2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)最新文献_第6页

Identity-Assisted Network for Pedestrian Attribute Recognition 行人属性识别的身份辅助网络

2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967721

Ye Li, L. Wu, Ziyang Chen, Guangqiang Yin, Xinzhong Wang, Zhiguo Wang

{"title":"Identity-Assisted Network for Pedestrian Attribute Recognition","authors":"Ye Li, L. Wu, Ziyang Chen, Guangqiang Yin, Xinzhong Wang, Zhiguo Wang","doi":"10.1109/DOCS55193.2022.9967721","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967721","url":null,"abstract":"Pedestrian attribute recognition aims to accurately locate and extract high-level semantic attributes of pedestrians, and provide important support for pedestrian re-identification. The existing pedestrian attribute recognition method has achieved good recognition results in indoor and other single scences. However, it does not perform well in complex background with changes of illumination, viewing position and occlusion. In this work, we introduce pedestrian identity (ID) as auxiliary information for attribute recognition, and propose an identity-assisted pedestrian attribute recognition network (IA). The IA network uses ResNet-50 as the backbone network, removes the last fully connected layer, and then connects to a multi-branch network, which contains re-identification branch and attribute branch. The re-identification branch is used to extract pedestrian features, then use hierarchical clustering to generate pseudo IDs, which finally assists pedestrian attribute identification. Besides, we construct a quintuple loss function. Firstly, it constructs a intra-triple loss within an attribute. And then, it constructs an inter-triple loss between attributes according to the pseudo ID information to fully optimize the attribute space. The average accuracy mA of the IA model for all attributes on the PETA dataset exceeds 85%. Through comparative experiments, it can be proved that the IA model gets a bettrer performance on attribute recognition.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133625398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Traffic Modeling and Rescheduling for High-speed Train Based on Block Sections 基于分段的高速列车交通建模与调度研究

2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967705

Peng Yue, Yaochu Jin, X. Dai, D. Cui, Qi Shi

引用次数: 0

Graph Multi-Attention Network-based Taxi Demand Prediction 基于多关注网络的出租车需求预测

2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967748

Haifan Tang, Youkai Wu, Zhaoxia Guo

引用次数: 0

Adaptive Heading Tracking Control of Intelligent Ship with Stochastic Noise and Dead Zone Output 具有随机噪声和死区输出的智能船舶自适应航向跟踪控制

2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967707

Yanli Liu, Runzhi Wang, Liying Hao

引用次数: 0

An Optimized Transfer Attack Framework Towards Multi-Modal Machine Learning 面向多模态机器学习的优化传输攻击框架

2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967734

Yinjie Zhang, Geyang Xiao, B. Bai, Zhiyu Wang, Caijun Sun, Yonggang Tu

{"title":"An Optimized Transfer Attack Framework Towards Multi-Modal Machine Learning","authors":"Yinjie Zhang, Geyang Xiao, B. Bai, Zhiyu Wang, Caijun Sun, Yonggang Tu","doi":"10.1109/DOCS55193.2022.9967734","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967734","url":null,"abstract":"Deep neural networks (DNNs) have excelled at a wide range of tasks, including computer vision (CV), natural language processing (NLP), and speech recognition. However, past research has demonstrated that DNNs are vulnerable to adversarial examples, which are deliberately meant to trick models into making incorrect predictions by adding subtle perturbations into inputs. Adversarial examples create an exponential threat to multi-modal models that can accept a variety of inputs. By attacking substitute models, we provide a transferable attack framework. The suggested framework optimizes the attack process by modifying the prompt templates and simultaneously raising the attack on multiple inputs. Our experiments demonstrate that the proposed attack framework can significantly improve the success rate of transferable attacks, and adversarial examples are rarely noticed by humans. Meanwhile, experiments show that in transferable attacks, coarse-grained adversarial examples can achieve higher attack success rates than fine-grained ones, and the multi-modal models has some robustness against uni-modal attacks.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128653824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Reference Point and Multi-direction Search Based Evolution Algorithm for Large-scale Multi-objective Optimization 基于参考点和多方向搜索的大规模多目标优化进化算法

