2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)最新文献

筛选
英文 中文
Incorporating the Graph Representation of Video and Text into Video Captioning 视频和文本的图形表示与视频字幕的结合
2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00065
Min Lu, Yuan Li
{"title":"Incorporating the Graph Representation of Video and Text into Video Captioning","authors":"Min Lu, Yuan Li","doi":"10.1109/ICTAI56018.2022.00065","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00065","url":null,"abstract":"Video captioning is to translate the video content into the textual descriptions. In the encoding phase, the existing approaches encode the irrelevant background and uncorrelated visual objects into visual features. That leads to semantic aberration between the visual features and the expected textual caption. In the decoding phase, the word-by-word prediction infers the next word only from the previously generated caption. That local text context is insufficient for word prediction. To tackle the above two issues, the representations of video and text stem from the convolution on two graphs. The convolution on the video graph distills the visual features by filtering the irrelevant background and uncorrelated salient objects. The key issue is to figure out the similar videos according to the video semantic feature. The word graph is constructed to help incorporate global neighborhood among words into word representation. That word global neigh-borhood serves as the global text context and compensates the local text context. Results on two benchmark datasets show the advantage of the proposed method. Experimental analysis is also conducted to verify the effectiveness of the proposed modules.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125012203","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
Information-Interaction Feature Pyramid Networks for Object Detection 用于目标检测的信息交互特征金字塔网络
2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00197
Jie Hu, Lihao Xie, Xiaoai Gu, Wencai Xu, Minjie Chang, Boyuan Xu
{"title":"Information-Interaction Feature Pyramid Networks for Object Detection","authors":"Jie Hu, Lihao Xie, Xiaoai Gu, Wencai Xu, Minjie Chang, Boyuan Xu","doi":"10.1109/ICTAI56018.2022.00197","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00197","url":null,"abstract":"Information interaction between multi-scale features is crucial for recognition systems detecting objects at different scales. In this paper, an Information-Interaction Feature Pyramid Network (IFPN) is proposed to enhance the power of the entire feature representations in a simple but efficient way. Specifically, to strengthen the longitudinal information interaction between multi-scale features, we establish a Bidirectional Information Pyramid Network, which significantly enhances all level features with reasonable localization and classification capabilities. Furthermore, Residual Information Branches are constructed to optimize the lateral information flow between the input and output neurons of the same middle pyramid levels. Taking Feature Pyramid Network (FPN) as the benchmark, by replacing Path Aggregation Network (PANet) with IFPN, our method achieves 3.5x and 1.6x Average Precision (AP) improvement in Faster R-CNN and YOLOX-Nano, respectively. With higher accuracy, IFPN uses 15% fewer GFLOPs than the Balanced Feature Pyramid (BFP) in YOLOX-Nano, achieving better speed and accuracy trade-offs. Furthermore, when IFPN replaces FPN, our method improves Mask R-CNN by 1.1% AP and RetinaNet by 1.0% AP, respectively, when using ResNet-50 as the backbone.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124741810","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 new multiscale texture surface defect detection method based on convolutional neural network 一种基于卷积神经网络的多尺度纹理表面缺陷检测方法
2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00196
Kaixiang Li, Min Dong, Dezhen Li
{"title":"A new multiscale texture surface defect detection method based on convolutional neural network","authors":"Kaixiang Li, Min Dong, Dezhen Li","doi":"10.1109/ICTAI56018.2022.00196","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00196","url":null,"abstract":"Traditional computer defect detection methods usually focus on the handcrafted features, but these methods have many limitations. In this paper, an approach of texture surface defect detection based on convolution neural network (CNN) and wavelet analysis is proposed. The approach combines wavelet analysis with patches extraction, which can detect and locate many kinds of defects in complex texture background, especially tiny defects in large-scale images. It is evaluated on DAGM 2007 dataset and Micro surface defect database, the results demonstrate that it has a high accuracy in defect detection with only a small amount of training data.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"204 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116515696","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
RGB-D Saliency Detection with 3D Cross-modal Fusion and Mid-level Integration RGB-D显著性检测与三维跨模态融合和中层融合
2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00201
Tao Liu, Bo Li
{"title":"RGB-D Saliency Detection with 3D Cross-modal Fusion and Mid-level Integration","authors":"Tao Liu, Bo Li","doi":"10.1109/ICTAI56018.2022.00201","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00201","url":null,"abstract":"In recent years, many salient object detection (SOD) methods introduce depth cues to boost detection performance in challenging scenes, named as RGB-D SOD. However, how to effectively fuse cross-modal features with various properties (i.e., RGB and depth) has become a key issue that is hard to be avoided. Most existing methods employ simple operations, such as concatenation or summation, for cross-modal fusion, ignoring the negative effects of low-quality depth maps, thus yielding poor performance. In this paper, we design a simple yet effective fusion method, which utilizes 3D convolution to extract modality-specific and modality-shared information respectively for sufficient cross-modal fusion, and combines modality weights to mitigate the interference of invalid information. In addition, we propose a novel multi-level feature integration strategy in the decoder, which explicitly incorporates the low-level detail information and high-level semantic information into the mid-level to generate accurate saliency maps. Extensive experiments on six public datasets show that our method achieves competitive results compared to 17 state-of-the-art methods.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121106283","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
