检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Chaolei Tan Jianhuang Lai Wei-Shi Zheng Jian-Fang Hu School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Video Paragraph Grounding (VPG) is an emerging task in video-language understanding, which aims at localizing multiple sentences with semantic relations and temporal or-der from an untrimmed video. However, existing VPG approaches are heavily reliant on a considerable number of temporal labels that are laborious and time-consuming to acquire. In this work, we introduce and explore Weakly-Supervised Video Paragraph Grounding (WSVPG) to elim-inate the need of temporal annotations. Different from pre-vious weakly-supervised grounding frameworks based on multiple instance learning or reconstruction learning for two-stage candidate ranking, we propose a novel siamese learning framework that jointly learns the cross-modal feature alignment and temporal coordinate regression without timestamp labels to achieve concise one-stage localization for WSVPG. Specifically, we devise a Siamese Grounding TRansformer (SiamGTR) consisting of two weight-sharing branches for learning complementary supervision. An Aug-mentation Branch is utilized for directly regressing the tem-poral boundaries of a complete paragraph within a pseudo video, and an Inference Branch is designed to capture the order-guided feature correspondence for localizing multi-ple sentences in a normal video. We demonstrate by exten-sive experiments that our paradigm has superior practica-bility and flexibility to achieve efficient weakly-supervised or semi-supervised learning, outperforming state-of-the-art methods trained with the same or stronger supervision.

关键词： Location awareness Computer vision Grounding Annotations Semantics Semisupervised learning Transformers

来源：评论

学校读者我要写书评

暂无评论

An Economic Framework for 6-DoF Grasp Detection

arXiv

引用

arXiv 2024年

作者： Wu, Xiao-Ming Cai, Jia-Feng Jiang, Jian-Jian Zheng, Dian Wei, Yi-Lin Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Peng Cheng Laboratory Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Robotic grasping in clutters is a fundamental task in robotic manipulation. In this work, we propose an economic framework for 6-DoF grasp detection, aiming to economize the resource cost in training and meanwhile maintain effective grasp performance. To begin with, we discover that the dense supervision is the bottleneck of current SOTA methods that severely encumbers the entire training overload, meanwhile making the training difficult to converge. To solve the above problem, we first propose an economic supervision paradigm for efficient and effective grasping. This paradigm includes a well-designed supervision selection strategy, selecting key labels basically without ambiguity, and an economic pipeline to enable the training after selection. Furthermore, benefit from the economic supervision, we can focus on a specific grasp, and thus we devise a focal representation module, which comprises an interactive grasp head and a composite score estimation to generate the specific grasp more accurately. Combining all together, the EconomicGrasp framework is proposed. Our extensive experiments show that EconomicGrasp surpasses the SOTA grasp method by about 3AP on average, and with extremely low resource cost, for about 1/4 training time cost, 1/8 memory cost and 1/30 storage cost. Our code is available at https://***/iSEE-laboratory/EconomicGrasp. Copyright © 2024, The Authors. All rights reserved.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Progressive Pretext Task Learning for Human Trajectory Prediction

arXiv

引用

arXiv 2024年

作者： Lin, Xiaotong Liang, Tianming Lai, Jianhuang Hu, Jian-Fang School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Human trajectory prediction is a practical task of predicting the future positions of pedestrians on the road, which typically covers all temporal ranges from short-term to long-term within a trajectory. However, existing works attempt to address the entire trajectory prediction with a singular, uniform training paradigm, neglecting the distinction between short-term and long-term dynamics in human trajectories. To overcome this limitation, we introduce a novel Progressive Pretext Task learning (PPT) framework, which progressively enhances the model's capacity of capturing short-term dynamics and long-term dependencies for the final entire trajectory prediction. Specifically, we elaborately design three stages of training tasks in the PPT framework. In the first stage, the model learns to comprehend the short-term dynamics through a stepwise next-position prediction task. In the second stage, the model is further enhanced to understand long-term dependencies through a destination prediction task. In the final stage, the model aims to address the entire future trajectory task by taking full advantage of the knowledge from previous stages. To alleviate the knowledge forgetting, we further apply a cross-task knowledge distillation. Additionally, we design a Transformer-based trajectory predictor, which is able to achieve highly efficient two-step reasoning by integrating a destination-driven prediction strategy and a group of learnable prompt embeddings. Extensive experiments on popular benchmarks have demonstrated that our proposed approach achieves state-of-the-art performance with high efficiency. Code is available at https://***/iSEE-laboratory/PPT. Copyright © 2024, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Excellent Student Training in Shielding Effectiveness Analysis with International Cooperation 10

Excellent Student Training in Shielding Effectiveness Analys...

