检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Li, Jiang Wang, Xiaoping Lv, Guoqing Zeng, Zhigang The School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

Emotion Recognition in Conversation (ERC) plays a significant part in Human-Computer Interaction (HCI) systems since it can provide empathetic services. Multimodal ERC can mitigate the drawbacks of uni-modal approaches. Recently, Graph Neural Networks (GNNs) have been widely used in a variety of fields due to their superior performance in relation modeling. In multimodal ERC, GNNs are capable of extracting both long-distance contextual information and inter-modal interactive information. Unfortunately, since existing methods such as MMGCN directly fuse multiple modalities, redundant information may be generated and diverse information may be lost. In this work, we present a directed Graph based Cross-modal Feature Complementation (GraphCFC) module that can efficiently model contextual and interactive information. GraphCFC alleviates the problem of heterogeneity gap in multimodal fusion by utilizing multiple subspace extractors and Pair-wise Cross-modal Complementary (PairCC) strategy. We extract various types of edges from the constructed graph for encoding, thus enabling GNNs to extract crucial contextual and interactive information more accurately when performing message passing. Furthermore, we design a GNN structure called GAT-MLP, which can provide a new unified network framework for multimodal learning. The experimental results on two benchmark datasets show that our GraphCFC outperforms the state-of-the-art (SOTA) approaches. Copyright © 2022, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning

Disentangling Spatial and Temporal Learning for Efficient Im...

引用

International Conference on Computer Vision (ICCV)

作者： Zhiwu Qing Shiwei Zhang Ziyuan Huang Yingya Zhang Changxin Gao Deli Zhao Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Alibaba Group ARC National University of Singapore

Recently, large-scale pre-trained language-image models like CLIP have shown extraordinary capabilities for understanding spatial contents, but naively transferring such models to video recognition still suffers from unsatisfactory temporal modeling capabilities. Existing methods insert tunable structures into or in parallel with the pre-trained model, which either requires back-propagation through the whole pre-trained model and is thus resource-demanding, or is limited by the temporal reasoning capability of the pre-trained structure. In this work, we present DiST, which disentangles the learning of spatial and temporal aspects of videos. Specifically, DiST uses a dual-encoder structure, where a pre-trained foundation model acts as the spatial encoder, and a lightweight network is introduced as the temporal encoder. An integration branch is inserted between the encoders to fuse spatio-temporal information. The disentangled spatial and temporal learning in DiST is highly efficient because it avoids the back-propagation of massive pre-trained parameters. Meanwhile, we empirically show that disentangled learning with an extra network for integration benefits both spatial and temporal understanding. Extensive experiments on five benchmarks show that DiST delivers better performance than existing state-of-the-art methods by convincing gaps. When pre-training on the large-scale Kinetics-710, we achieve 89.7% on Kinetics-400 with a frozen ViT-L model, which verifies the scalability of DiST. Codes and models can be found in https://***/alibaba-mmai-research/DiST.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implicit Tracking-Based Distributed Constraint-Coupled Optimization

arXiv

引用

arXiv 2022年

作者： Li, Jingwang Su, Housheng The School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

A class of distributed optimization problem with a globally coupled equality constraint and local constrained sets is studied in this paper. For its special case where local constrained sets are absent, an augmented primal-dual gradient dynamics is proposed and analyzed, but it cannot be implemented distributedly since the violation of the coupled constraint needs to be used. Benefiting from the brand-new comprehending of a classical distributed unconstrained optimization algorithm, the novel implicit tracking approach is proposed to track the violation distributedly, which leads to the birth of the implicit tracking-based distributed augmented primal-dual gradient dynamics (IDEA). A projected variant of IDEA, i.e., Proj-IDEA, is further designed to deal with the general case where local constrained sets exist. With the aid of the Lyapunov stability theory, the convergences of IDEA and Proj-IDEA over undigraphs and digraphs are analyzed respectively. As far as we know, Proj-IDEA is the first constant step-size distributed algorithm which can solve the studied problem without the need of the strict convexity of local cost functions. Besides, if local cost functions are strongly convex and smooth, IDEA can achieve exponential convergence with a weaker condition about the coupled constraint. Finally, numerical experiments are taken to corroborate our theoretical results. © 2022, CC BY.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

