检索结果-内蒙古大学图书馆

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China Department of Computer Science University of Exeter United Kingdom

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

学校读者我要写书评

暂无评论

GUEST EDITORIAL

China Communications 2022年第1期 4-9页

作者： Zhenyu Xiao Qihui Wu Jiajia Liu Ning Zhang Tao Sun the School of Electronic and Information Engineering Beihang University IET China Institute of Communications and of Electronics the Nanjing University of Aeronautics and Astronautics (NUAA) key lab of Ministry of Industry and Information Technology of China the School of Cybersecurity Northwestern Polytechnical University Shaanxi Provincial Engineering Laboratory of Cyber Security Xi’an Unmanned System Security and Intelligent Communications ISTC Center IEEE IOT-AHSN TC IEEE Communications Society IEEE Vehicular Technology Society the Department of Electrical and Computer Engineering at University of Windsor China Mobile Research Institute 3GPP SA2 China Mobile’s 3GPP SA and CT groups

Space-Air-Ground Integrated Network with Native Intelligence(NI-SAGIN): Concept, Architecture, Access and Networking Ubiquitous coverage is one of the most important goals for mobile communication networks. To achieve this, integration of space, air, and ground networks is highly demanded, which expects to become the one of the enabling technologies for 6G networks. However, the integrated network faces the demand of orders of magnitude improvement in coverage,

关键词：

Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Tianlin Zhang, Lingling Wang, Jiaxin Lei, Yunkuo Li, Yifei Wang, Haofen Liu, Jun School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi’an710049 China School of Computer Science and Technology Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi’an710049 China College of Design and Innovation Tongji University Shanghai200092 China

Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bao, Shilong Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Alibaba Group China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China Peng Cheng Laboratory China

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a diversity control regularization term to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML. © 2022, CC BY-NC-SA.

关键词： Embeddings

Short-term Portfolio Optimization using Doubly Regularized Exponential Growth Rate

学校读者我要写书评

暂无评论

Short-term Portfolio Optimization using Doubly Regularized E...

International Conference on Computer Supported Cooperative Work in Design

作者： Quanlong Guan Jinneng He Zhao-Rong Lai Yuyu Zhou Quming Jiang Ziliang Chen College of Information Science and Technology Jinan University Guangzhou China Guangdong Institute of Smart Education Jinan University Guangzhou China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China Guangdong-Macao Advanced Intelligent Computing Joint Laboratory Zhuhai China Chutian Dragon Co. Ltd Dongguan China School of Intelligent Systems Science and Engineering Jinan University China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In the realm of short-term portfolio optimization, the integration of machine learning with exponential growth rate techniques is gaining prominence. This paper introduces a novel approach for short-term portfolio optimization, termed Short-term Portfolio Optimization using Doubly Regularized EGR (SPODR), to address the challenges posed by limited data availability. SPODR utilizes radial basis functions for the effective identification of market trends, enabling improved stock market forecasts. The approach uniquely combines ℓ 1 and ℓ 2 -regularization, adhering to empirical financial principles, to strike a balance between risk and return in short-term portfolios. A key aspect of SPODR is addressing the complexity of its ElasticNet-like objective, which poses a challenge for traditional methods due to its online learning nature. To overcome this, we have developed an algorithm based on the log barrier interior-point method. This algorithm is adept at efficiently optimizing portfolio allocation, taking into account the specific constraints inherent in our approach. Extensive comparative experiments across five benchmark datasets demonstrate that SPODR significantly outperforms existing short-term portfolio optimization models. It achieves a right balance between return and risk. Furthermore, SPODR showcases efficient computational speed, enhancing its applicability in real-world financial settings.

关键词： Computational modeling Benchmark testing Market research Robustness Regulation Computational efficiency Resource management

Hard Sample Matters a Lot in Zero-Shot Quantization

学校读者我要写书评

暂无评论

Hard Sample Matters a Lot in Zero-Shot Quantization

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Huantong Li Xiangmiao Wu Fanbing Lv Daihai Liao Thomas H. Li Yonggang Zhang Bo Han Mingkui Tan South China University of Technology Information Technology R&D Innovation Center of Peking University Changsha Hisense Intelligent System Research Institute Co. Ltd School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen China Hong Kong Baptist University Key Laboratory of Big Data and Intelligent Robot Ministry of Education PengCheng Laboratory

Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural networks when the data for training full-precision models are inaccessible. In ZSQ, network quantization is performed using synthetic samples, thus, the performance of quantized models depends heavily on the quality of synthetic samples. Nonetheless, we find that the synthetic samples constructed in existing ZSQ methods can be easily fitted by models. Accordingly, quantized models obtained by these methods suffer from significant performance degradation on hard samples. To address this issue, we propose HArd sample Synthesizing and Training (HAST). Specifically, HAST pays more attention to hard samples when synthesizing samples and makes synthetic samples hard to fit when training quantized models. HAST aligns features extracted by full-precision and quantized models to ensure the similarity between features extracted by these two models. Extensive experiments show that HAST significantly outperforms existing ZSQ methods, achieving performance comparable to models that are quantized with real data.

