检索结果-内蒙古大学图书馆

CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation

International Journal of computer vision 2025年 1-20页

作者： Xie, Jinheng Deng, Songhe Hou, Xianxu Luo, Zhaochuan Shen, Linlin Huang, Yawen Zheng, Yefeng Shou, Mike Zheng Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science Wenzhou-Kean University Wenzhou325060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore639798 Singapore School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou215400 China Jarvis Research Center Tencent YouTu Lab Shenzhen518703 China

While promising results have been achieved in weakly-supervised semantic segmentation (WSSS), limited supervision from image-level tags inevitably induces discriminative reliance and spurious relations between target classes and background regions. Thus, Class Activation Map (CAM) usually tends to activate discriminative object regions and falsely includes lots of class-related backgrounds. Without pixel-level supervisions, it could be very difficult to enlarge the foreground activation and suppress those false activation of background regions. In this paper, we propose a novel framework of Cross Language Image Matching with Automatic Context Discovery (CLIMS++), based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress class-related background regions in CAM. In particular, we design object, background region, and text label matching losses to guide the model to excite more reasonable object regions of each category. In addition, we propose to automatically find spurious relations between foreground categories and backgrounds, through which a background suppression loss is designed to suppress the activation of class-related backgrounds. The above designs enable the proposed CLIMS++ to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets show that our CLIMS++ significantly outperforms the previous state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Multi-Agent Digital Twin Framework for AI-Driven Fitness Coaching 25

A Multi-Agent Digital Twin Framework for AI-Driven Fitness C...

引用

Proceedings of the 2025 ACM International Conference on Interactive Media Experiences

作者： Monica (Monireh) Vahdati Kamran Gholizadeh HamlAbadi Fedwa Laamarti Abdulmotaleb El Saddik Multimedia Communications Research Laboratory (MCRLab) School of Electrical Engineering and Computer Science University of Ottawa Ottawa Ontario Canada Computer Vision Department Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi United Arab Emirates and Multimedia Communications Research Laboratory (MCRLab) School of Electrical Engineering and Computer Science University of Ottawa Ottawa Ontario Canada

来源：评论

学校读者我要写书评

暂无评论

FlashMix: Fast Map-Free LiDAR Localization via Feature Mixing and Contrastive-Constrained Accelerated Training

FlashMix: Fast Map-Free LiDAR Localization via Feature Mixin...

引用

IEEE Workshop on Applications of computer vision (WACV)

作者： Raktim Gautam Goswami Naman Patel Prashanth Krishnamurthy Farshad Khorrami Department of Electrical and Computer Engineering Control/Robotics Research Laboratory (CRRL) NYU Tandon School of Engineering Brooklyn NY USA

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Map-free LiDAR localization systems accurately localize within known environments by predicting sensor position and orientation directly from raw point clouds, eliminating the need for large maps and descriptors. However, their long training times hinder rapid adaptation to new environments. To address this, we propose FlashMix, which uses a frozen, scene-agnostic backbone to extract local point descriptors, aggregated with an MLP mixer to predict sensor pose. A buffer of local descriptors is used to accelerate training by orders of magnitude, combined with metric learning or contrastive loss regularization of aggregated descriptors to improve performance and convergence. We evaluate FlashMix on various LiDAR localization benchmarks, examining different regularizations and aggregators, and demonstrating its effectiveness for rapid and accurate LiDAR localization in real-world scenarios. The code is available at https://***/raktimgg/FlashMix.

关键词： Location awareness Training Measurement Point cloud compression Laser radar Accuracy Pose estimation Benchmark testing Mixers Convergence

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Adaptive Filter for Head Tracking in Augmented Reality (AR)-based Flight Simulators

引用

IEEE Transactions on computers 2025年

作者： Nwobodo, Onyeka J. Kuaban, Godlove Suila Nkemeni, Valery Wereszczynski, Kamil Cyran, Krzysztof A. Silesian University of Technology Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Gliwice Poland Polish Academy of Sciences Institute of Theoretical and Applied Informatics Poland University of Buea Laboratory of Electrical Engineering and Computing Faculty of Engineering and Technology Buea Cameroon

This paper presents a novel approach for head tracking in augmented reality (AR) flight simulators using an adaptive fusion of Kalman and particle filters. This fusion dynamically balances the strengths of both algorithms, leveraging Kalman filters for computational efficiency and particle filters for handling non-linearities based on real-time factors such as sensor noise and head movement patterns. Our method demonstrates superior tracking precision and reduced latency, making it particularly effective for immersive pilot training in AR-based flight simulations. While focused on flight simulation, our approach holds high potential for broader applications in other AR and virtual reality (VR) environments where precise, real-time head tracking is crucial. These results provide actionable design guidance for developers optimizing tracking systems in environments that require fast response times and high accuracy. Future extensions of this research could explore the generalization of our approach across diverse AR applications, including human-computer interaction (HCI), medical simulations, and gaming. © 1968-2012 IEEE.