引用

10th IEEE International Conference on Computer Science and Network Technology, ICCSNT 2022

作者： Li, Yingsong Huang, Zhixiang Wang, Meiyu Jiang, Tao Sinkevich, Eugene Mordachev, Vladimir College of Information and Communication Engineering Harbin Engineering University Harbin15001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Belarusian State University of Informatics and Radioelectronics Emc RandD Laboratory Minsk Belarus

ISBN: (数字)9781665470612

ISBN: (纸本)9781665470612

We present the excellent student training scheme in shielding effectiveness analysis with international cooperation of Belarus. As we know, the shielding is vital for modern information devices due to the radiating around us. Herein, the shielding effectiveness is important for training excellent students to master the design of the frequency selective components. In this method, we teach the students to use the EM simulation tools to construct different EM structures for obtaining the shielding, and the performance of these structures are verified from the simulations and measurements. Using this shielding effectiveness training scheme, a frequency selective surface is presented, simulated and discussed to analyze its performance. In future, the excellent student training methods given herein for shielding effectiveness can be expanded to develop other EM structures. © 2022 IEEE.

关键词： International cooperation

来源：评论

学校读者我要写书评

暂无评论

Differentiable Gated Autoencoders for Unsupervised Feature Selection

SSRN

引用

SSRN 2024年

作者： Chen, Zebin Bian, Jintang Qiao, Bo Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Unsupervised feature selection (UFS) aims to identify a subset of the most informative features from high-dimensional data without labels. However, most existing UFS methods cannot adequately capture the intricate nonlinear relationships present in high-dimensional data, limiting their ability to obtain meaningful features. In this letter, we propose a novel UFS model that leverages the autoencoder with a differentiable gating function to address this limitation. Our model optimizes a bi-level loss function to automatically select a subset of informative and stable features by capturing the nonlinear interactions between features. Furthermore, we leverage the continuous relaxation of the Bernoulli distribution to parameterize stochastic gates, thereby enabling the learning of a relaxed model through a low-variance gradient estimator. The proposed model does not necessitate prior knowledge or domain-specific tuning, making it a versatile and widely applicable method. Extensive experiments on 13 benchmark datasets demonstrate the effectiveness and superiority of the proposed method. © 2024, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A Method for Generating Medical Text Data by Integrating Spatiotemporal Attributes and Implicit State Transitions 9

A Method for Generating Medical Text Data by Integrating Spa...

引用

9th IEEE International Conference on Data Science in Cyberspace, DSC 2024

作者： Yang, Xu Sun, Lijuan Gao, Yutong Guo, Sanchuan Wu, Xu Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing China Beijing University of Posts and Telecommunications School of Cyberspace Security BUPT Beijing China Beihang University Intellectual Property Information Service Center Beijing China Minzu University of China School of Information Engineering China

ISBN: (纸本)9798350391367

This study aims to generate medical text data that integrates spatiotemporal attributes to solve the problems of small size and low availability of open source text datasets due to the privacy of medical data. This paper optimizes the LeakGAN model by using a multi-layer LSTM structure and increasing the number of hidden and embedding layers to help generate networks that capture long-distance dependencies in data. In addition, we designed a spatiotemporal data generation method based on random algorithms and Markov chains to generate the spatiotemporal attributes of electronic medical records. In order to comprehensively evaluate the generation effect of the model, this paper evaluates from similarity-based indicators and likelihood-based indicators. The results show that the method designed in this article is 2.038 better than other models on NLL-oracle, 0.016 on NLL-test, and 0.0069 on EmbSim. The method proposed in this article has good ability to fit real data and can avoid the high cost and privacy leakage problems faced when manually constructing electronic medical record data sets by generating realistic medical electronic medical record synthetic data. This method also provides new solutions to the problem of insufficient data sets faced by more downstream applications (such as data auditing, anomaly detection, etc.). © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding

arXiv

引用

arXiv 2024年

作者： Tan, Chaolei Lai, Jianhuang Zheng, Wei-Shi Hu, Jian-Fang School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Video Paragraph Grounding (VPG) is an emerging task in video-language understanding, which aims at localizing multiple sentences with semantic relations and temporal order from an untrimmed video. However, existing VPG approaches are heavily reliant on a considerable number of temporal labels that are laborious and time-consuming to acquire. In this work, we introduce and explore Weakly-Supervised Video Paragraph Grounding (WSVPG) to eliminate the need of temporal annotations. Different from previous weakly-supervised grounding frameworks based on multiple instance learning or reconstruction learning for two-stage candidate ranking, we propose a novel siamese learning framework that jointly learns the cross-modal feature alignment and temporal coordinate regression without timestamp labels to achieve concise one-stage localization for WSVPG. Specifically, we devise a Siamese Grounding TRansformer (SiamGTR) consisting of two weight-sharing branches for learning complementary supervision. An Augmentation Branch is utilized for directly regressing the temporal boundaries of a complete paragraph within a pseudo video, and an Inference Branch is designed to capture the order-guided feature correspondence for localizing multiple sentences in a normal video. We demonstrate by extensive experiments that our paradigm has superior practicability and flexibility to achieve efficient weakly-supervised or semi-supervised learning, outperforming state-of-the-art methods trained with the same or stronger supervision. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Lips are lying: spotting the temporal inconsistency between audio and visual in lip-syncing DeepFakes 24

Lips are lying: spotting the temporal inconsistency between ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Weifeng Liu Tianyi She Jiawei Liu Boheng Li Dongyu Yao Ziyou Liang Run Wang Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China Nanyang Technological University Carnegie Mellon University

