检索结果-内蒙古大学图书馆

Late better than early: A decision-level information fusion approach for RGB-Thermal crowd counting with illumination awareness

引用

NEUROCOMPUTING 2024年 594卷

作者： Cheng, Jian Feng, Chen Xiao, Yang Cao, Zhiguo Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

In this paper, we make the first research effort to address the RGB-Thermal (RGB-T) crowd counting problem with the decision -level late fusion manner. Being different from the existing pixel -level or feature -level fusion methods, our proposition chooses to fuse the density maps yielded by RGB and thermal counterparts via spatially adaptive weighting with RGB illumination -aware attention. Our key intuition to conduct RGB-T density map fusion lies in 2 main folders. First, compared with the raw RGB-T images or convolutional feature maps, RGB-T density maps contain stronger counting -wise semantic meanings. Secondly, they are also of high spatial resolution for revealing fine local details. To fuse them adaptively, a spatial weighting map for each modality, together with an illumination -related RGB weight is generated. In this way, the issues of RGB illumination awareness and local counting pattern characterization ability are concerned jointly. To the best of our knowledge, we are the first to leverage RGB-T crowd counting concerning these 2 issues in a unified way. Meanwhile, cross -modality feature interaction is conducted between RGB and thermal modalities to facilitate spatial weighting map generation. The experiments on 2 well -established RGB-T crowd counting datasets ( i.e. , RGBT-CC and DroneRGBT) verify the superiority of our proposition.

关键词： Crowd counting RGB-T image Decision-level fusion

来源：评论

学校读者我要写书评

暂无评论

Cross-Task Inconsistency Based Active Learning (CTIAL) for Emotion Recognition

引用

IEEE TRANSACTIONS ON AFFECTIVE COMPUTING 2024年第3期15卷 1659-1668页

作者： Xu, Yifan Jiang, Xue Wu, Dongrui Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Minist Educ Image Proc & Intelligent Control Wuhan 430074 Peoples R China

Emotion recognition is a critical component of affective computing. Training accurate machine learning models for emotion recognition typically requires a large amount of labeled data. Due to the subtleness and complexity of emotions, multiple evaluators are usually needed for each affective sample to obtain its ground-truth label, which is expensive. To save the labeling cost, this paper proposes an inconsistency-based active learning approach for cross-task transfer between emotion classification and estimation. Affective norms are utilized as prior knowledge to connect the label spaces of categorical and dimensional emotions. Then, the prediction inconsistency on the two tasks for the unlabeled samples is used to guide sample selection in active learning for the target task. Experiments on within-corpus and cross-corpus transfers demonstrated that cross-task inconsistency could be a very valuable metric in active learning. To our knowledge, this is the first work that utilizes prior knowledge on affective norms and data in a different task to facilitate active learning for a new task, even the two tasks are from different datasets.

关键词： Task analysis Uncertainty Measurement uncertainty Estimation Entropy Emotion recognition Affective computing Active learning emotion classification emotion estimation transfer learning

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Feature Warping and Blending for Talking Head Animation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第8期34卷 7301-7314页

作者： Zhang, Jiale Liu, Chengxin Xian, Ke Cao, Zhiguo Huazhong Univ Sci & Technol Minist Educ Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

Talking head animation transforms a source anime image to a target pose, where the transformation includes the change of facial expression and head movement. In contrast to existing approaches that operate on the low-resolution image (256 x 256), we study this task at a higher resolution, e.g., 512 x 512 . High-resolution talking head animation, however, raises two major challenges: i) how to achieve smooth global transformation while maintaining rich details of anime characters under large-displacement pose variations;ii) how to address the shortage of data, because no related dataset is publicly available. In this paper, we present a Hierarchical Feature Warping and Blending (HFWB) model, which tackles talking head animation hierarchically. Specifically, we use low-level features to control global transformation and high-level features to determine the details of anime characters, under the guidance of feature flow fields. These features are then blended by selective fusion units, outputting transformed anime images. In addition, we construct an anime pose dataset-AniTalk-2K, aiming to alleviate the shortage of data. It contains around 2000 anime characters with thousands of different face/head poses at a resolution of 512 x 512 . Extensive experiments on AniTalk-2K demonstrate the superiority of our approach in generating high-quality anime talking heads over state-of-the-art methods.

关键词： Head image resolution Task analysis Generators Vectors Animation Iterative methods Talking head animation generative adversarial networks pose transformation anime image generation anime dataset

来源：评论

学校读者我要写书评

暂无评论

Optimal Spatial-Temporal Scheduling for EVs With Stochastic Behaviors and Possible Inauthentic Information

引用

IEEE TRANSACTIONS ON SMART GRID 2024年第1期15卷 729-742页

作者： Wang, Yan-Wu Cao, Zhong Xiao, Jiang-Wen Liu, Xiao-Kang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China

This paper studies the spatial-temporal scheduling for electric vehicles with stochastic charging behaviors. A new spatial-temporal scheduling model is proposed to achieve both the spatial coordination and temporal coordination for EV users and is modeled as a non-convex optimization problem which can be solved by the coordinate descent method. Further, a new billing method of charging cost is proposed based on the Vickrey-Clarke-Groves to avoid possible inauthentic information from users. Specially, the individual rationality and incentive compatibility of the method are theoretically proved. Moreover, a stochastic optimization problem is proposed to describe the stochastic charging behavior of users, which can fit the real application better than the deterministic one. Consequently, an efficient charging strategy is obtained via chance constraint method. Simulation results and comparison studies show the effectiveness of both the model and the billing method.