2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967781

Shuai Tian, Ziqing Wang, Xiangjuan Wu, Yuping Wang

{"title":"A Reference Point and Multi-direction Search Based Evolution Algorithm for Large-scale Multi-objective Optimization","authors":"Shuai Tian, Ziqing Wang, Xiangjuan Wu, Yuping Wang","doi":"10.1109/DOCS55193.2022.9967781","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967781","url":null,"abstract":"This paper proposes a new algorithm based on a reference point selection mechanism and a multi-direction search strategy for large-scale multi-objective optimization problems. Firstly, a center point symmetry strategy is designed to select uniformly distributed reference points and transform the original problem into several low-dimensional single-objective optimization problems. Based on the reference points, a multi-directional weight variable association strategy is proposed to add search directions for the original problem and to improve the search ability of the algorithm. Then, to solve the transformed single-objective problem effectively, an improved differential evolution algorithm based on center mutation is presented. Finally, the numerical experiments are conducted on the large-scale optimization problem benchmarks LSMOP with 200, 500, and 1000 decision variables and the comparison of the proposed algorithm with four state-of-the-art algorithms is made. The results show that the proposed algorithm significantly outperforms the compared algorithms.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131303648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on destination images with information containing sentiment classification driven by multi-source data 多源数据驱动下包含情感信息的目的地图像分类研究

2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967750

Yuyan Luo, Lihong Deng, Letian Xiao, Bingqian Wu, Junchen Pan, J. Wang

引用次数: 0

Multi-scale Enhanced Fine-grained Feature-based Person Re-identification Algorithm 基于多尺度增强细粒度特征的人物再识别算法

2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967712

Zhen Ding, Kangning Yin, Tingting Huang, Lin Xiao, Zhi-hua Dong, Guangqiang Yin

{"title":"Multi-scale Enhanced Fine-grained Feature-based Person Re-identification Algorithm","authors":"Zhen Ding, Kangning Yin, Tingting Huang, Lin Xiao, Zhi-hua Dong, Guangqiang Yin","doi":"10.1109/DOCS55193.2022.9967712","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967712","url":null,"abstract":"The key to solve the problem of Person Re-identification is to improve the extraction and application of Person effective features. Convolutional neural networks have powerful capabilities in this regard. This paper proposes a Person re-recognition algorithm based on multi-scale enhanced fine-grained features. Resnet50 is used as the backbone network to extract Person features at different scales, and the EFOM module is proposed to enable the extraction of fine-grained features by adding relevant global features while compensating for the shortcomings of its own attention mechanism to obtain enhancement and refinement. Finally, the MFFP module is used to obtain the fused features at different scales and then stitched into the BNNeck module. The fused feature vectors are supervised and trained using a variant triplet loss function with less overhead and a more flexible central loss function. Experimental results of the method on the DukeMTMC-ReID and Market-1501 datasets show that it achieves 86.7%% and 92.0% on the mAP evaluation metric; 91.1% and 94.8% on the Rank-1 evaluation metric. The experimental results show that the method makes full use of different scale feature information and key fine-grained features. It enhances the recognition degree of person features and improves the efficiency of person Re-ID.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129101228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Over-the-Horizon Air Combat Environment Modeling and Deep Reinforcement Learning Application 超视距空战环境建模与深度强化学习应用

2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967482

Ao Wang, Shangwei Zhao, Zhengkang Shi, Jingcheng Wang

引用次数: 1

A High-dimensional Anomaly Detection Algorithm Based on IForest with Autoencoder 基于自编码器的ifforest高维异常检测算法

2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967746

Jinhong Yang, Xinxin Yang, Zhenyu Zhang

{"title":"A High-dimensional Anomaly Detection Algorithm Based on IForest with Autoencoder","authors":"Jinhong Yang, Xinxin Yang, Zhenyu Zhang","doi":"10.1109/DOCS55193.2022.9967746","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967746","url":null,"abstract":"The existing anomaly detection algorithms based on isolated forest are limited by the height of isolated tree. High-dimensional problem domains pose significant challenges for anomaly detection. The presence of irrelevant features can conceal the presence of anomalies. This problem known as curse of dimensionality, is an obstacle for many anomaly detection techniques. Building a robust anomaly detection model for high- dimensional data requires the combination of an unsupervised feature extractor and an anomaly detector. A high-dimensional anomaly detection algorithm is proposed based on isolated forest with deep autoencoder (AE-IForest). Firstly, AE-IForest maps the high-dimensional and nonlinear original data to the low- dimensional space by a deep self-coding network. In the low-dimensional space, the isolated forest algorithm is used to sort the data isolation score, and the reconstruction error of the samples is fused to detect the abnormal data. Finally, the experimental results on six data sets show that the anomaly detection effect of AE-IForest algorithm is better than three classical algorithms LOF, IForest and SVDD. AE-IForest is an efficient anomaly detection model for high-dimensional data.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121114497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0