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

Autonomous Multiple-Trolley Collection System with Nonholonomic Robots: Design, Control, and Implementation

arXiv

引用

arXiv 2024年

作者： Xie, Peijia Xia, Bingyi Hu, Anjun Zhao, Ziqi Meng, Lingxiao Sun, Zhirui Gao, Xuheng Wang, Jiankun Meng, Max Q.-H. Shenzhen Key Laboratory of Robotics Perception and Intelligence Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China The Jiaxing Research Institute Southern University of Science and Technology Jiaxing China The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong The Department of Electrical and Computer Engineering The University of Alberta Canada

The intricate and multi-stage task in dynamic public spaces like luggage trolley collection in airports presents both a promising opportunity and an ongoing challenge for automated service robots. Previous research has primarily focused on handling a single trolley or individual functional components, creating a gap in providing cost-effective and efficient solutions for practical scenarios. In this paper, we propose a mobile manipulation robot incorporated with an autonomy framework for the collection and transportation of multiple trolleys that can significantly enhance operational efficiency. We address the key challenges in the trolley collection problem through the novel design of the mechanical system and the vision-based control strategy. We design a lightweight manipulator and docking mechanism, optimized for the sequential stacking and transportation of multiple trolleys. Additionally, based on the Control Lyapunov Function and Control Barrier Function, we propose a novel vision-based control with the online Quadratic Programming which significantly improves the accuracy and efficiency of the collection process. The practical application of our system is demonstrated in real-world scenarios, where it successfully executes multiple-trolley collection tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

A Joint Tracking System: Robot is Online to Access Surveillance Views

A Joint Tracking System: Robot is Online to Access Surveilla...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Zheyuan Lin Shanshan Ji Wen Wang Mengjie Qin Rong Yang Minhong Wan Jason Gu Te Li Chunlong Zhang Research Center for Intelligent Robotics Zhejiang Laboratory Research Institute of Interdisciplinary Innovation Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax Canada

The application of robots in social life, equipped with sensors and actuators and embedded with AI, assists people in all aspects. However, the first perspective of the robot horizon is heavily constrained, which weakens its performance. A joint tracking system is designed and built to deal with this, by integrating a surveillance system with the robot visual, providing a third perspective. This system takes one horizontal view and two top views from various directions as inputs and matches a person among the frames and in time sequence. In order to deal with the identity match with a huge visual feature gap, a special dataset is collected, simultaneously labeling identities from a mobile robot perspective and multiple indoor static surveillance monitors. The experiment shows that such match is a task worth exploring that can be better handled by training on our dataset than existing open source Re-identification (Re-id) datasets. Moreover, in the real scenario, this system improves the performance on issues like in and out of the robot’s field of vision and heavy occlusion by people or objects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Video Instance Segmentation with Recurrent Graph Neural Networks 43rd

Video Instance Segmentation with Recurrent Graph Neural Net...

引用

43rd DAGM German Conference on Pattern Recognition, DAGM GCPR 2021

作者： Johnander, Joakim Brissman, Emil Danelljan, Martin Felsberg, Michael Computer Vision Laboratory Department of Electrical Engineering Linköping University Linköping Sweden Zenseact Gothenburg Sweden Saab Bröderna Ugglas gata Linköping582 54 Sweden Computer Vision Lab ETH Zürich Zürich Switzerland School of Engineering University of KwaZulu-Natal Durban South Africa

ISBN: (纸本)9783030926588

Video instance segmentation is one of the core problems in computer vision. Formulating a purely learning-based method, which models the generic track management required to solve the video instance segmentation task, is a highly challenging problem. In this work, we propose a novel learning framework where the entire video instance segmentation problem is modeled jointly. To this end, we design a graph neural network that in each frame jointly processes all detections and a memory of previously seen tracks. Past information is considered and processed via a recurrent connection. We demonstrate the effectiveness of the proposed approach in comprehensive experiments. Our approach, operating at over 25 FPS, outperforms previous video real-time methods. We further conduct detailed ablative experiments that validate the different aspects of our approach. © 2021, Springer Nature Switzerland AG.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Exploring Seasonal Variability in the Context of Neural Radiance Fields for 3D Reconstruction on Satellite Imagery

arXiv

引用

arXiv 2024年

作者： Kåreborn, Liv Ingerstad, Erica Berg, Amanda Karlsson, Justus Haglund, Leif Maxar International Sweden AB Ebbegatan 13 Linköping582 13 Sweden AI Sweden Folkungagatan 44 Stockholm118 26 Sweden Computer Vision Laboratory Department of Electrical Engineering Linköping University Linköping581 83 Sweden

