检索结果-内蒙古大学图书馆

International Conference on Intelligent Computation and Bio-Medical Instrumentation (ICBMI)

作者： Yangguang Sun Mingyue Ding College of Computer Science South-Central University for Nationalities Image Processing and Intelligence Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan China College of Life Science and Technology Image Processing and Intelligence Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan China

A novel statistical method was proposed for boundary extraction of interested objects in this letter. The proposed method was inspired by the physical nature of quantum and the statistical property of wave function. By introducing the polymer representation of quantum particle and based on quantum particle motion in the gradient-based image potential field, the boundary extraction was realized in our method. Experimental results demonstrated that our method has the capability to make the boundary extraction with arbitrary initialization and topology changes possible.

关键词： Quantum mechanics Wave functions Educational institutions Polymers Monte Carlo methods Deformable models Probability distribution

来源：评论

学校读者我要写书评

暂无评论

Reliability on Deep Learning Models: A Comprehensive Observation

Reliability on Deep Learning Models: A Comprehensive Observa...

引用

International Symposium on System and Software Reliability (ISSSR)

作者： Yuhong Zhang Chunjing Xiao School of Artificial Intelligence and Big Data Key Laboratory of Grain Information Processing and Control Ministry of Education Henan University of Technology Zhengzhou China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

ISBN: (数字)9780738104973

ISBN: (纸本)9781665423236

This paper provides a comprehensive observation to examine the reliability of deep learning (DL) models. First, we will briefly introduce the essential background and kernel techniques in deep learning, such as downsampling and nonlinear discontinuity. Each of them may have some relation to the reliability of DL models. Then we discuss the inherent structural flaws of deep learning and the risk of unreliability that can result from it. Subsequently, we discuss various ways of generating adversarial samples that affect the DL model's reliability and corresponding preventive measures. Finally, we complete this observation by identifying current challenges and future trends for research.

关键词： Reliability Deep learning Biological neural networks Perturbation methods Neural networks Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Text-based Person Re-Identification

Weakly Supervised Text-based Person Re-Identification

引用

International Conference on Computer Vision (ICCV)

作者： Shizhen Zhao Changxin Gao Yuanjie Shao Wei-Shi Zheng Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Sun Yat-sen University

ISBN: (纸本)9781665428132

The conventional text-based person re-identification methods heavily rely on identity annotations. However, this labeling process is costly and time-consuming. In this paper, we consider a more practical setting called weakly supervised text-based person re-identification, where only the text-image pairs are available without the requirement of annotating identities during the training phase. To this end, we propose a Cross-Modal Mutual Training (CMMT) framework. Specifically, to alleviate the intra-class variations, a clustering method is utilized to generate pseudo labels for both visual and textual instances. To further re-fine the clustering results, CMMT provides a Mutual Pseudo Label Refinement module, which leverages the clustering results in one modality to refine that in the other modality constrained by the text-image pairwise relationship. Mean-while, CMMT introduces a Text-IoU Guided Cross-Modal Projection Matching loss to resolve the cross-modal matching ambiguity problem. A Text-IoU Guided Hard Sample Mining method is also proposed for learning discriminative textual-visual joint embeddings. We conduct extensive experiments to demonstrate the effectiveness of the proposed CMMT, and the results show that CMMT performs favorably against existing text-based person re-identification methods. Our code will be available at https://***/X-BrainLab/WS_Text-ReID.

关键词： Training Visualization Computer vision Codes Annotations Computational modeling Clustering methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing inundation monitoring of road networks using crowdsourced flood reports

引用

Urban Informatics 2024年第1期3卷 1-21页

作者： Esparza, Miguel Farahmand, Hamed Liu, Xueming Mostafav, Ali Urban Resilience. AI Lab Zachry Department of Civil and Environmental Engineering Texas A&M University College Station USA MAPFRE Boston USA Key Laboratory of Imaging Processing and Intelligence Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan People’s Republic of China

