检索结果-内蒙古大学图书馆

IEEE International Joint Conference on Biometrics (IJCB)

作者： Bizhu Wu Mingyan Wu Haoqin Ji Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China

ISBN: (纸本)9781665463959

Recently, researchers have achieved significant results in the skeleton based action recognition task. To better model the skeleton sequences, existing methods learned the feature representations in the self-supervised setting by solving pretext tasks, such as predicting the order of a shuffled skeleton sequence or verifying whether a given skeleton sequence is shuffled or not. However, these pretext tasks are either too challenging or too easy for the encoder to obtain a proper skeleton representation for action recognition. Therefore, we propose a novel self-pretraining pretext task, Which One Is Better (WOIB), to identify which one is more temporally coherent, given two shuffled skeleton sequences. Experiments on the NTU RGB+D, NTU RGB+D 120, and Kinetics-Skeleton datasets with different network architectures show significant improvements in recognition accuracy, demonstrating that such a well-designed pretext task is general and able to drive the encoder to learn more discriminative representations.

关键词： Biometrics (access control) Coherence Predictive models Network architecture Drives Benchmark testing Skeleton

来源：评论

学校读者我要写书评

暂无评论

Translate the facial regions you like using region-wise normalization

arXiv

引用

arXiv 2020年

作者： Liu, Wenshuang Chen, Wenting Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China

Though GAN (Generative Adversarial Networks) based technique has greatly advanced the performance of image synthesis and face translation, only few works available in literature provide region based style encoding and translation. We propose in this paper a region-wise normalization framework, for region level face translation. While per-region style is encoded using available approach, we build a so called RIN (region-wise normalization) block to individually inject the styles into per-region feature maps and then fuse them for following convolution and upsampling. Both shape and texture of different regions can thus be translated to various target styles. A region matching loss has also been proposed to significantly reduce the inference between regions during the translation process. Extensive experiments on three publicly available datasets, i.e. Morph, RaFD and CelebAMask-HQ, suggest that our approach demonstrate a large improvement over state-of-the-art methods like StarGAN, SEAN and FUNIT. Our approach has further advantages in precise control of the regions to be translated. As a result, region level expression changes and step by step make up can be achieved. The video demo is available at https://***/ceRqsbzXAfk. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Deep Face Attributes Recognition Using Spatial Transformer Network

Deep Face Attributes Recognition Using Spatial Transformer N...

引用

IEEE International Conference on Information and Automation

作者： Lianzhi Tan Zhifeng Li Qiao Yu Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9781509041039

-Face alignment is very crucial to the task of face attributes recognition. The performance of face attributes recognition would notably degrade if the fiducial points of the original face images are not precisely detected due to large lighting, pose and occlusion variations. In order to alleviate this problem, we propose a spatial transform based deep CNNs to improve the performance of face attributes recognition. In this approach, we first learn appropriate transformation parameters by a carefully designed spatial transformer network called LoNet to align the original face images, and then recognize the face attributes based on the aligned face images using a deep network called CINet. To the best of our knowledge, this is the first attempt to use spatial transformer network in face attributes recognition task. Extensive experiments on two large and challenging databases (CelebA and LFWA) clearly demonstrate the effectiveness of the proposed approach over the current state-of-the-art.

关键词： Face Attribute Recognition Spatial Transformer Network Face Alignment

来源：评论

学校读者我要写书评

暂无评论

Neural Transformation Fields for Arbitrary-Styled Font Generation

Neural Transformation Fields for Arbitrary-Styled Font Gener...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Bin Fu Junjun He Jianjun Wang Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory

