检索结果-内蒙古大学图书馆

International Conference on Computer Vision (ICCV)

作者： Sixian Zhang Xinhang Song Yubing Bai Weijie Li Yakui Chu Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing Huawei Application Innovate Laboratory Beijing Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (纸本)9781665428132

The goal of object navigation is to reach the expected objects according to visual information in the unseen environments. Previous works usually implement deep models to train an agent to predict actions in real-time. However, in the unseen environment, when the target object is not in egocentric view, the agent may not be able to make wise decisions due to the lack of guidance. In this paper, we propose a hierarchical object-to-zone (HOZ) graph to guide the agent in a coarse-to-fine manner, and an online-learning mechanism is also proposed to update HOZ according to the real-time observation in new environments. In particular, the HOZ graph is composed of scene nodes, zone nodes and object nodes. With the pre-learned HOZ graph, the real-time observation and the target goal, the agent can constantly plan an optimal path from zone to zone. In the estimated path, the next potential zone is regarded as sub-goal, which is also fed into the deep reinforcement learning model for action prediction. Our methods are evaluated on the AI2-Thor simulator. In addition to widely used evaluation metrics SR and SPL, we also propose a new evaluation metric of SAE that focuses on the effective action rate. Experimental results demonstrate the effectiveness and efficiency of our proposed method. The code is available at https://***/sx-zhang/***.

关键词： Measurement Weight measurement Visualization Computer vision Codes Navigation Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An axial-ratio beam-width enhancement of antenna based on electromagnetic bandgap (EBG)

An axial-ratio beam-width enhancement of antenna based on el...

引用

IEEE information Technology, Networking, Electronic and Automation Control Conference

作者： Shijie Huang Liang Zhang Chao Wang Changqing Liu Shenbing Wu Xianliang Wu Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University AnHui Province Key Laboratory of simulation and design for Electronic information system Hefei Normal university Hefei China

ISBN: (数字)9781728143903

ISBN: (纸本)9781728143910

In order to meet the requirements of the navigation system for antennas with wide 3-dB AR beam-width, this paper proposes an axial-ratio beam-width enhancement of antenna based on electromagnetic bandgap (EBG). The effect of surface wave on the circular polarization of the antenna is suppressed by loading two layers of mushroom-like EBG unit cells around the patch. The loading of the EBG increases the 3-dB AR beam-width of the antenna by 78% in the xoz plane and the by 84% in the yoz plane, the simulation and test results demonstrate the effectiveness of this method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Balanced Contrastive Learning for Long-Tailed Visual Recognition

arXiv

引用

arXiv 2022年

作者： Zhu, Jianggang Wang, Zheng Chen, Jingjing Chen, Yi-Ping Phoebe Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Department of Computer Science and Information Technology La Trobe University Australia

Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle to represent and classify the tail classes. Although the problem of learning unbiased classifiers has been well studied, methods for representing imbalanced data are under-explored. In this paper, we focus on representation learning for imbalanced data. Recently, supervised contrastive learning has shown promising performance on balanced data recently. However, through our theoretical analysis, we find that for long-tailed data, it fails to form a regular simplex which is an ideal geometric configuration for representation learning. To correct the optimization behavior of SCL and further improve the performance of long-tailed visual recognition, we propose a novel loss for balanced contrastive learning (BCL). Compared with SCL, we have two improvements in BCL: class-averaging, which balances the gradient contribution of negative classes;class-complement, which allows all classes to appear in every mini-batch. The proposed balanced contrastive learning (BCL) method satisfies the condition of forming a regular simplex and assists the optimization of cross-entropy. Equipped with BCL, the proposed two-branch framework can obtain a stronger feature representation and achieve competitive performance on long-tailed benchmark datasets such as CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, and iNaturalist2018. Our code is available at this URL. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Low Profile Dual-Band Antenna on an EBG Substrate

Low Profile Dual-Band Antenna on an EBG Substrate

引用

IEEE International Wireless Symposium (IWS)

作者： Shijie Huang Liang Zhang Chao Wang Changqing Liu Yifan Jiang Xianliang Wu Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University AnHui Province Key Laboratory of simulation and design for Electronic information system Hefei Normal university Hefei China

ISBN: (数字)9781728167039

ISBN: (纸本)9781728167046

This paper proposes a dual-band antenna based on the electromagnetic band gap structure suitable for WLAN communication systems. The proposed antenna is designed to work at 2.45/5.8 GHz WLAN band. By loading the EBG structure directly below a dual-frequency monopole antenna, the in-phase superposition of electromagnetic waves at the center frequency of the antenna is achieved. The antenna exhibits high gains of near 8.0 and 12.0 dB at the low and high working frequencies while maintaining the low profile characteristics.