As the risk of flooding continues to impose on transportation infrastructure systems, enhancing the ability to monitor flood inundations in road networks becomes more significant. This research explores the potential crowdsourced data, specifically 3-1-1 reports, has to complement information from physical flood sensors. Three flooding events in two watersheds in Harris County, Texas were studied. To assess 3-1-1 report's capabilities, a time series analysis between reports and water elevation of physical sensor data was performed to capture channel overflow. Next, a graph-based observability analysis identified multiple combinations of minimum additional sensor locations needed for complete network monitoring in the study area. To find the optimal combination, a principal component analysis assigns a criticality score based on exposure, road importance, neighborhood vulnerability, and frequency of 3-1-1 reports near a node. The results indicate that 3-1-1 reports effectively improve flood monitoring by reducing the need for physical sensors by 32% in areas that lack flood sensors. This approach can help city managers improve flood monitoring by leveraging socially sensed data to supplement physical sensors, especially in blind spots where no flood gauge exists.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TMMM: Transformer in Multimodal Sentiment Analysis under Missing Modalities

TMMM: Transformer in Multimodal Sentiment Analysis under Mis...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Huanyu Wu Siyang Li Dongrui Wu Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The cross-task gap presents a significant challenge for multimodal models because of the differences in input-output workflows. For instance, multimodal pre-trained transformers may encounter uni-modal data during testing. To mitigate the gap, this paper introduces a Transformer in Multimodal Sentiment Analysis under Missing Modalities (TMMM) aims to perform well using missing-modal data during testing. TMMM uses a missing multimodal training approach to prevent accuracy degradation in testing. At the same time, a new network architecture allows the model to reconstruct missing modalities during testing. Classification token fusion and Mixture-of-Experts structures further enhance the model’s performance. A pre-training method utilizing contrastive learning, which can construct negative samples with positive samples, is proposed to overcome insufficient labeled data. Our experiments demonstrated the effectiveness of TMMM on two datasets with no modalities missing, i.e., it consistently achieved the highest classification accuracy and Macro-F1, which outperformed the best state-of-the-art baseline on each dataset by about 2% and 2.5%. Additionally, TMMM usually performs better than other baselines on datasets with missing modalities during testing.

关键词： Training Sentiment analysis Accuracy Contrastive learning Network architecture Transformers Brain modeling

来源：评论

学校读者我要写书评

暂无评论

A robust approach to the detection and tracking of small targets with low contrast

A robust approach to the detection and tracking of small tar...

引用

IEEE International Workshop on VLSI Design and Video Technology, IWVDVT

作者： Xinyu Wang Guilin Zhang Ying Chu State Key Laboratory for Image Processing and lntelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)0780390059

An effective approach to the detection and tracking of small moving targets with low contrast is proposed. In our application, small moving targets are detected and tracked in a low quality video sequence captured from an airborne platform. The detection and tracking system includes three modules. First, the global motion parameters are estimated using fast least trimmed squares (FAST-ITS) regression and hierarchical processing. Once the global motion is robustly estimated, relatively stationary background can be eliminated almost completely through image warping. Then a motion-based fast target detector selects candidate pixels of the moving targets with motions statistically different from that of the background, and a particle filtering tracker examines the temporal consistency of targets to identify them and update their states. Information in the system flows in a closed loop form, in which the tracker instructs the detector where to look for a target, and the detector returns what it has found. Experimental results prove that the proposed method can reliably and effectively detect and track the real small moving target in real-time even if there is strong clutter influence.

关键词： Robustness Target tracking Detectors Motion estimation Video sequences Parameter estimation Motion detection Filtering Particle tracking Tracking loops

来源：评论

学校读者我要写书评

暂无评论

OadTR: Online Action Detection with Transformers

OadTR: Online Action Detection with Transformers

引用

International Conference on Computer Vision (ICCV)

作者： Xiang Wang Shiwei Zhang Zhiwu Qing Yuanjie Shao Zhengrong Zuo Changxin Gao Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China

ISBN: (纸本)9781665428132

Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure. However, RNN suffers from non-parallelism and gradient vanishing, hence it is hard to be optimized. In this paper, we propose a new encoder-decoder framework based on Transformers, named OadTR, to tackle these problems. The encoder attached with a task token aims to capture the relationships and global inter-actions between historical observations. The decoder extracts auxiliary information by aggregating anticipated future clip representations. Therefore, OadTR can recognize current actions by encoding historical information and predicting future context simultaneously. We extensively evaluate the proposed OadTR on three challenging datasets: HDD, TVSeries, and THUMOS14. The experimental results show that OadTR achieves higher training and inference speeds than current RNN based approaches, and significantly outperforms the state-of-the-art methods in terms of both mAP and mcAP. Code is available at https://***/wangxiang1230/OadTR.