Morphological Classification of Neurons Based Deep Residual Multiscale Convolutional Neural Network 基于深度残差多尺度卷积神经网络的神经元形态分类
2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00077
Fuyun He, Yan Wei, Youwei Qian
{"title":"Morphological Classification of Neurons Based Deep Residual Multiscale Convolutional Neural Network","authors":"Fuyun He, Yan Wei, Youwei Qian","doi":"10.1109/ICTAI56018.2022.00077","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00077","url":null,"abstract":"The study of neuron morphological classification has important application value to improve the accuracy and efficiency of three-dimensional reconstruction of neurons. However, due to the complex structure of neurons and the existence of global and local self-similarity in morphological distribution, it brings great difficulties to the classification of neuron morphology. Therefore, a new neuronal morphological classification model based on deep residual multiscale convolutional neural network is proposed. Firstly, the overall architecture of the model is based on the fast connection idea of ResNet, which can effectively prevent network model degradation. Secondly, by using the residual connection module, the input information is directly transferred to the output layer through a shortcut, so as to simplify the goal and difficulty of feature learning. Finally, the multi-scale convolution module is combined for feature extraction, and the dilated convolution with different dilation rates is adopted to increase the receiving field to expand the diversity of features, so as to improve the classification accuracy. To verify the effectiveness of the model, experiments are carried out on the neuron morphology classification dataset. The experimental results show that the accuracy, precision, sensitivity and specificity of our method reach 90.11%, 89.63%, 90.77% and 93.27%, respectively. Compared with other classification models (VGG, ResNet, RNN), the proposed model has better classification effect.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133845297","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
Approximating Element-Wise Functions of Matrix with Improved Streaming Randomized SVD 用改进的流随机SVD逼近矩阵的元函数
2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00026
Yuyang Xie, Xu Feng, Xizhi Zhang, J. Qiu, Wenjian Yu
{"title":"Approximating Element-Wise Functions of Matrix with Improved Streaming Randomized SVD","authors":"Yuyang Xie, Xu Feng, Xizhi Zhang, J. Qiu, Wenjian Yu","doi":"10.1109/ICTAI56018.2022.00026","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00026","url":null,"abstract":"The element-wise functions of a matrix are widely used in machine learning. For the applications with large matrices, efficiently computing the matrix-vector multiplication of matrix element-wise function without explicitly constructed matrix is very desired. In this work, we aim to develop an efficient low-rank approximation of the element-wise function of matrix with the time/memory cost linear to the matrix dimension. We first propose a sparse-sign streaming randomized SVD (ssrSVD) algorithm based on a streaming singular value decomposition (SVD) algorithm and the sparse-sign random projection for the approximation of element-wise function of general asymmetric matrix. For symmetric positive semi-definite (SPSD) matrix, for which the existing Nyström [1] and FastSPSD [2] method do not perform well if the matrix's singular value decays slowly, we propose a theoretically proved shift skill to improve the approximation accuracy. Combining with the ssrSVD, we obtain the sparse-sign streaming SPSD matrix approximation with shift (S3SPSD) algorithm. Experiments are carried out to evaluate the proposed algorithms' performance in approximating element-wise functions of matrix. With the color transfer task based on the Sinkhorn algorithm, the ssrSVD algorithm largely reduces the approximation error (up to $10^{5}times$) compared with the state-of-the-art baselines, and results in high-quality color transfer result. For the kernel matrix approximation, the proposed S3SPSD algorithm also consistently outperforms the state-of-the-art baselines. Experimental results finally validate the linear time complexity of the proposed algorithms.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133847675","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
Measuring Machine Learning Robustness in front of Static and Dynamic Adversaries* 在静态和动态对手面前测量机器学习的鲁棒性*
2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00033
Héctor D. Menéndez
{"title":"Measuring Machine Learning Robustness in front of Static and Dynamic Adversaries*","authors":"Héctor D. Menéndez","doi":"10.1109/ICTAI56018.2022.00033","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00033","url":null,"abstract":"Adversarial machine learning brought a new way of understanding the reliability of different learning systems. Knowing that the learning confidence depends significantly on small changes, such as noise, created a mind change in the artificial intelligence community, who started to consider the boundaries and limitations of machine learning methods. However, if we can measure these limitations, we can improve the strength of our machine learning models and their robustness. Following this motivation, this work introduces different measures of robustness for machine learning models based on false negatives. These measures can be evaluated for either static or dynamic scenarios, where an adversary performs intelligent actions to evade the system. To evaluate the metrics I have applied 11 classifiers to different benchmark datasets and created an adversary that performs an evolutionary search process aiming to reduce the classification accuracy. The results show that the most robust models are related to K-Nearest Neighbours, Logistic regression, and neural networks, although none of the systems is robust enough when the target is to reach a single misclassification.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133231348","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: 2