关键词： Wireless LAN Directive antennas Reflector antennas Metamaterials Loaded antennas Gain Periodic structures

来源：评论

学校读者我要写书评

暂无评论

A circularly polarized low-profile Metasurface antenna based on CPW feed

A circularly polarized low-profile Metasurface antenna based...

引用

IEEE International Wireless Symposium (IWS)

作者： Changqing Liu Liang Zhang Shijie Huang Chao Wang Xingchuan Yu Xianliang Wu Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University AnHui Province Key Laboratory of simulation and design for Electronic information system Hefei Normal university Hefei China

ISBN: (数字)9781728167039

ISBN: (纸本)9781728167046

A low-profile circularly polarized Metasurfaces antenna based on compact coplanar waveguide (CPW) feed was proposed. The Metasurfaces consists of 16 periodic square-cut metal patches. An hourglass coupled slot was adopted to achieve broadband impedance matching. The antenna has a simple structure and a low cross section, and it can be implemented by a layer of a printed circuit substrate. A circular polarized wave is generated by changing the size of the cut angle of the Metasurfaces, and at the same time, the impedance bandwidth can be widened. To verify the simulation results, a 1λ 0 ×1λ 0 ×0.05λ 0 (at 10 GHz) model antenna was fabricated and measured. The simulation and measurement results show good consistency. The test results show that the -10dB return loss bandwidth reaches 45.3 %, and the circular polarization axis ratio(AR) is less than 3dB with a bandwidth of 18.5%.

关键词： Antenna measurements Polarization Bandwidth Metasurfaces Radar antennas Antenna feeds Coplanar waveguides

来源：评论

学校读者我要写书评

暂无评论

12-Port Hybrid MIMO Antenna Array for 5G Smartphone Applications

12-Port Hybrid MIMO Antenna Array for 5G Smartphone Applicat...

引用

IEEE International Wireless Symposium (IWS)

作者： Peng Liu Yufa Sun Bingbing Chen Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University Anhui Province Key Laboratory of simulation and design for Electronic information system Hefei Normal University Hefei China

ISBN: (数字)9781728167039

ISBN: (纸本)9781728167046

A hybrid twelve-antenna array operating in the 3.3-3.6 GHz and 4.8-5.0 GHz band for multiple input multiple output (MIMO) applications in 5G smartphones is proposed. The proposed hybrid antenna array elements are symmetrically placed along the long edges of the smartphone, and they are composed of two inverted-F antennas (IFA) with different structural parameters. Simulated antenna isolation is better than -14.5 dB without any decoupling structures. Moreover, simulated radiation patterns, antenna efficiencies, and envelop correlation coefficients are also given in the paper.

关键词： Wireless communication 5G mobile communication Structural engineering Smart phones MIMO communication Antenna arrays Antenna radiation patterns

来源：评论

学校读者我要写书评

暂无评论

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Language-Image Pre-Training 24

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Lang...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Yudong Hou, Xianxu Dezhi, Zheng Shen, Linlin Zhao, Zhe School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Tencent AI Lab Beijing China

ISBN: (纸本)9798400706868

While significant progress has been made in multi-modal learning driven by large-scale image-text datasets, there is still a noticeable gap in the availability of such datasets within the facial domain. To facilitate and advance the field of facial representation learning, we present FLIP-80M, a large-scale visual-linguistic dataset comprising over 80 million face images paired with text descriptions. FLIP-80M is constructed by leveraging the large openly available image-text-pair dataset LAION-5B and a mixed-method approach to filter face-related pairs from both visual and linguistic perspectives. Our curation process involves face detection, face caption classification, text de-noising, and synthesis-based image augmentation. As a result, FLIP-80M stands as the largest face-text dataset to date. To evaluate the potential of our dataset, we fine-tune the CLIP model using the proposed FLIP-80M, to create FLIP (Facial Language-Image Pretraining) and assess its representation capabilities across various downstream tasks. Our experiments demonstrate that our FLIP model achieves state-of-the-art results in a range of face analysis tasks, including face parsing, face alignment, and face attribute classification. The dataset and models are available at https://***/ydli-ai/FLIP. © 2024 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Non-rigid 3D models retrieval based on hierarchical matching