关键词： Electric vehicle charging strategy chance constraint inauthentic information coordinate descent method

来源：评论

学校读者我要写书评

暂无评论

Pseudo label Fusion With Uncertainty Estimation for Semi-Supervised Cropping Box Regression

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 8157-8171页

作者： Pan, Zhiyu Cui, Jiahao Wang, Kewei Wu, Yizheng Cao, Zhiguo Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Sch Artificial Intelligence & Automat Minist Educ Wuhan 430074 Peoples R China

Cropping box regression algorithms re-frame the images with predicted cropping boxes for better composition quality, which can save considerable manpower and time for massive image retouching work. Yet, recent learning-based cropping box regression algorithms require expert annotations, which makes the scale of training limited. This consequently incurs a performance bottleneck. To address this issue, previous works seek the help from auxiliary datasets of related tasks, e.g., the composition classification. However, the domain gap between related tasks and the likewise restricted scale of auxiliary datasets are still limiting factors. Hence, our work provides a novel semi-supervised framework that can learn better re-framing knowledge with unlimited unlabeled data. We make use of the unlabeled data via pseudo-labeling, where the model learns from the pseudo labels generated from a temporal ensemble version of itself. To prevent the model learns from its own mistakes, a.k.a. the problem of confirmation bias, we propose to rectify the mistakes by fusing multiple candidate pseudo labels into the better ones. The fusion procedure is based on the uncertainty estimation for each boundary of the candidate cropping boxes. The multiple candidates are from the proposed aesthetic region proposal network. Extensive experimental results explain how the uncertainty-based pseudo label fusion procedure overcomes the confirmation bias and demonstrate the superiority of our semi-supervised cropping box regression framework.

关键词： Task analysis Uncertainty Annotations Semisupervised learning Object detection Data models Multitasking image cropping cropping box regression semi-supervised learning uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

Geometry-sensitive semantic modeling in visual and visual-language domains for image captioning

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 147卷

作者： Zhu, Wencai Jiang, Zetao He, Yuting Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541004 Peoples R China

Transformer-based models with grid features as visual representations perform well in image captioning. However, the division and flattening operations increase the difficulty of capturing objects and their relationships via pure semantic modeling. Furthermore, the natural language generated by the current Transformer model still suffers from semantic overconcentration. In this paper, we aim to improve the attention modules in two ways to solve the above issues. We first propose a Geometry-Sensitive Self-Attention (GSSA) module, subdivide geometric signals in the visual domain into relative position and distance, and assist the semantic modeling process according to their unique characteristics. It compensates for the lack of objects and their relationships in the grid features. Then, we propose a Geometry-Sensitive Cross-Attention (GSCA) module, which perceives the source neighboring relationships between images and text in the visual-language domain from a geometric perspective and uses these relationships to adjust the semantic correspondences between the two dynamically. It spreads overly focused attention to surrounding grids to improve understanding of full image content during captioning. To prove our designs, we apply GSSA and GSCA to a standard Transformer to construct a novel Geometry-Sensitive Transformer Network (GSTNet), which conducts geometry-sensitive semantic modeling in visual and visual-language domains. Extensive experiments are conducted to verify the effectiveness of our proposal. The results show that our GSTNet achieves superior performance compared to many state-of-theart image captioning models on the Microsoft Common Objects in Context (MSCOCO) dataset. Besides, the generalization of GSTNet is also verified on the Flickr30k dataset.

关键词： image captioning Grid features Transformer mechanism Geometry-sensitive semantic modeling

来源：评论

学校读者我要写书评

暂无评论

DMFormer: Dense Memory Linformer for image Captioning

引用

ELECTRONICS 2025年第9期14卷 1716-1716页

作者： He, Yuting Jiang, Zetao Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541004 Peoples R China

image captioning is a cross-task of computer vision and natural language processing, aiming to describe image content in natural language. Existing methods still have deficiencies in modeling the spatial location and semantic correlation between image regions. Furthermore, these methods often exhibit insufficient interaction between image features and text features. To address these issues, we propose a Linformer-based image captioning method, the Dense Memory Linformer for image Captioning (DMFormer), which has lower time and space complexity than the traditional Transformer architecture. The DMFormer contains two core modules: the Relation Memory Augmented Encoder (RMAE) and the Dense Memory Augmented Decoder (DMAD). In the RMAE, we propose Relation Memory Augmented Attention (RMAA), which combines explicit spatial perception and implicit spatial perception. It explicitly uses geometric information to model the geometric correlation between image regions and implicitly constructs memory unit matrices to learn the contextual information of image region features. In the DMAD, we introduce Dense Memory Augmented Cross Attention (DMACA). This module fully utilizes the low-level and high-level features generated by the RMAE through dense connections, and constructs memory units to store prior knowledge of image and text. It learns the cross-modal associations between visual and linguistic features through an adaptive gating mechanism. Experimental results on the MS-COCO dataset show that the descriptions generated by the DMFormer are richer and more accurate, with significant improvements in various evaluation metrics compared to mainstream methods.