Towards Query-limited Adversarial Attacks on Graph Neural Networks 基于查询限制的图神经网络对抗性攻击研究
2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00082
Haoran Li, Jinhong Zhang, Song Gao, Liwen Wu, Wei Zhou, Ruxin Wang
{"title":"Towards Query-limited Adversarial Attacks on Graph Neural Networks","authors":"Haoran Li, Jinhong Zhang, Song Gao, Liwen Wu, Wei Zhou, Ruxin Wang","doi":"10.1109/ICTAI56018.2022.00082","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00082","url":null,"abstract":"Graph Neural Network (GNN) is a graph representation learning approach for graph-structured data, which has witnessed a remarkable progress in the past few years. As a counterpart, the robustness of such a model has also received considerable attention. Previous studies show that the performance of a well-trained GNN can be faded by black-box adversarial examples significantly. In practice, the attacker can only query the target model with very limited counts, yet the existing methods require hundreds of thousand queries to extend attacks, leading the attacker to be exposed easily. To perform a step forward in addressing this issue, in this paper, we propose a novel attack methods, namely Graph Query-limited Attack (GQA), in which we generate adversarial examples on the surrogate model to fool the target model. Specifically, in GQA, we use contrastive learning to fit the feature extraction layers of the surrogate model in a query-free manner, which can reduce the need of queries. Furthermore, in order to utilize query results sufficiently, we obtain a series of queries with rich information by changing the input iteratively, and storing them in a buffer for recycling usage. Experiments show that GQA can decrease the accuracy of the target model by 4.8%, with only 1% edges modified and 100 queries performed.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"307 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131016805","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: 1
How Features Benefit: Parallel Series Embedding for Multivariate Time Series Forecasting with Transformer 特征对多变量时间序列预测有何好处
2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00148
Xuande Feng, Zonglin Lyu
{"title":"How Features Benefit: Parallel Series Embedding for Multivariate Time Series Forecasting with Transformer","authors":"Xuande Feng, Zonglin Lyu","doi":"10.1109/ICTAI56018.2022.00148","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00148","url":null,"abstract":"Forecasting time series is an engaging and vital mathematical topic. Theories and applications in related fields have been studied for decades, and deep learning has provided reliable tools in recent years. Transformer, capable to capture longer sequence dependencies, was exploited as a powerful architecture in time series forecasting. While existing work majorly contributed to breaking memory bottleneck of Trasnformer, how to effectively leverage multivariate time series remains barely focused. In this work, a novel architecture utilizing a primary Transformer is proposed to conduct multivariate time series predictions. Our proposed architecture has two main advantages. Firstly, it accurately predicts multivariate time series with shorter or longer sequence lengths and steps. We benchmark our proposed model with various baseline architectures on real-world datasets, and our model improved their performances significantly. Secondly, it can easily be leveraged in Transformer-based variants, which guarantees broad applications of our proposed work.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132114175","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
CATREEN: Context-Aware Code Timing Estimation with Stacked Recurrent Networks 上下文感知的代码时序估计与堆叠循环网络
2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00090
Abderaouf N. Amalou, É. Fromont, I. Puaut
{"title":"CATREEN: Context-Aware Code Timing Estimation with Stacked Recurrent Networks","authors":"Abderaouf N. Amalou, É. Fromont, I. Puaut","doi":"10.1109/ICTAI56018.2022.00090","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00090","url":null,"abstract":"Automatic prediction of the execution time of programs for a given architecture is crucial, both for performance analysis in general and for compiler designers in particular. In this paper, we present CATREEN, a recurrent neural network able to predict the steady-state execution time of each basic block in a program. Contrarily to other models, CATREEN can take into account the execution context formed by the previously executed basic blocks which allows accounting for the processor micro-architecture without explicit modeling of micro-architectural elements (caches, pipelines, branch predictors, etc.). The evaluations conducted with synthetic programs and real ones (programs from Mibench and Polybench) show that CATREEN can provide accurate prediction for execution time with 11.4% and 16.5% error on average, respectively and that we got an improvement of 18% and 27.6% respectively when comparing our tool estimations to the state-of-the-art LSTM-based model.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"53 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133401111","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: 2
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信