In this work, the seasonal predictive capabilities of Neural Radiance Fields (NeRF) applied to satellite images are investigated. Focusing on the utilization of satellite data, the study explores how Sat-NeRF, a novel approach in computer vision, performs in predicting seasonal variations across different months. Through comprehensive analysis and visualization, the study examines the model's ability to capture and predict seasonal changes, highlighting specific challenges and strengths. Results showcase the impact of the sun direction on predictions, revealing nuanced details in seasonal transitions, such as snow cover, color accuracy, and texture representation in different landscapes. Given these results, we propose Planet-NeRF, an extension to Sat-NeRF capable of incorporating seasonal variability through a set of month embedding vectors. Comparative evaluations reveal that Planet-NeRF outperforms prior models in the case where seasonal changes are present. The extensive evaluation combined with the proposed method offers promising avenues for future research in this domain. © 2024, CC BY.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2023 Image Shadow Removal Challenge Report

NTIRE 2023 Image Shadow Removal Challenge Report

引用

2023 IEEE/CVF Conference on computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Vasluianu, Florin-Alexandru Seizinger, Tim Timofte, Radu Cui, Shuhao Huang, Junshi Tian, Shuman Fan, Mingyuan Zhang, Jiaqi Zhu, Li Wei, Xiaoming Wei, Xiaolin Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjölund, Jens Schön, Thomas B. Dong, Xiaoyi Zhang, Xi Sheryl Li, Chenghua Leng, Cong Yeo, Woon-Ha Oh, Wang-Taek Lee, Yeo-Reum Ryu, Han-Cheol Luo, Jinting Jiang, Chengzhi Han, Mingyan Wu, Qi Lin, Wenjie Yu, Lei Li, Xinpeng Jiang, Ting Fan, Haoqiang Liu, Shuaicheng Xu, Shuning Song, Binbin Chen, Xiangyu Zhang, Shile Zhou, Jiantao Zhang, Zhao Zhao, Suiyi Zheng, Huan Gao, Yangcheng Wei, Yanyan Wang, Bo Ren, Jiahuan Luo, Yan Kondo, Yuki Miyata, Riku Yasue, Fuma Naruki, Taito Ukita, Norimichi Chang, Hua-En Yang, Hao-Hsiang Chen, Yi-Chung Chiang, Yuan-Chun Huang, Zhi-Kai Chen, Wei-Ting Chen, I-Hsiang Hsieh, Chia-Hsuan Kuo, Sy-Yen Xianwei, Li Fu, Huiyuan Liu, Chunlin Ma, Huadong Fu, Binglan He, Huiming Wang, Mengjia She, Wenxuan Liu, Yu Nathan, Sabari Kansal, Priya Zhang, Zhongjian Yang, Huabin Wang, Yan Zhang, Yanru Phutke, Shruti S. Kulkarni, Ashutosh Khan, Md Raqib Murala, Subrahmanyam Vipparthi, Santosh Kumar Ye, Heng Liu, Zixi Yang, Xingyi Liu, Songhua Wu, Yinwei Jing, Yongcheng Yu, Qianhao Zheng, Naishan Huang, Jie Long, Yuhang Yao, Mingde Zhao, Feng Zhao, Bowen Ye, Nan Shen, Ning Cao, Yanpeng Xiong, Tong Xia, Weiran Li, Dingwen Xia, Shuchen Computer Vision Lab Ifi Caidas University of Würzburg Germany Computer Vision Lab Eth Zürich Switzerland Meituan Group China Department of Information Technology Uppsala University Sweden Institute of Automation Chinese Academy of Sciences Beijing China Nanjing China Maicro Nanjing China Department of Artificial Intelligence Convergence Sahmyook University Seoul Korea Republic of Megvii Technology China University of Electronic Science and Technology of China China University of Macau China China Toyota Technological Institute Japan Graduate Institute of Electronics Engineering National Taiwan University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan ServiceNow United States Beijing University of Post and Teleconmunication Beijing China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education China Couger Inc. Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar Punjab Rupnagar India Research Institute Singapore National University of Singapore Singapore Research Institute Singapore University of Sydney Australia Brain-Inspired Vision Laboratory Information Science and Technology Institution University of Science and Technology of China China State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310027 China Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province School of Mechanical Engineering Zhejiang University Hangzhou310027 China South China University of Technology China

