检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Xiaoqin Ma, Xusen Hou, Xianxu Ding, Meidan Li, Yudong Chen, Junliang Chen, Wenting Peng, Xiaoyang Shen, Linlin Computer Vision Institute College 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 AIAC Xi’an Jiaotong-Liverpool University China Tsinghua University China The Hong Kong Polytechnic University Hong Kong City University of Hong Kong Hong Kong Sun Yat-sen University China

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in various tasks. However, effectively evaluating these MLLMs on face perception remains largely unexplored. To address this gap, we introduce FaceBench, a dataset featuring hierarchical multi-view and multi-level attributes specifically designed to assess the comprehensive face perception abilities of MLLMs. Initially, we construct a hierarchical facial attribute structure, which encompasses five views with up to three levels of attributes, totaling over 210 attributes and 700 attribute values. Based on the structure, the proposed FaceBench consists of 49,919 visual question-answering (VQA) pairs for evaluation and 23,841 pairs for fine-tuning. Moreover, we further develop a robust face perception MLLM baseline, Face-LLaVA, by training with our proposed face VQA data. Extensive experiments on various mainstream MLLMs and Face-LLaVA are conducted to test their face perception ability, with results also compared against human performance. The results reveal that, the existing MLLMs are far from satisfactory in understanding the fine-grained facial attributes, while our Face-LLaVA significantly outperforms existing open-source models with a small amount of training data and is comparable to commercial ones like GPT-4o and Gemini. The dataset will be released at https://***/CVI-SZU/FaceBench. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hypotheses Tree Building for One-Shot Temporal Sentence Localization

arXiv

引用

arXiv 2023年

作者： Liu, Daizong Fang, Xiang Zhou, Pan Di, Xing Lu, Weining Cheng, Yu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China Peking University China Nanyang Technological University Singapore ProtagoLabs Inc United States Tsinghua University China Microsoft Research United States

Given an untrimmed video, temporal sentence localization (TSL) aims to localize a specific segment according to a given sentence query. Though respectable works have made decent achievements in this task, they severely rely on dense video frame annotations, which require a tremendous amount of human effort to collect. In this paper, we target another more practical and challenging setting: one-shot temporal sentence localization (one-shot TSL), which learns to retrieve the query information among the entire video with only one annotated frame. Particularly, we propose an effective and novel tree-structure baseline for one-shot TSL, called Multiple Hypotheses Segment Tree (MHST), to capture the query-aware discriminative frame-wise information under the insufficient annotations. Each video frame is taken as the leaf-node, and the adjacent frames sharing the same visual-linguistic semantics will be merged into the upper non-leaf node for tree building. At last, each root node is an individual segment hypothesis containing the consecutive frames of its leaf-nodes. During the tree construction, we also introduce a pruning strategy to eliminate the interference of query-irrelevant nodes. With our designed self-supervised loss functions, our MHST is able to generate high-quality segment hypotheses for ranking and selection with the query. Experiments on two challenging datasets demonstrate that MHST achieves competitive performance compared to existing methods. Copyright © 2023, 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

NONSMOOTH INTERVAL-VALUED MULTIOBJECTIVE OPTIMIZATION PROBLEMS AND GENERALIZED VARIATIONAL INEQUALITIES ON HADAMARD MANIFOLDS

Applied Set-Valued Analysis and Optimization

引用

Applied Set-Valued Analysis and Optimization 2023年第1期5卷 69-84页

作者： Upadhyay, B.B. Li, Lijie Mishra, Priyanka Department of Mathematics Indian Institute of Technology Patna Bihar Patna801103 India Guangxi Colleges Universities Key Laboratory of Complex System Optimization and Big Data Processing Yulin Normal University Guangxi Yulin537000 China Mathematics Division School of Advanced Sciences and Languages VIT Bhopal University Bhopal-Indore Highway Kothrikalan Madhya Pradesh Sehore466114 India

In this paper, we study the classes of approximate Minty and Stampacchia type vector variational inequalities along with their local and weak versions on a Hadamard manifold, and a class of nonsmooth interval-valued multiobjective optimization problems, respectively. We obtain the equivalence between the solutions of considered approximate vector variational inequalities and LU-efficient solutions of nonsmooth interval-valued multiobjective optimization problems in which the cost function is assumed to be geodesic approximately LU-convex or geodesic LU-α-convex. ©2023 Applied Set-Valued Analysis and Optimization.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

When to update your model: constrained model-based reinforcement learning 22

When to update your model: constrained model-based reinforce...