Few-shot font generation (FFG), aiming at generating font images with a few samples, is an emerging topic in recent years due to the academic and commercial values. Typically, the FFG approaches follow the style-content disentanglement paradigm, which transfers the target font styles to characters by combining the content representations of source characters and the style codes of reference samples. Most existing methods attempt to increase font generation ability via exploring powerful style representations, which may be a sub-optimal solution for the FFG task due to the lack of modeling spatial transformation in transferring font styles. In this paper, we model font generation as a continuous transformation process from the source character image to the target font image via the creation and dissipation of font pixels, and embed the corresponding transformations into a neural transformation field. With the estimated transformation path, the neural transformation field generates a set of intermediate transformation results via the sampling process, and a font rendering formula is developed to accumulate them into the target font image. Extensive experiments show that our method achieves state-of-the-art performance on few-shot font generation task, which demonstrates the effectiveness of our proposed model. Our implementation is available at: https://***/fubinfb/NTF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CAS-YNU multi-modal cross-view human action dataset

CAS-YNU multi-modal cross-view human action dataset

引用

2018 IEEE International Conference on Information and Automation, ICIA 2018

作者： Zhao, Qingsong Cheng, Jun Tao, Dapeng Ji, Xiaopeng Wang, Lei Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences China Chinese University of Hong Kong Hong Kong School of Information Science and Engineering Yunnan University China

ISBN: (纸本)9781538680698

Human action recognition is a hot research topic in computer vision, which has extensive applications including human-computer interaction, robot and surveillance. Some outstanding human action datasets have been published. However, they still have some defects, such as the limited modality types, camera views, complexity of scene and action categories. Furthermore, most of them are devised for a subset of the action recognition, such as single-modal recognition and single-view recognition. In this paper, we propose a multi-modal cross-view human action dataset (named CAS-YNU MCHAD). It consists of five synchronous data modalities, including RGB image, depth maps, human segment maps, skeleton data and inertial data. Our dataset contains 14782 action samples from 50 subjects and 10 actions in two perspectives. Extensive benchmark experiments on this dataset are conducted with the state-of-the-art recognition approaches. Experimental results illustrate that it is challenging on cross-view action recognition. We also provide the baseline for the assessment of existing recognition methods. © 2018 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Sample hardness based gradient loss for long-tailed cervical cell detection

arXiv

引用

arXiv 2022年

作者： Liu, Minmin Li, Xuechen Gao, Xiangbo Chen, Junliang Shen, Linlin Wu, Huisi Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China University of California Irvine United States

Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the cancer cells in a WSI (Whole Slice Image) image captured from the TCT (Thinprep Cytology Test) specimen, head categories (e.g. normal cells and inflammatory cells) typically have a much larger number of samples than tail categories (e.g. cancer cells). Most existing state-of-the-art long-tailed learning methods in object detection focus on category distribution statistics to solve the problem in the long-tailed scenario, without considering the "hardness" of each sample. To address this problem, in this work we propose a Grad-Libra Loss that leverages the gradients to dynamically calibrate the degree of hardness of each sample for different categories, and re-balance the gradients of positive and negative samples. Our loss can thus help the detector to put more emphasis on those hard samples in both head and tail categories. Extensive experiments on a long-tailed TCT WSI image dataset show that the mainstream detectors, e.g. RepPoints, FCOS, ATSS, YOLOF, etc. trained using our proposed Gradient-Libra Loss, achieved much higher (7.8%) mAP than that trained using cross-entropy classification loss. Copyright © 2022, The Authors. All rights reserved.

关键词： Cytology

来源：评论

学校读者我要写书评

暂无评论

StyleGene: Crossover and Mutation of Region-level Facial Genes for Kinship Face Synthesis

StyleGene: Crossover and Mutation of Region-level Facial Gen...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Hao Li Xianxu Hou Zepeng Huang Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

High-fidelity kinship face synthesis has many potential applications, such as kinship verification, missing child identification, and social media analysis. However, it is challenging to synthesize high-quality descendant faces with genetic relations due to the lack of large-scale, high-quality annotated kinship data. This paper proposes RFG (Region-level Facial Gene) extraction framework to address this issue. We propose to use IGE (Image-based Gene Encoder), LGE (Latent-based Gene Encoder) and Gene Decoder to learn the RFGs of a given face image, and the relationships between RFGs and the latent space of Style-GAN2. As cycle-like losses are designed to measure the $\mathcal{L}_{2}$ distances between the output of Gene Decoder and image encoder, and that between the output of LGE and IGE, only face images are required to train our framework, i.e. no paired kinship face data is required. Based upon the proposed RFGs, a crossover and mutation module is further designed to inherit the facial parts of parents. A Gene Pool has also been used to introduce the variations into the mutation of RFGs. The diversity of the faces of descendants can thus be significantly increased. Qualitative, quantitative, and subjective experiments on FIW, TSKinFace, and FF-Databases clearly show that the quality and diversity of kinship faces generated by our approach are much better than the existing state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Haptic display for virtual reality: progress and challenges