An SVM-based small target segmentation and clustering approach

An SVM-based small target segmentation and clustering approa...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Sheng Zheng Jian Liu Jin-Wen Tian State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)0780384032

Segmentation and clustering of infrared small target images in a sky or sea-sky background is considered in this paper, which is the preprocessing part of the detection and recognition of the moving small targets in an infrared image sequence. The infrared image intensity surface is well fitted by the least squares support vector machines (LS-SVM), and then the maximum extremum points are detected on the well fitted intensity surface by convolving the image with the second order directional derivative operators deduced from the mapped LS-SVM with mixtures of kernels. With the coarse locations, the possible targets are extracted by the clustering analysis. The computer experiments are carried out for the real and simulated sky and sea-sky infrared images. The experimental results demonstrate the proposed approach is effective.

关键词： Infrared detectors Infrared imaging Image segmentation Sea surface Image recognition Target recognition Image sequences Least squares methods Support vector machines Kernel

来源：评论

学校读者我要写书评

暂无评论

A New Multi-Scale Model for Medium-Term Load Forecasting

A New Multi-Scale Model for Medium-Term Load Forecasting

引用

第35届中国控制与决策会议

作者： Peng Liu Hongliang Fang Jiang-Wen Xiao Yan-Wu Wang Xiao-Kang Liu School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control (Huazhong University of Science and Technology) Ministry of Education

When a large number of distributed power and renewable energy are connected to the smart grid,the volatility and intermittency of renewable energy bring some challenges to the smart ***,accurate medium-term load forecasting is essential because it is conducive to the stability of the power grid and can provide data support for the power generating *** factors affect medium-term load forecasting and the real-time electricity price is a very important factor among *** this paper,a multi-scale model based on LSTM model is proposed to extracts features from 3 different time scales including half-hourly time scale,daily time scale and monthly time *** first,the half-hourly data is processed by a half-hourly data processing layer to extract the half-hourly ***,its output is concatenated with the daily load data and is input into a daily data processing ***,the daily features are concatenated with the monthly load data and they are input into a monthly data processing layer to extract the monthly features and get the final forecasting *** case study results demonstrate that the proposed multi-scale model has better performance than the single-scale models.

关键词： Deep learning medium-term load forecasting LSTM real-time electricity price

来源：评论

学校读者我要写书评

暂无评论

NPGA: A Unified Algorithmic Framework for Decentralized Constraint-Coupled Optimization

arXiv

引用

arXiv 2022年

作者： Li, Jingwang Su, Housheng School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

This work focuses on a class of general decentralized constraint-coupled optimization problems. We propose a novel nested primal-dual gradient algorithm (NPGA), which can achieve linear convergence under the weakest known condition, and its theoretical convergence rate surpasses all known results. More importantly, NPGA serves not only as an algorithm but also as a unified algorithmic framework, encompassing various existing algorithms as special cases. By designing different network matrices, we can derive numerous versions of NPGA and analyze their convergences by leveraging the convergence results of NPGA conveniently, thereby enabling the design of more efficient algorithms. Finally, we conduct numerical experiments to compare the convergence rates of NPGA and existing algorithms, providing empirical evidence for the superior performance of NPGA. Copyright © 2022, The Authors. All rights reserved.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Cooperative path planning for multiple air vehicles using a co-evolutionary algorithm

Cooperative path planning for multiple air vehicles using a ...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Chang-Wen Zheng Ming-Yue Ding Cheng-Ping Zhou State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattem Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

The coordinated path-planning problem for multiple unmanned air vehicles is studied with the proposal of a co-evolving and cooperating path planner. In the new planner, potential paths of each vehicle form their own subpopulation, and evolve only in their own sub-population, while the interaction among all sub-problems is reflected by the definition of fitness function. Meanwhile, the individual candidates are evaluated with respect to the workspace so that the computation of the configuration space is avoided. By using a problem-specific representation of candidate solutions and genetic operators, our algorithm can take into account different kinds of mission constraints and generate the solutions in real-time.