引用

Proceedings of the 36th International Conference on Neural Information Processing systems

作者： Tianying Ji Yu Luo Fuchun Sun Mingxuan Jing Fengxiang He Wenbing Huang Department of Computer Science and Technology Tsinghua University Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences JD Explore Academy *** Inc Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

ISBN: (纸本)9781713871088

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These discoveries encourage us to formulate a constrained lower-bound optimization problem to permit the monotonicity of MBRL. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns. Motivated by these analyses, we design a simple but effective algorithm CMLO (Constrained Model-shift Lower-bound Optimization), by introducing an event-triggered mechanism that flexibly determines when to update the model. Experiments show that CMLO surpasses other state-of-the-art methods and produces a boost when various policy optimization methods are employed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Contrastive Learning for Gastroenteroscopy Classification

Multi-scale Contrastive Learning for Gastroenteroscopy Class...

引用

Annual IEEE Symposium on Computer-Based Medical systems

作者： Dan Li Xuechen Li Zhibin Peng Wenting Chen Linlin Shen Guangyao Wu Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology ShenZhen University Shenzhen China City University of Hong Kong Hong Kong SAR China Shenzhen Institute of Artificial Intelligence & Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University General Hospital

In gastroenteroscopy image analysis, numerous CADs demonstrate that deep learning aids doctors' diagnosis. The shapes and sizes of the lesions are varied. And in the clinic, the dataset appears to be data imbalanced. However, existing methods directly classify by texture and ignore lesions with various shapes and sizes. To address the issue above, we propose a deep neural network, which consists of multi-scale feature extraction, contrastive feature learning and a multi-scale feature fusion module. We train the contrastive feature learning module and multi-scale feature fusion module simultaneously to alleviate the issue of data distribution differences. Thus, the proposed network can better identify various categories. Extensive experiments on the Hyper Kvasir dataset show that the proposed Hybrid-M2CL outperforms the benchmark proposed by the dataset with 5.0% Macro Precision, 3.3% Macro Recall, 3.4% Macro F1-score, 3.3% Micro Precision, 3.6% MCC. In addition, it outperforms the SOTA by 1.1% Macro F1-score, 2.6% MCC, and 2.0% B-ACC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Li, Qiufu Yu, Zitong Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China School of Computing and Information Technology Great Bay University Guangdong Dongguan523000 China

Face forgery detection (FFD) is devoted to detecting the authenticity of face images. Although current CNN-based works achieve outstanding performance in FFD, they are susceptible to capturing local forgery patterns generated by various manipulation methods. Though transformer-based detectors exhibit improvements in modeling global dependencies, they are not good at exploring local forgery artifacts. Hybrid transformer-based networks are designed to capture local and global manipulated traces, but they tend to suffer from the attention collapse issue as the transformer block goes deeper. Besides, soft labels are rarely available. In this paper, we propose a distilled transformer network (DTN) to capture both rich local and global forgery traces and learn general and common representations for different forgery faces. Specifically, we design a mixture of expert (MoE) module to mine various robust forgery embeddings. Moreover, a locally-enhanced vision transformer (LEVT) module is proposed to learn locally-enhanced global representations. We design a lightweight multi-attention scaling (MAS) module to avoid attention collapse, which can be plugged and played in any transformer-based models with only a slight increase in computational costs. In addition, we propose a deepfake self-distillation (DSD) scheme to provide the model with abundant soft label information. Extensive experiments show that the proposed method surpasses the state of the arts on five deepfake datasets. Copyright © 2024, 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

Investigation of traffic radar coverage efficiency under different placement strategies

Investigation of traffic radar coverage efficiency under dif...

