检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liu, Jinfu Chen, Chen Liu, Mengyuan State Key Laboratory of General Artificial Intelligence Peking University Shenzhen Graduate School Shenzhen China Center for Research in Computer Vision University of Central Florida Orlando United States

Skeleton-based action recognition has garnered significant attention due to the utilization of concise and resilient skeletons. Nevertheless, the absence of detailed body information in skeletons restricts performance, while other multimodal methods require substantial inference resources and are inefficient when using multimodal data during both training and inference stages. To address this and fully harness the complementary multimodal features, we propose a novel multi-modality co-learning (MMCL) framework by leveraging the multimodal large language models (LLMs) as auxiliary networks for efficient skeleton-based action recognition, which engages in multi-modality co-learning during the training stage and keeps efficiency by employing only concise skeletons in inference. Our MMCL framework primarily consists of two modules. First, the Feature Alignment Module (FAM) extracts rich RGB features from video frames and aligns them with global skeleton features via contrastive learning. Second, the Feature Refinement Module (FRM) uses RGB images with temporal information and text instruction to generate instructive features based on the powerful generalization of multimodal LLMs. These instructive text features will further refine the classification scores and the refined scores will enhance the model’s robustness and generalization in a manner similar to soft labels. Extensive experiments on NTU RGB+D, NTU RGB+D 120 and Northwestern-UCLA benchmarks consistently verify the effectiveness of our MMCL, which outperforms the existing skeleton-based action recognition methods. Meanwhile, experiments on UTD-MHAD and SYSU-Action datasets demonstrate the commendable generalization of our MMCL in zero-shot and domain-adaptive action recognition. Our code is publicly available at: https://***/liujf69/MMCL-Action. Copyright © 2024, The Authors. All rights reserved.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Circular Decomposition and Cross-Modal Recombination for Multimodal Sentiment Analysis

Circular Decomposition and Cross-Modal Recombination for Mul...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Haijian Liang Weicheng Xie Xilin He Siyang Song Linlin Shen School of Computer Science & Software Engineering Computer Vision Institue Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University School of Computing and Mathematical Sciences University of Leicester National Engineering Laboratory for Big Data System Computing Technology Shenzhen University

Multimodal Sentiment Analysis is a burgeoning research area, leveraging various modalities to predict the sentiment score. Nevertheless, previous studies have disregarded the impact of noise interference on specific modal sentiments during video recording, thereby compromising the accuracy of sentiment prediction. In this paper, we propose the Guided Circular Decomposition and Cross-Modal Recombination (GCD-CMR) model, which aims to eliminate contaminated sentiment features in a fine-grained way. To achieve this, we utilize tailored global information specific to each modality to guide the circular decomposing process in the GCD module, to produce a set of sentiment prototypes. Subsequently, in the CMR module, we align cross-modal sentiment prototypes and remove the contaminated prototypes for recombination. Experimental results on two publicly available datasets demonstrate that our model surpasses state-of-the-art models, confirming the effectiveness of our proposed method. We release the code at: https://***/nianhua20/GCD-CMR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UniTSFace: unified threshold integrated sample-to-sample loss for face recognition 23

UniTSFace: unified threshold integrated sample-to-sample los...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Qiufu Li Xi Jia Jiancan Zhou Linlin Shen Jinming Duan National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and School of Computer Science University of Birmingham UK National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and Aqara Lumi United Technology Co. Ltd China School of Computer Science University of Birmingham UK and Alan Turing Institute UK

Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available at https://***/CVI-SZU/UniTSFace.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Manifold-preserved GANs

arXiv

引用

arXiv 2021年

作者： Liu, Haozhe Liang, Hanbang Hou, Xianxu Wu, Haoqian Liu, Feng Shen, Linlin College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