关键词： Flight simulators

来源：评论

学校读者我要写书评

暂无评论

Prior Knowledge-Driven Hybrid Prompter Learning for RGB-Event Tracking

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wang, Mianzhao Shi, Fan Cheng, Xu Chen, Shengyong Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education Key Laboratory of Computer Vision and System School of Computer Science and Engineering Tianjin300384 China Technical University of Denmark Department of Technology Management and Economics Kongens Lyngby Denmark

Event data can asynchronously capture variations in light intensity, thereby implicitly providing valuable complementary cues for RGB-Event tracking. Existing methods typically employ a direct interaction mechanism to fuse RGB and event data. However, due to differences in imaging mechanisms, the representational disparity between these two data types is not fixed, which can lead to tracking failures in certain challenging scenarios. To address this issue, we propose a novel prior knowledge-driven hybrid prompter learning framework for RGB-Event tracking. Specifically, we develop a frame-event hybrid prompter that leverages prior tracking knowledge from the foundation model as intermediate modal support to mitigate the heterogeneity between RGB and event data. By leveraging its rich prior tracking knowledge, the intermediate modal reduces the gap between the dense RGB and sparse event data interactions, effectively guiding complementary learning between modalities. Meanwhile, to mitigate the internal learning disparities between the lightweight hybrid prompter and the deep transformer model, we introduce a pseudo-prompt learning strategy that lies between full fine-tuning and partial fine-tuning. This strategy adopts a divide-and-conquer approach to assign different learning rates to modules with distinct functions, effectively reducing the dominant influence of RGB information in complex scenarios. Extensive experiments conducted on two public RGB-Event tracking datasets show that the proposed HPL outperforms state-of-the-art tracking methods, achieving exceptional performance. © 1991-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Effective dual-region augmentation for reduced reliance on large amounts of labeled data

arXiv

引用

arXiv 2025年

作者： Pulakurthi, Prasanna Reddy Rabbani, Majid de Melo, Celso M. Dianat, Sohail A. Rao, Raghuveer M. Rochester Institute of Technology Department of Electrical and Computer Engineering United States DEVCOM U.S. Army Research Laboratory United States

This paper introduces a novel dual-region augmentation approach designed to reduce reliance on large-scale labeled datasets while improving model robustness and adaptability across diverse computer vision tasks, including source-free domain adaptation (SFDA) and person re-identification (ReID). Our method performs targeted data transformations by applying random noise perturbations to foreground objects and spatially shuffling background patches. This effectively increases the diversity of the training data, improving model robustness and generalization. Evaluations on the PACS dataset for SFDA demonstrate that our augmentation strategy consistently outperforms existing methods, achieving significant accuracy improvements in both single-target and multi-target adaptation settings. By augmenting training data through structured transformations, our method enables model generalization across domains, providing a scalable solution for reducing reliance on manually annotated datasets. Furthermore, experiments on Market-1501 and DukeMTMC-reID datasets validate the effectiveness of our approach for person ReID, surpassing traditional augmentation techniques. The code is available at ***/PrasannaPulakurthi/Foreground-Background-Augmentation. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Scene Understanding for Automatic Target Recognition Using Large vision-Language Models

arXiv

引用

arXiv 2025年

作者： Ranasinghe, Yasiru Vibashan, V.S. Uplinger, James De Melo, Celso Patel, Vishal M. The Department of Electrical and Computer Engineering The Johns Hopkins University BaltimoreMD United States The DEVCOM Army Research Laboratory Adelphi United States

Automatic target recognition (ATR) plays a critical role in tasks such as navigation and surveillance, where safety and accuracy are paramount. In extreme use cases, such as military applications, these factors are often challenged due to the presence of unknown terrains, environmental conditions, and novel object categories. Current object detectors, including open-world detectors, lack the ability to confidently recognize novel objects or operate in unknown environments, as they have not been exposed to these new conditions. However, Large vision-Language Models (LVLMs) exhibit emergent properties that enable them to recognize objects in varying conditions in a zero-shot manner. Despite this, LVLMs struggle to localize objects effectively within a scene. To address these limitations, we propose a novel pipeline that combines the detection capabilities of open-world detectors with the recognition confidence of LVLMs, creating a robust system for zero-shot ATR of novel classes and unknown domains. In this study, we compare the performance of various LVLMs for recognizing military vehicles, which are often underrepresented in training datasets. Additionally, we examine the impact of factors such as distance range, modality, and prompting methods on the recognition performance, providing insights into the development of more reliable ATR systems for novel conditions and classes. © 2025, CC BY.