关键词： Training Visualization Recurrent neural networks Streaming media Transformers Encoding Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

A pushing-grasping collaborative method based on deep q-network algorithm in dual perspectives

arXiv

引用

arXiv 2021年

作者： Gang, Peng Jinhu, Liao Shangbin, Guan Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Aiming at the traditional grasping method for manipulators based on 2D camera, when faced with the scene of gathering or covering, it can hardly perform well in unstructured scenes that appear as gathering and covering, for the reason that can’t recognize objects accurately in cluster scenes from a single perspective and the manipulators can’t make the environment better for grasping. In this case, a novel method of pushing-grasping collaborative based on the deep Q-network in dual perspectives is proposed in this paper. This method adopts an improved deep Q-network algorithm, with an RGB-D camera to obtain the information of objects’ RGB images and point cloud from two perspectives, and combines the pushing and grasping actions, so that the trained manipulator can make the scenes better for grasping, so that it can perform well in more complicated grasping scenes. What’s more, we improved the reward function of the deep Q-network and propose the piecewise reward function to speed up the convergence of the deep Q-network. We trained different models and tried different methods in the V-REP simulation environment, and it drew a conclusion that the method proposed in this paper converges quickly and the success rate of grasping objects in unstructured scenes raises up to 83.5%. Besides, it shows the generalization ability and well performance when novel objects appear in the scenes that the manipulator has never grasped before. Copyright © 2021, The Authors. All rights reserved.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Active Learning for Simultaneous Emotion Classification and Regression

Multi-Task Active Learning for Simultaneous Emotion Classifi...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xue Jiang Lubin Meng Dongrui Wu Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781665442084

Emotion recognition, which aims to identify an individual’s emotional state from the acquired physiological or body signals, is very important in affective computing. Emotions have two common representations: categorical, e.g., happy, sad, etc., and dimensional (continuous), e.g., valence, arousal and dominance. Training a good emotion classification or regression model usually requires a large number of labeled data. However, the labeling process is very difficult. As emotions are subtle and uncertain, it usually requires multiple assessors to label each emotional instance to obtain the groundtruth categorical label or dimensional values. In this paper, we propose a multi-task active learning (MTAL) framework to query the most useful samples for labeling, which enables the efficient training of an emotion classification model and multiple emotion regression models simultaneously. This is novel and challenging, as all previous research considered only emotion classification or regression alone, but not simultaneously. Experimental results on the IEMOCAP dataset demonstrated that MTAL outperformed random selection and several state-of-the-art single task active learning approaches, i.e., with the same number of labeled samples, MTAL can obtain better emotion classification and regression models simultaneously.

关键词： Training Emotion recognition Conferences Multitasking Physiology Data models Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

A Multi-scale Network for Semantic Segmentation of 3D Point Clouds

A Multi-scale Network for Semantic Segmentation of 3D Point ...

引用

Chinese Automation Congress (CAC)

作者： Ying He Li Xiao Yong Jiang Zhigang Sun Zhuo Wang Gang Peng Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

Semantic segmentation is a fundamental operation in scene analysis. In this paper, an effective multiscale network for 3D point cloud semantic segmentation was introduced. By using a multiscale local feature extraction module which composed of four feature extractors of different scales in parallel, the generalizability of network for complex structures is enhanced effectively. To adaptively learn important feature channels, an attention mechanism is designed. Combining multiple features through skip connection, the network can preferably assign the semantic label for every point by exploiting global and local features. Experiments on 3D dataset (S3DIS) verify that our network is able to learn local region features, and the results are superior or comparable to the state-of-the-art.

关键词： Feature extraction Three-dimensional displays Semantics Two dimensional displays Intelligent control Image processing Automation

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：