Generative Adversarial Networks (GANs) have been widely adopted in various fields. However, existing GANs generally are not able to preserve the manifold of data space, mainly due to the simple representation of discriminator for the real/generated data. To address such open challenges, this paper proposes Manifold-preserved GANs (MaF-GANs), which generalize Wasserstein GANs into high-dimensional form. Specifically, to improve the representation of data, the discriminator in MaF-GANs is designed to map data into a high-dimensional manifold. Furthermore, to stabilize the training of MaF-GANs, an operation with precise and universal solution for any K-Lipschitz continuity, called Topological Consistency is proposed. The effectiveness of the proposed method is justified by both theoretical analysis and empirical results. When adopting DCGAN as the backbone on CelebA (256×256), the proposed method achieved 12.43 FID, which outperforms the state-of-the-art model like Realness GAN (23.51 FID) by a large margin. Code will be made publicly available. Copyright © 2021, 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

Locating high-density clusters with noisy queries

Locating high-density clusters with noisy queries

引用

International Conference on Pattern Recognition

作者： Chen Cao Shifeng Chen Changqing Zou Jianzhuang Liu Shenzhen Key Laboratory for Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Department of Information Engineering Chinese University of Hong Kong China

ISBN: (纸本)9781467322164

Semi-supervised learning (SSL) relies on a few labeled samples to explore data's intrinsic structure through pairwise smooth transduction. The performance of SSL mainly depends on two folds: (1) the accuracy of labeled queries, (2) the integrity of manifolds in data distribution. Both of these qualities would be poor in real applications as data often consist of several irrelevant clusters and discrete noise. In this paper we propose a novel framework to simultaneously remove discrete noise and locate the high-density clusters. Experiments demonstrate that our algorithm is quite effective to solve several problems such as non-feedback image re-ranking and image co-segmentation.

关键词： Noise Noise measurement Clustering algorithms Databases Vectors Manifolds Semisupervised learning

来源：评论

学校读者我要写书评

暂无评论

Compressed sensing ensemble classifier for human detection

Compressed sensing ensemble classifier for human detection

引用

4th International Conference on Intelligence Science and Big Data Engineering, IScIDE 2013

作者： Zhang, Baochang Liu, Juan Gao, Yongsheng Liu, Jianzhuang Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical Engineering BeiHang University Beijing 100191 China School of Engineering Griffith University Australia Shenzhen Key Lab for Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Department of Information Engineering Chinese University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9783642420566

This paper proposes a novel Compressed Sensing Ensemble Classifier (CSEC) for human detection. The proposed CSEC employs the compressed sensing technique to get a more sparse model with a more reasonable selection of base classifiers. The major contributions of this paper are: 1) a novel principled framework for ensemble classifier design based on compressed sensing;2) a new concept of considering both the simplicity of ensemble classifier and irrelevance of base classifiers towards optimal classifier design;and 3) a quadratic function for CSEC optimization which includes a new optimizable positive semi-definite relevance matrix to simultaneously select appropriate base classifiers with minimized relevance. Experimental results on INRIA and SDL databases show that the performance of CSEC is better than two most popular classifiers SVM and AdaBoost, as well as a most recent method CLML. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models

arXiv

引用

arXiv 2024年

作者： Li, Peiming Wang, Ziyi Liu, Mengyuan Liu, Hong Chen, Chen State Key Laboratory of General Artificial Intelligence Peking University Shenzhen Graduate School Shenzhen China Center for Research in Computer Vision University of Central Florida Orlando United States

Grasp generation aims to create complex hand-object interactions with a specified object. While traditional approaches for hand generation have primarily focused on visibility and diversity under scene constraints, they tend to overlook the fine-grained hand-object interactions such as contacts, resulting in inaccurate and undesired grasps. To address these challenges, we propose a controllable grasp generation task and introduce ClickDiff, a controllable conditional generation model that leverages a fine-grained Semantic Contact Map (SCM). Particularly when synthesizing interactive grasps, the method enables the precise control of grasp synthesis through either user-specified or algorithmically predicted Semantic Contact Map. Specifically, to optimally utilize contact supervision constraints and to accurately model the complex physical structure of hands, we propose a Dual Generation Framework. Within this framework, the Semantic Conditional Module generates reasonable contact maps based on fine-grained contact information, while the Contact Conditional Module utilizes contact maps alongside object point clouds to generate realistic grasps. We evaluate the evaluation criteria applicable to controllable grasp generation. Both unimanual and bimanual generation experiments on GRAB and ARCTIC datasets verify the validity of our proposed method, demonstrating the efficacy and robustness of ClickDiff, even with previously unseen objects. Our code is available at https://***/adventurer-w/ClickDiff. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Distributional Estimation of Data Uncertainty for Surveillance Face Anti-spoofing

arXiv

引用

arXiv 2023年

作者： Huang, Mouxiao The Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Shenzhen China

