant discrepancies across modalities. State-of-the-art methods that generate a single intermediate bridging domain are often less effective, as this generated domain may not adequately capture sufficient common discriminant information. This paper introduces Bidirectional Multi-step Domain Generalization (BMDG), a novel approach for unifying feature representations across diverse modalities. BMDG creates multiple virtual intermediate domains by learning and aligning body part features extracted from both I and V modalities. In particular, our method aims to minimize the cross-modal gap in two steps. First, BMDG aligns modalities in the feature space by learning shared and modality-invariant body part prototypes from V and I images. Then, it generalizes the feature representation by applying bidirectional multi-step learning, which progressively refines feature representations in each step and incorporates more prototypes from both modalities. Based on these prototypes, multiple bridging steps enhance the feature representation. Experiments 1 1 Our code is available at: ***/BMDG conducted on V-I ReID datasets indicate that our BMDG approach can outperform state-of-the-art part-based and intermediate generation methods, and can be integrated into other part-based methods to enhance their V-I ReID performance.

关键词： Training computer vision Accuracy Codes Prototypes Feature extraction Identification of persons

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：