引用

Computer Aided Drafting,Design and Manufacturing 2017年第1期27卷 39-47页

作者： Liu Yujie Li Wei Song Yang Gong Weiqing Li Zongmin Li Hua Department of Computer & Communication Engineering China University of Petroleum ChinaPetro (Karamay) Data Center Sinopec Exploration & Production Research Institute (PEPRIS) Key Lab of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of Sciences

In 3D models retrieval, feature description and retrieval of non-rigid model face more complex problems due to the isometry transformation of itself. We introduce the hierarchical combination matching into the feature comparison, and build a map between the divided regions of two models, and then achieve accurate feature matching based on patch-by-patch, which successfully introduces the spatial information into feature matching. Verified by experiment, the 3D model retrieval method proposed in this paper based on hierarchical combination matching can make sure more accurate feature matching, so as to enhance the precision of retrieval.

关键词： non-rigid 3D model shape descriptor spatial distribution hierarchical combination matching

来源：评论

学校读者我要写书评

暂无评论

Deepfake Network Architecture Attribution

arXiv

引用

arXiv 2022年

作者： Yang, Tianyun Huang, Ziyao Cao, Juan Li, Lei Li, Xirong Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

With the rapid progress of generation technology, it has become necessary to attribute the origin of fake images. Existing works on fake image attribution perform multi-class classification on several Generative Adversarial Network (GAN) models and obtain high accuracies. While encouraging, these works are restricted to model-level attribution, only capable of handling images generated by seen models with a specific seed, loss and dataset, which is limited in real-world scenarios when fake images may be generated by privately trained models. This motivates us to ask whether it is possible to attribute fake images to the source models’ architectures even if they are finetuned or retrained under different configurations. In this work, we present the first study on Deepfake Network Architecture Attribution to attribute fake images on architecture-level. Based on an observation that GAN architecture is likely to leave globally consistent fingerprints while traces left by model weights vary in different regions, we provide a simple yet effective solution named DNA-Det for this problem. Extensive experiments on multiple cross-test setups and a large-scale dataset demonstrate the effectiveness of DNA-Det. Our source code and dataset can be found here: https://***/ICTMCG/DNA-Det Copyright © 2022, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Learning Open-Vocabulary Semantic Segmentation Models From Natural Language Supervision

Learning Open-Vocabulary Semantic Segmentation Models From N...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jilan Xu Junlin Hou Yuejie Zhang Rui Feng Yi Wang Yu Qiao Weidi Xie Shanghai Key Lab of Intelligent Information Processing School of Computer Science Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai AI Laboratory CMIC Shanghai Jiao Tong University

This paper considers the problem of open-vocabulary semantic segmentation (OVS), that aims to segment objects of arbitrary classes beyond a pre-defined, closed-set categories. The main contributions are as follows: First, we propose a transformer-based model for OVS, termed as OVSegmentor, which only exploits web-crawled imagetext pairs for pre-training without using any mask annotations. OVSegmentor assembles the image pixels into a set of learnable group tokens via a slotattention based binding module, then aligns the group tokens to corresponding caption embeddings. Second, we propose two proxy tasks for training, namely masked entity completion and cross-image mask consistency. The former aims to infer all masked entities in the caption given group tokens, that enables the model to learn fine-grained alignment between visual groups and text entities. The latter enforces consistent mask predictions between images that contain shared entities, encouraging the model to learn visual invariance. Third, we construct CC4M dataset for pre-training by filtering CC12M with frequently appeared entities, which significantly improves training efficiency. Fourth, we perform zero-shot transfer on four benchmark datasets, PASCAL VOC, PASCAL Context, COCO Object, and ADE20K. OVSegmentor achieves superior results over state-of-the-art approaches on PASCAL VOC using only 3% data (4M vs 134M) for pre-training.

关键词：

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：