关键词： Automatic target recognition

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Recognition from an Open-Set Perspective

引用

IEEE Transactions on Multimedia 2025年

作者： Zhou, Jun Xu, Chi Cheng, Li China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Vision and Learning Laboratory Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada

Existing hand gesture recognition methods predominantly rely on a close-set assumption, which in essence limits the viewpoints, gesture categories, and hand shapes at test time to closely resemble those seen during training. This requirement is however rarely met in practice, as images are often captured from unconstrained viewpoints, with novel gestures and unseen hand shapes that can differ significantly from the training data. This motivates us to investigate an open-set hand gesture recognition problem, where hand gestures are still recognizable from unconstrained viewpoints, and novel gesture classes and hand shapes can be incrementally learned with just a few examples. To address this, we propose a viewpoint influence elimination network that extracts view-independent features, significantly improving performance in scenarios with unconstrained viewpoints. Moreover, a joint-weighted classification scheme is introduced to augment the cosine similarity metric for evaluating few-shot incremental learning of novel gestures and shapes. Finally, as existing hand gesture recognition datasets primarily adhere to the close-set assumption, a new hand gesture recognition dataset, OHG, is introduced in this paper, that includes a wide range of viewpoints, diverse gesture classes, and distinct hand shapes. Experimental hand gesture recognition results demonstrate the superior performance of our approach in both unconstrained viewpoint and few-shot incremental learning scenarios. The source code and the OHG dataset are to be made available at https://***/zhoujun-7/OSHGR. © 1999-2012 IEEE.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

FM-FCN:A Neural Network with Filtering Modules for Accurate Vital Signs Extraction

引用

research 2025年第1期2024卷 92-106页

作者： Fangfang Zhu Qichao Niu Xiang Li Qi Zhao Honghong Su Jianwei Shuai Department of Physics and Fujian Provincial Key Laboratory for Soft Functional Materials ResearchXiamen UniversityXiamen 361005China National Institute for Data Science in Health and Medicine and State Key Laboratory of Cellular Stress BiologyInnovation Center for Cell Signaling NetworkXiamen UniversityXiamen 361005China Vitalsilicon Technology Co.Ltd. JiaxingZhejiang 314006China School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan 114051China Yangtze Delta Region Institute of Tsinghua University ZhejiangJiaxing 314006China Wenzhou Institute University of Chinese Academy of SciencesWenzhou 325001China Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine Vision and Brain Health)Wenzhou 325001China

Neural networks excel at capturing local spatial patterns through convolutional modules,but they may struggle to identify and effectively utilize the morphological and amplitude periodic nature of physiological *** this work,we propose a novel network named filtering module fully convolutional network(FM-FCN),which fuses traditional filtering techniques with neural networks to amplify physiological signals and suppress ***,instead of using a fully connected layer,we use an FCN to preserve the time-dimensional correlation information of physiological signals,enabling multiple cycles of signals in the network and providing a basis for signal ***,we introduce the FM as a network module that adapts to eliminate unwanted interference,leveraging the structure of the *** approach builds a bridge between deep learning and signal processing ***,we evaluate the performance of FM-FCN using remote *** results demonstrate that FM-FCN outperforms the second-ranked method in terms of both blood volume pulse(BVP)signal and heart rate(HR)*** substantially improves the quality of BVP waveform reconstruction,with a decrease of 20.23%in mean absolute error(MAE)and an increase of 79.95%in signal-to-noise ratio(SNR).Regarding HR estimation accuracy,FM-FCN achieves a decrease of 35.85%in MAE,29.65%in error standard deviation,and 32.88%decrease in 95%limits of agreement width,meeting clinical standards for HR accuracy *** results highlight its potential in improving the accuracy and reliability of vital sign measurement through high-quality BVP signal *** codes and datasets are available online at https://***/zhaoqi106/FM-FCN.

关键词： physiological signalsin filtering module fully convolutional network fm fcn which vital signs extraction amplify physiological signals convolutional modulesbut neural networks filtering module capturing local spatial patterns

来源：评论

学校读者我要写书评

暂无评论

SENSOR-DRIVEN INTELLIGENT ROBOTICS

引用

ADVANCES IN computerS 1991年第C期32卷 105-148页

作者： TRIVEDI, MM CHEN, CX Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department The University of Tennessee Knoxville Tennessee

Intelligent robotic systems should be capable of performing a range of complex tasks in unstructured and dynamic environments. This chapter discusses a number of important items associated with intelligent robots, role of vision sensing in intelligent robotics, and architecture for the design of an intelligent robot. The chapter also describes the computational task hierarchy that governs a model-based robot vision system, and presents a detailed tutorial on two important components of this hierarchy: image segmentation and matching. The main capabilities that intelligent robotic systems should possess include ability for perception of their environment, planning of their actions, and execution of the planned action. The two important components of a model-based vision system are image segmentation and the matching module. A procedure that allows transformation of 2D image coordinates into 3D world coordinates is also discussed in the chapter. The architecture and control aspects of an integrated sensor-based robotic system consist of six modules: supervisor, task planner, perception, motor, user interface, and knowledge-base. Intelligent, sensor-driven systems pose many challenging basic-research problems from a broad range of scientific and technological disciplines; however, there are many important application areas where such systems would be of significant value and utility, including hazardous environments such as nuclear plants, underwater, and space as well as many industrial-automation tasks. Recent advancements in the VLSI, computer-architectures, sensor-and robot-hardware, and artificial-intelligence fields may aid to the development of robust, practical, and cost-effective intelligent robotic systems for a wide variety of applications.

关键词： Robotics

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：