ISBN: (纸本)9798350302493

This work reviews the results of the NTIRE 2023 Challenge on Image Shadow Removal. The described set of solutions were proposed for a novel dataset, which captures a wide range of object-light interactions. It consists of 1200 roughly pixel aligned pairs of real shadow free and shadow affected images, captured in a controlled environment. The data was captured in a white-box setup, using professional equipment for lights and data acquisition sensors. The challenge had a number of 144 participants registered, out of which 19 teams were compared in the final ranking. The proposed solutions extend the work on shadow removal, improving over the performance level describing state-of-the-art methods. © 2023 IEEE.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Adaptive Block Elevation Mapping for Large-scale Scene

Adaptive Block Elevation Mapping for Large-scale Scene

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Zhou, Yang Zhu, Shiqiang Huang, Huang Li, Yuehua Gu, Jason The Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China The Beijing Institute of Control Engineering Beijing100094 China The Beijing Research Institute Zhejiang Laboratory Beijing100094 China The Department of Electrical and Computer Engineering Dalhousie University HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9781665481090

Dense map that contains the surrounding geometry and vision information of a robot is widely used for path planning, navigation, obstacle avoidance and other applications. Considering the performance of the processing unit mounted on the robot is limited, mapping algorithm has to make compromise by sacrificing speed and precision. It will be more challenging when the dense mapping scene is very large because the memory consumption will be greatly increased and the map is difficult to be extended if beyonding the initial map. To suppress the negative impact from the increased map scale, we proposed a novel block mapping approach to generate the dense map in large scale of scene. In this work, the elevation map is selected as the base dense map. The entire elevation map is segmented into numerous block maps of which size is much smaller than that of the entire map. The present moment of lidar and vision measurements are used to generate the local elevation map. The local elevation map is used to update block maps which are adaptively generated along the motion trajectory. A memory-disk interaction mechanism, which the block maps will be loaded to memory or saved to local disk when needed, is introduced. Our block mapping approach is tested on the KITTI datasets, and the results demonstrate that the mapping approach can stably operate in a large scale of scene with a much smaller consumption of memory. © 2022 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition

arXiv

引用

arXiv 2023年

作者： Lou, Meng Zhou, Hong-Yu Yang, Sibei Yu, Yizhou The Artificial Intelligence Laboratory Deepwise Healthcare Beijing China The Department of Computer Science The University of Hong Kong Hong Kong The Shanghai Engineering Research Center of Intelligent Vision and Imaging ShanghaiTech University Shanghai China

Recent studies have integrated convolution into transformers to introduce inductive bias and improve generalization performance. However, the static nature of conventional convolution prevents it from dynamically adapting to input variations, resulting in a representation discrepancy between convolution and self-attention as self-attention calculates attention matrices dynamically. Furthermore, when stacking token mixers that consist of convolution and self-attention to form a deep network, the static nature of convolution hinders the fusion of features previously generated by self-attention into convolution kernels. These two limitations result in a suboptimal representation capacity of the constructed networks. To find a solution, we propose a lightweight Dual Dynamic Token Mixer (D-Mixer) that aggregates global information and local details in an input-dependent way. D-Mixer works by applying an efficient global attention module and an input-dependent depthwise convolution separately on evenly split feature segments, endowing the network with strong inductive bias and an enlarged effective receptive field. We use D-Mixer as the basic building block to design TransXNet, a novel hybrid CNN-Transformer vision backbone network that delivers compelling performance. In the ImageNet-1K image classification task, TransXNet-T surpasses Swin-T by 0.3% in top-1 accuracy while requiring less than half of the computational cost. Furthermore, TransXNet-S and TransXNet-B exhibit excellent model scalability, achieving top-1 accuracy of 83.8% and 84.6% respectively, with reasonable computational costs. Additionally, our proposed network architecture demonstrates strong generalization capabilities in various dense prediction tasks, outperforming other state-of-the-art networks while having lower computational costs. Our code will be available at https://***/LMMMEng/TransXNet. © 2023, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Exploring the Frontiers of Synthetic Image-Based Deep Learning Training in Digital X-ray Radiography.