关键词： Path planning Unmanned aerial vehicles Level measurement Terrain mapping Genetics Evolutionary computation Laboratories Image processing Intelligent control Image recognition

来源：评论

学校读者我要写书评

暂无评论

Multimodal Representations Learning Based on Mutual Information Maximization and Minimization and Identity Embedding for Multimodal Sentiment Analysis

arXiv

引用

arXiv 2022年

作者： Zheng, Jiahao Zhang, Sen Wang, Xiaoping Zeng, Zhigang School of Artificial Intelligence and Automation The Key Laboratory of Image Processing Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

Multimodal sentiment analysis (MSA) is a fundamental complex research problem due to the heterogeneity gap between different modalities and the ambiguity of human emotional expression. Although there have been many successful attempts to construct multimodal representations for MSA, there are still two challenges to be addressed: 1) A more robust multimodal representation needs to be constructed to bridge the heterogeneity gap and cope with the complex multimodal interactions, and 2) the contextual dynamics must be modeled effectively throughout the information flow. In this work, we propose a multimodal representation model based on Mutual information Maximization and Minimization and Identity Embedding (MMMIE). We combine mutual information maximization between modal pairs, and mutual information minimization between input data and corresponding features to mine the modal-invariant and task-related information. Furthermore, Identity Embedding is proposed to prompt the downstream network to perceive the contextual information. Experimental results on two public datasets demonstrate the effectiveness of the proposed model. Copyright © 2022, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Deployment of Heterogeneous Multi-Agent Systems via a PDE Approach

Deployment of Heterogeneous Multi-Agent Systems via a PDE Ap...

引用

Chinese Automation Congress (CAC)

作者： Jingtao Man Zhigang Zeng Qiang Xiao Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China School of Artificial Intelligence and Automation (of Huazhong University of Science and Technology) Wuhan China

Spatial deployment of large-scale heterogeneous multi-agent systems (HMASs) over desired 2D or 3D curves is investigated in this paper. With assumption that HMASs consist of numerous first-order agents (FOAs) and second-order agents (SOAs) that could obtain local information of desired curves and their positions relative to their closest neighbors, the collective dynamics of large-scale HMASs are modeled as heterogeneous partial differential equations (PDEs). In particular, this paper introduces series-dependent topological weights between neighboring agents, which are more versatile and practical than constant topological weights commonly used in previous studies. A novel single-point control scheme is proposed, where an informed agent is situated between the last FOA and first SOA. This operation could not only ensure successful implementation of spatial deployment, but also guarantee well-posedness of the constructed heterogeneous error PDEs. By utilizing inequality techniques, sufficient conditions for exponential convergence of error system are derived. A numerical example is presented to demonstrate effectiveness of the proposed approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Person Search with Region Siamese Networks

Weakly Supervised Person Search with Region Siamese Networks

引用

International Conference on Computer Vision (ICCV)

作者： Chuchu Han Kai Su Dongdong Yu Zehuan Yuan Changxin Gao Nong Sang Yi Yang Changhu Wang Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology ByteDance University of Technology Sydney

ISBN: (纸本)9781665428132

Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. Large-scale labeled training data is often difficult to collect, especially for person identities. A natural question is whether a good person search model can be trained without the need of identity supervision. In this paper, we present a weakly supervised setting where only bounding box annotations are available. Based on this new setting, we provide an effective baseline model termed Region Siamese Networks (R-SiamNets). Towards learning useful representations for recognition in the absence of identity labels, we supervise the R-SiamNet with instance-level consistency loss and cluster-level contrastive loss. For instance-level consistency learning, the R-SiamNet is constrained to extract consistent features from each person region with or without out-of-region context. For cluster-level contrastive learning, we enforce the aggregation of closest instances and the separation of dissimilar ones in feature space. Extensive experiments validate the utility of our weakly supervised method. Our model achieves the rank-1 of 87.1% and mAP of 86.0% on CUHK-SYSU benchmark, which surpasses several fully supervised methods, such as OIM [36] and MGTS [4], by a clear margin. More promising performance can be reached by incorporating extra training data. We hope this work could encourage the future research in this field.

关键词： Training Computer vision Annotations Supervised learning Training data Benchmark testing Feature extraction

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：