引用

Virtual Reality & Intelligent Hardware 2019年第2期1卷 136-162页

作者： Dangxiao WANG Yuan GUO Shiyi LIU Yuru ZHANG Weiliang XU Jing XIAO State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100083China Beijing Advanced Innovation Center for Biomedical Engineering Beihang UniversityBeijing 100083China Peng Cheng Laboratory Shenzhen 518055China Department of Mechanical Engineering University of AucklandAuckland 1142New Zealand School of Computer Science and the Robotics Engineering Program Worcester Polytechnic InstituteWorcesterMA 01609-2280USA

Immersion, interaction, and imagination are three features of virtual reality (VR). Existing VR systems possess fairly realistic visual and auditory feedbacks, and however, are poor with haptic feedback, by means of which human can perceive the physical world via abundant haptic properties. Haptic display is an interface aiming to enable bilateral signal communications between human and computer, and thus to greatly enhance the immersion and interaction of VR systems. This paper surveys the paradigm shift of haptic display occurred in the past 30 years, which is classified into three stages, including desktop haptics, surface haptics, and wearable haptics. The driving forces, key technologies and typical applications in each stage are critically reviewed. Toward the future high-fidelity VR interaction, research challenges are highlighted concerning handheld haptic device, multimodal haptic device, and high fidelity haptic rendering. In the end, the importance of understanding human haptic perception for designing effective haptic devices is addressed.

关键词： Haptic display Virtual reality Desktop haptics Surface haptics Wearable haptics Multimodal haptics

来源：评论

学校读者我要写书评

暂无评论

Q-value path decomposition for deep multiagent reinforcement learning 37

Q-value path decomposition for deep multiagent reinforcement...

引用

37th International Conference on Machine Learning, ICML 2020

作者： Yang, Yaodong Hao, Jianye Chen, Guangyong Tang, Hongyao Chen, Yingfeng Hu, Yujing Fan, Changjie Wei, Zhongyu College of Intelligence and Computing Tianjin University China Huawei Noah‘s Ark Lab Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Tencent Quantum Lab NetEase Fuxi AI Lab Fudan University China

ISBN: (纸本)9781713821120

Recently, deep multiagent reinforcement learning (MARL) has become a highly active research area as many real-world problems can be inherently viewed as multiagent systems. A particularly interesting and widely applicable class of problems is the partially observable cooperative multiagent setting, in which a team of agents learns to coordinate their behaviors conditioning on their private observations and commonly shared global reward signals. One natural solution is to resort to the centralized training and decentralized execution paradigm and during centralized training, one key challenge is the multiagent credit assignment: how to allocate the global rewards for individual agent policies for better coordination towards maximizing system-level’s benefits. In this paper, we propose a new method called Q-value Path Decomposition (QPD) to decompose the system’s global Q-values into individual agents’ Q-values. Unlike previous works which restrict the representation relation of the individual Q-values and the global one, we leverage the integrated gradient attribution technique into deep MARL to directly decompose global Q-values along trajectory paths to assign credits for agents. We evaluate QPD on the challenging StarCraft II micromanagement tasks and show that QPD achieves the state-of-the-art performance in both homogeneous and heterogeneous multiagent scenarios compared with existing cooperative MARL algorithms. Copyright 2020 by the author(s).

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semanti...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Weizhao He Yang Zhang Wei Zhuo Linlin Shen Jiaqi Yang Songhe Deng Liang Sun Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Computer Science University of Nottingham China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively.

关键词： Training Metalearning Visualization Semantic segmentation Semantics Prototypes Training data

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：