引用

International Conference on Internet of Things 2024 (ICIoT 2024)

作者： Shun Yao Jin Zhou David Chieng Chiew Foong Kwong Boon Giin Lee Jianqiang Li Yusen Chen Next-Generation Internet of Everything Laboratory Department of Electrical and Electronic Engineering University of Nottingham Ningbo People's Republic of China School of Computer Science University of Nottingham Ningbo People's Republic of China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen People's Republic of China Zhejiang Communication Investment Group Co. Ltd. Zhejiang People's Republic of China

ISBN: (数字)9781837242177

This paper presents a comprehensive investigation of traffic radar coverage efficiency under different placement strategies in collaboration with Zhejiang Communications Investment Group Company Limited (CICO). The overall goal is to maximise coverage while minimising blind spots and the number of radars, given the constraints of the road. The NSGA-II multi-objective optimisation algorithm is found to be capable of generating a set of optimal solutions for the proposed radar placement configurations. When aiming for 100% coverage, the results indicate that a multi-antenna radar configuration requires the lowest radar density. Overall, this study provides valuable insights to transportation infrastructure owners in determining the best radar placement strategies for road traffic monitoring.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Virtual Network Mapping Method Based on Compound Particle Swarm Optimization

A Virtual Network Mapping Method Based on Compound Particle ...

引用

Cyber Security and Information Engineering (ICCSIE), International Conference on

作者： Jianhua Huang Yunlong Tang Yongjun Wei Huan Wang Haifeng Zhang Bing Zhang Liuzhou Key Laboratory of Big Data Intelligent Processing and Security Guangxi Education System Network Security Monitoring Center School of Computer Science and Technology (School of Software) Guangxi University of Science and Technology Liuzhou China Liuzhou Railway Vocational Technical College Liuzhou China

ISBN: (纸本)9781665455756

Aiming at problems of low credibility of results and low accuracy of the scheme in the mapping process of virtual networks. It is suggested to use a composite particle swarm optimization approach for virtual network mapping. Firstly, to derive the maximum number of virtual cyberspaces, we construct the virtual network model and the physical network model; secondly, resource limitations are used to build the node mapping and link mapping models, and once more, the mapping scheme of the virtual network on the physical network is solved using the composite particle swarm algorithm to improve the acceptance rate of virtual network requests. In simulation experiments, we compare our established algorithm with two algorithms, D-ViNE-SP and VNE-R-PSO, in two dimensions, and the results show that our proposed VNE-MM-PSO mapping method improves the acceptance rate of network requests by 8% and also improves on the benefit-cost ratio.

关键词： Cyberspace Compounds Particle swarm optimization Computer crime

来源：评论

学校读者我要写书评

暂无评论

A Novel Machine Learning Approach for Fast and Efficient Detection of Mango Leaf Diseases

A Novel Machine Learning Approach for Fast and Efficient Det...

引用

Computing and Machine Intelligence (ICMI), International Conference on

作者： S M Masfequier Rahman Swapno Sm Nuruzzaman Nobel Md Babul Islam R. Haque V. P. Meena F. Benedetto Dept. of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka Bangladesh Department of Computer Modeling Electronic and System Engineering UNICAL Rende Italy Applied Bahari Big Data Research House Dhaka Bangladesh Department of EEE Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Economics Dept SP4TE Laboratory University of ROMA TRE Italy

ISBN: (数字)9798350372977

ISBN: (纸本)9798350372984

Monitoring plantation diseases is a fundamental issue for the agricultural industry. Early diagnosis of plant illnesses dramatically affects food quantity and quality. Here we focus on the case of Mangoes, whose demand is very high. To maximize earnings, mango plant diseases must be managed well. Manual mango leaf disease diagnosis is impractical in today's computerized world due to its high cost, shortage of mango experts, and variable symptoms. In this work, we provide a novel machine Learning-based mango leaf disease classification method. We build a reliable categorization system using 4000 photographs from the Kaggle dataset grouped into 8 sickness categories. Our model reaches a remarkable accuracy of 96.87% throughout the training phase, and an accuracy rate of 93.12% during the validation phase. Finally, using previously unknown data, our model demonstrates an exceptional testing accuracy rate of 94.99 %. Our solution outperforms other existing machine learning detection methods, thus proving to be very effective in enhancing the categorization of Mango Leaf disease. and, more generally, offering improved and enduring food security and safety in the future.

关键词： Training Plant diseases Accuracy Plantations Machine learning Safety Reliability

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

arXiv

引用

arXiv 2023年

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

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. © 2023, CC BY.

关键词： Face recognition

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：