ISBN: (纸本)9798331314385

In recent years, DeepFake technology has achieved unprecedented success in high-quality video synthesis, but these methods also pose potential and severe security threats to humanity. DeepFake can be bifurcated into entertainment applications like face swapping and illicit uses such as lip-syncing fraud. However, lip-forgery videos, which neither change identity nor have discernible visual artifacts, present a formidable challenge to existing DeepFake detection methods. Our preliminary experiments have shown that the effectiveness of the existing methods often drastically decrease or even fail when tackling lip-syncing videos. In this paper, for the first time, we propose a novel approach dedicated to lip-forgery identification that exploits the inconsistency between lip movements and audio signals. We also mimic human natural cognition by capturing subtle biological links between lips and head regions to boost accuracy. To better illustrate the effectiveness and advances of our proposed method, we create a high-quality LipSync dataset, AVLips, by employing the state-of-the-art lip generators. We hope this high-quality and diverse dataset could be well served the further research on this challenging and interesting field. Experimental results show that our approach gives an average accuracy of more than 95.3% in spotting lip-syncing videos, significantly outperforming the baselines. Extensive experiments demonstrate the capability to tackle deepfakes and the robustness in surviving diverse input transformations. Our method achieves an accuracy of up to 90.2% in real-world scenarios (e.g., WeChat video call) and shows its powerful capabilities in real scenario deployment. To facilitate the progress of this research community, we release all resources at https://***/AaronComo/LipFD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Optimization of Stacked Chip Macro-Module Layout Based on Memristor-Inspired Evolutionary Game 4

Multi-Modal Optimization of Stacked Chip Macro-Module Layout...

引用

4th International Conference on Electronic Information engineering and Computer Communication, EIECC 2024

作者： Qiao, Kaikai Ma, Ben Chen, Mingze Ding, Ke Li, Changqing Duan, Shukai Wang, Lidan Southwest University College of Artificial Intelligence Chongqing China College of Artificial Intelligence Southwest University Chongqing China National Local Joint Engineering Research Center of of Intelligent Transmission and Control Technology Chongqing China Chongqing Key Laboratory of Brain-inspired Computing and Intelligent Chips Chongqing China Ministry of Education Chongqing China

ISBN: (纸本)9798331534622

As the complexity of chip design continues to increase, the stacking of multiple device layers in a three dimension(3D) architecture has emerged as a promising approach, which aims to optimize the placement and interconnections of large function blocks across the vertically-stacked device layers. Due to the complex interactions between layout and design constraints, traditional deterministic optimization often struggle to navigate its multi-modal search landscape effectively. Thus, we creatively propose the memristive evolutionary game: the diverse metal layers engage in a strategic interplay that determines the ownership hierarchy of chip macro modules and the 2D layout of these chip macro modules within each designated metal layer is orchestrated using evolutionary algorithm, which harness the power of game theoretic evolution to seek the optimal solution, balancing the objectives of minimizing layout area and wiring length. Upon comparison with alternative algorithms, the game evolution algorithm introduced in this paper exhibits superior optimization performance. © 2024 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

A physics-informed data-driven model for landslide susceptibility assessment in the Three Gorges Reservoir area

引用

Geoscience Frontiers 2023年第5期14卷 1-16页

作者： Songlin Liu Luqi Wang Wengang Zhang Weixin Sun Jie Fu Ting Xiao Zhenwei Dai School of Civil Engineering Chongqing UniversityChongqing 400045China Key Laboratory of New Technology for Construction of Cities in Mountain Area Chongqing UniversityMinistry of EducationChongqing 400045China National Joint Engineering Research Center of Geohazards Prevention in the Reservoir Areas Chongqing UniversityChongqing 400045China Chongqing Field Scientific Observation Station for Landslide Hazards in Three Gorges Reservoir Area Chongqing UniversityChongqing 400045China Center for Hydrogeology and Environmental Geology CGSBaoding Hebei 071051China Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring Ministry of EducationSchool of Geosciences and Info-PhysicsCentral South UniversityChangsha 410083China Central South China Innovation Center for Geosciences Wuhan Centre of China Geological SurveyWuhan 430205China

Landslide susceptibility mapping is a crucial tool for analyzing geohazards in a *** publications have popularized data-driven models,particularly machine learning-based methods,owing to their strong capability in dealing with complex nonlinear ***,a significant proportion of these models have neglected qualitative aspects during analysis,resulting in a lack of interpretability throughout the process and causing inaccuracies in the negative sample *** this study,Scoops 3D was employed as a physics-informed tool to qualitatively assess slope stability in the study area(the Hubei Province section of the Three Gorges Reservoir Area).The non-landslide samples were extracted based on the calculated factor of safety(FS).Subsequently,the random forest algorithm was employed for data-driven landslide susceptibility analysis,with the area under the receiver operating characteristic curve(AUC)serving as the model evaluation *** to the benchmark model(i.e.,the standard method of utilizing the pure random forest algorithm),the proposed method’s AUC value improved by 20.1%,validating the effectiveness of the dual-driven method(physics-informed data-driven).

关键词： Machine Learning Physics-informed Negative sample extraction Interpretability Dual-driven

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：