Face recognition systems have become increasingly vulnerable to security threats in recent years, prompting the use of Face Anti-spoofing (FAS) to protect against various types of attacks, such as phone unlocking, face payment, and self-service security inspection. While FAS has demonstrated its effectiveness in traditional settings, securing it in long-distance surveillance scenarios presents a significant challenge. These scenarios often feature low-quality face images, necessitating the modeling of data uncertainty to improve stability under extreme conditions. To address this issue, this work proposes Distributional Estimation (DisE), a method that converts traditional FAS point estimation to distributional estimation by modeling data uncertainty during training, including feature (mean) and uncertainty (variance). By adjusting the learning strength of clean and noisy samples for stability and accuracy, the learned uncertainty enhances DisE's performance. The method is evaluated on SuHiFiMask [1], a large-scale and challenging FAS dataset in surveillance scenarios. Results demonstrate that DisE achieves comparable performance on both ACER and AUC metrics. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

FusionPortableV2: A Unified Multi-Sensor Dataset for Generalized SLAM Across Diverse Platforms and Scalable Environments

arXiv

引用

arXiv 2024年

作者： Wei, Hexiang Jiao, Jianhao Hu, Xiangcheng Yu, Jingwen Xie, Xupeng Wu, Jin Zhu, Yilong Liu, Yuxuan Wang, Lujia Liu, Ming Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Robot Perception and Learning Lab Department of Computer Science University College London United Kingdom Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology China Guangzhou China

Simultaneous Localization and Mapping (SLAM) technology has been widely applied in various robotic scenarios, from rescue operations to autonomous driving. However, the generalization of SLAM algorithms remains a significant challenge, as current datasets often lack scalability in terms of platforms and environments. To address this limitation, we present FusionPortableV2, a multi-sensor SLAM dataset featuring sensor diversity, varied motion patterns, and a wide range of environmental scenarios. Our dataset comprises 27 sequences, spanning over 2.5 hours and collected from four distinct platforms: a handheld suite, a legged robot, a unmanned ground vehicle (UGV), and a vehicle. These sequences cover diverse settings, including buildings, campuses, and urban areas, with a total length of 38.7km. Additionally, the dataset includes ground-truth (GT) trajectories and RGB point cloud maps covering approximately 0.3km2. To validate the utility of our dataset in advancing SLAM research, we assess several state-of-the-art (SOTA) SLAM algorithms. Furthermore, we demonstrate the dataset's broad application beyond traditional SLAM tasks by investigating its potential for monocular depth estimation. The completae dataset, including sensor data, GT, and calibration details, is accessible at https://***/dataset/fusionportable v2. Copyright © 2024, The Authors. All rights reserved.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

A novel feature extracting method for dynamic gesture recognition based on support vector machine

A novel feature extracting method for dynamic gesture recogn...

引用

International Conference on Information and Automation (ICIA)

作者： Yuanrong Xu Qianqian Wang Xiao Bai Yen-Lun Chen Xinyu Wu Shenzhen Key Lab for Computer Vision and Pattern Recognition Chinese Academy of Sciences University of Science and Technology of China Dept. Mechanical and Automation Engineering The Chinese University of Hong Kong Guangdong Provincial Key Laboratory of Robotics and Intelligent System Chinese Academy of Sciences

In this paper, we propose a method based on the SVM algorithm to recognize dynamic hand gestures. The information of motion trajectory is captured by a leap motion in three-dimension space. A new methodology of feature extracting is proposed to guarantee the length of samples being the same. The elements of feature vectors are ranged according to two different criteria: one is the amplitude of the variation of orientation angles, and the other criterion is the order of the appearance of features. Experimental results show that this method can classify the dynamic hand gestures effectively.

关键词： Vectors Trajectory Feature extraction Equations Mathematical model Hidden Markov models Automation

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：