关键词：

Research on intelligent Scheduling Method of Multi-Machine Cooperative Operation Based on Nsga-Iii and Improved Ant Colony Algorithm

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Zhang, Man Li, Shichao Cao, Ruyue Wang, Ning Zhang, Zhenqian Ji, Yuhan Li, Han Wang, Hao Key Lab of Smart Agriculture System Integration Ministry of Education China Agricultural University Beijing100083 China Key Laboratory of Agricultural Machinery Monitoring and Big Data Applications Ministry of Agriculture and Rural Affairs Beijing100083 China National Research Center of Intelligent Equipment for Agriculture Beijing100097 China

Aiming at the problems of over-reliance on traditional manual harvest operation experience and lack of effective collaborative operation scheduling method in agricultural machinery cluster operation in agricultural harvest scenario. A multi-objective combined optimization intelligent scheduling model of harvesters and grain transport vehicles was established to save agricultural machinery resources, and improve the overall efficiency of harvesters and transport vehicles, to meet the constraints of plot location, task number, operation time window, and path planning. The model was solved by an intelligent search algorithm, and an intelligent scheduling method of command multi-machine cooperative operation based on NSGA-III and an improved ant colony algorithm was proposed. It can be seen from the simulation test that the scheduling model established, and the solution algorithm designed in this research can obtain many groups of good optimization results. Moreover, it can make the unproductive waiting time of harvester 0, and minimize the transfer distance and number of grain transporters. This method can be combined closely with the practical application of unmanned farms, which lays a theoretical foundation for improving the efficiency of multi-machine cooperative operations. © 2022, The Authors. All rights reserved.

关键词： Scheduling

A Wolf in Sheep's Clothing: Practical Black-box Adversarial Attacks for Evading Learning-based Windows Malware Detection in the Wild

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ling, Xiang Wu, Zhiyu Wang, Bin Deng, Wei Wu, Jingzheng Ji, Shouling Luo, Tianyue Wu, Yanjun Intelligent Software Research Center Institute of Software Chinese Academy of Sciences China China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Network and Data Security China Hangzhou Research Institute Xidian University China Zhejiang University China

Given the remarkable achievements of existing learning-based malware detection in both academia and industry, this paper presents MalGuise, a practical black-box adversarial attack framework that evaluates the security risks of existing learning-based Windows malware detection systems under the black-box setting. MalGuise first employs a novel semantics-preserving transformation of call-based redividing to concurrently manipulate both nodes and edges of malware's control-flow graph, making it less noticeable. By employing a Monte-Carlo-tree-search-based optimization, MalGuise then searches for an optimized sequence of call-based redividing transformations to apply to the input Windows malware for evasions. Finally, it reconstructs the adversarial malware file based on the optimized transformation sequence while adhering to Windows executable format constraints, thereby maintaining the same semantics as the original. MalGuise is systematically evaluated against three state-of-the-art learning-based Windows malware detection systems under the black-box setting. Evaluation results demonstrate that MalGuise achieves a remarkably high attack success rate, mostly exceeding 95%, with over 91% of the generated adversarial malware files maintaining the same semantics. Furthermore, MalGuise achieves up to a 74.97% attack success rate against five anti-virus products, highlighting potential tangible security concerns to real-world users. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

XTQA: Span-Level Explanations for Textbook Question Answering

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ma, Jie Chai, Qi Liu, Jun Yin, Qingyu Wang, Pinghui Zheng, Qinghua Ministry of Education of Key Lab for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering The School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Amazon United States

Textbook Question Answering (TQA) is the task of correctly answering diagram or non-diagram questions given large multi-modal contexts consisting of abundant essays and diagrams. In real-world scenarios, an explainable TQA system plays a key role in deepening humans’ understanding of learned knowledge. However, there is no work to investigate how to provide explanations currently. To address this issue, we devise a novel architecture towards span-level eXplanations for TQA (XTQA). In this paper, spans are the combinations of sentences within a paragraph. The key idea is to consider the entire textual context of a lesson as candidate evidence, and then use our proposed coarse-to-fine grained Explanation Extracting (EE) algorithm to narrow down the evidence scope and extract the span-level explanations with varying lengths for answering different questions. The EE algorithm can also be integrated into other TQA methods to make them explainable and improve the TQA performance. Experimental results show that XTQA obtains the best overall explanation result (mIoU) of 52.38% on the first 300 questions of CK12-QA test splits, demonstrating the explainability of our method (non-diagram: 150 and diagram: 150). The results also show that XTQA achieves the best TQA performance of 36.46% and 36.95% on the aforementioned splits respectively. We have released our code in https://***/dr-majie/*** Codes 68T07 Copyright © 2020, The Authors. All rights reserved.

关键词： Textbooks