关键词： image captioning Linformer relation memory augmented attention dense memory augmented cross attention

来源：评论

学校读者我要写书评

暂无评论

Model-Independent Robust Consensus for Multiple Euler-Lagrange Systems of an Uncertain Leader

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2024年第12期54卷 7279-7290页

作者： Long, Mingkang Su, Housheng Huazhong Univ Sci & Technol Educ Minist China Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

In this article, we introduce adaptive robust observers for the estimation of comprehensive state variables and model parameters of a leader system. In particular, we suppose that the communication network among followers suffers communication link faults (CLFs), and the leader contains uncertainty, which means no follower knows the model parameters of leader system. Then, by applying the proposed observers, we elaborate on the design of a robust model-independent controller tailored for the leader-follower consensus problem (LFCP) of multiple Euler-Lagrange systems (MELSs). In contrast to the controllers currently employed for the LFCP in MELSs, the controller developed herein exhibits robustness against bounded external disturbances. Besides, the controller does not rely on the specific structure or characteristics of the Euler-Lagrange (EL) system model. At last, we provide simulation examples to demonstrate the validity of the proposed observers and the robust controller in the context of the LFCP for MELSs.

关键词： Observers Adaptation models Vectors Adaptive systems Communication networks Robustness Eigenvalues and eigenfunctions Communication link faults (CLFs) leader-follower consensus problem (LFCP) model-independent multiple Euler-Lagrange systems (MELSs) robust control uncertain leader

来源：评论

学校读者我要写书评

暂无评论

Additive-state-decomposition-based model predictive tracking control for PMSM servo system with multiple disturbances

引用

JOURNAL OF THE FRANKLIN INSTITUTE 2023年第13期360卷 9378-9398页

作者： Jiang, Fuxi Cheng, Shanmei Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan Peoples R China

This paper presents an additive-state-decomposition-based model predictive tracking control and disturbance rejection method for a permanent magnet synchronous motor (PMSM) servo system subject to unknown parameter perturbations, unmodeled dynamics, and time-varying load torque. The basic idea of this method is to equivalently decompose the original system into a primary system for handling the tracking control subproblem and a secondary system for dealing with the robust stabilization subproblem. A model predictive controller is designed for the primary system to achieve high-accuracy tracking of the reference speed. As for the secondary system, a novel high-order generalized extended state observer (HGESO) is constructed to estimate the multiple disturbances simultaneously, and a state feedback control law incorporating a disturbance compensator is developed to eliminate the adverse effect of the multiple disturbances on the system output. By combining the control inputs of the two subsystems together, the control objectives of the original system can be achieved. Both the stability criterion and design procedure of the closed-loop control system are developed. Finally, hardware-in-the-loop-based comparative experiments are conducted to demonstrate that the proposed method effectively suppresses the influence of the multiple disturbances on motor speed tracking accuracy and that the control system has both satisfactory dynamic performance and robustness. (c) 2023 The Franklin Institute. Published by Elsevier Inc. All rights reserved.

关键词： Closed loop control systems

来源：评论

学校读者我要写书评

暂无评论

Channel-level Matching Knowledge Distillation for object detectors via MSE

引用

PATTERN RECOGNITION LETTERS 2024年 179卷 52-57页

作者： Jiang, Zetao Huang, Qinyang Zhang, Huijuan Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541004 Peoples R China

Knowledge distillation (KD) has been widely used in different tasks as a practical model compression technique. Due to the poor performance of directly using Mean Square Error (MSE) between the intermediate features of the teacher and student, most feature -based detector distillation methods are primarily concerned with proposing diverse attention mechanisms and employing MSE to guide the student in learning critical information. However, the significance of MSE in detector distillation is often overlooked. To enhance the distillation performance of MSE and provide a novel perspective, we propose channel -level Matching Knowledge Distillation via MSE (MKD). The idea of MKD is simple but effective: based on the match or mismatch of student and teacher channel features in Feature Pyramid Networks (FPN), we divide channels at the same location in the FPN layers of the student and teacher into match channels and mismatch channels and then assign different weights to them to calculate the MSE-based distillation loss, which forces the student to distinguish the teacher's channels and imitate the features of the corresponding channels to achieve better performance. We conduct extensive experiments on MS COCO and PASCAL VOC benchmarks to prove that MKD is superior to state-of-the-art distillation methods. For example, with a powerful RetinaNet-ResNeXt101 detector as the teacher, ResNet-50 based RetinaNet and RepPoints with our distillation method achieve 40.9% and 42.2% mAP on COCO2017, which are 3.5% and 3.6% higher than the baseline, respectively.

关键词： Knowledge distillation Object detection Channel matching Mean squared error

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：