e-Journal of Nondestructive Testing

引用

e-Journal of Nondestructive Testing 2024年第8期29卷

作者： Hena, Bata Wei, Ziang Perron, Luc Castanedo, Clemente Ibarra Maldague, Xavier Department of Electrical and Computer Engineering Université Laval 1065 Ave de la Médecine Quebec CityQCG1V 0A6 Canada Computer Vision and Systems Laboratory Department of Electrical and Computer Engineering Université Laval 1065 Ave de la Médecine Quebec CityQCG1V 0A6 Canada GI Lab Solutions 475 Pruneau Ave Québec CityQCG1M 2J8 Canada

Industrial radiography is a pivotal non-destructive testing (NDT) method that ensures quality and safety in a wide range of industrial sectors. Nevertheless, the conventional human-based approaches to carrying out industrial radiography are prone to challenges that negatively impact the accuracy and efficiency of defect detection. To solve this challenge, numerous computer-based alternatives have been developed, including Automated Defect Recognition (ADR) using deep learning algorithms. At the core of training, these ADR algorithms demand large volumes of qualitative data that should be representative of real-world cases to be expected during deployment. However, the availability of digital X-ray radiography data, especially for open research, is limited by non-disclosure contractual terms in the industry. In this study, we present a pipeline that is capable of modelling synthetic images based on real digital X-ray radiography images. This is achieved through a systematic analysis of the intensity distribution, considering grey value (GV) statistical uniqueness related to exposure conditions used during image acquisition, type of imaged component, material thickness variations, X-ray beam divergence, anode heel effect, scatter radiation, edge delineation, etc. The generated synthetic images were exclusively utilized to train a deep learning model, yielding an impressive model performance with mean intersection over union (IoU) of 0.93, and mean dice coefficient of 0.96 when tested on real unseen digital X-ray radiography images. The presented methodology is scalable and adaptable, making it suitable for diverse industrial applications. © 2024 The Authors.

关键词： X ray radiography

来源：评论

学校读者我要写书评

暂无评论

Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition

arXiv

引用

arXiv 2024年

作者： Yang, Shu Luo, Luyang Wang, Qiong Chen, Hao Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen Futian China

Existing state-of-the-art methods for surgical phase recognition either rely on the extraction of spatial-temporal features at a short-range temporal resolution or adopt the sequential extraction of the spatial and temporal features across the entire temporal resolution. However, these methods have limitations in modeling spatial-temporal dependency and addressing spatial-temporal redundancy: 1) These methods fail to effectively model spatial-temporal dependency, due to the lack of long-range information or joint spatial-temporal modeling. 2) These methods utilize dense spatial features across the entire temporal resolution, resulting in significant spatial-temporal redundancy. In this paper, we propose the Surgical Transformer (Surgformer) to address the issues of spatial-temporal modeling and redundancy in an end-to-end manner, which employs divided spatial-temporal attention and takes a limited set of sparse frames as input. Moreover, we propose a novel Hierarchical Temporal Attention (HTA) to capture both global and local information within varied temporal resolutions from a target frame-centric perspective. Distinct from conventional temporal attention that primarily emphasizes dense long-range similarity, HTA not only captures long-term information but also considers local latent consistency among informative frames. HTA then employs pyramid feature aggregation to effectively utilize temporal information across diverse temporal resolutions, thereby enhancing the overall temporal representation. Extensive experiments on two challenging benchmark datasets verify that our proposed Surgformer performs favorably against the state-of-the-art methods. The code is released at https://***/isyangshu/Surgformer. Copyright © 2024, The Authors. All rights reserved.

关键词： Transplantation (surgical)

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

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

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：