检索结果-内蒙古大学图书馆

Action quality assessment via moment aware network

Evolving Systems 2025年第2期16卷 1-10页

作者： Han, Jifeng Zhang, Yanduo Lu, Tao Wang, Jiaming Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

Recent action quality assessment methods attempt to decompose the entire video into sub-actions of the same level, which still suffers from information redundancy and lacks certain interpretability. Through studying and analysing the evaluation rules of relevant sports events, we assume that certain critical moments in the actions will significantly impact the assessment of the entire action, if the weight of these critical moments in the evaluation process can be increased, then the results can be more accurate and more persuasive. To validate this idea, we propose a moment-aware approach for action quality assessment, a novel moment-aware module is used to explore the key moments in action globally and locally to obtain more reliable evaluation results. Extensive experiments have shown that our module captures key moments that are close to the focus of human referees, and our method has also achieved favorable results on multiple public AQA benchmarks, the Spearman’s rank correlation reached 0.9360 on FineDiving dataset and 0.8797 on AQA-7 dataset. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

An Efficient Instance Segmentation Based on Layer Aggregation and Lightweight Convolution

引用

Computers, Materials & Continua 2025年第4期83卷 1041-1055页

作者： Hui Jin Shuaiqi Xu Chengyi Duan Ruixue He Ji Zhang College of Mechanical Engineering Chongqing University of TechnologyChongqing400054China Robot and Intelligent Manufacturing Technology Key Laboratory of Chongqing Education Commission of ChinaChongqing400054China

Instance segmentation is crucial in various domains,such as autonomous driving and ***,there is scope for improvement in the detection speed of instance-segmentation algorithms for edge ***,it is essential to enhance detection speed while maintaining high *** this study,we propose you only look once-layer fusion(YOLO-LF),a lightweight instance segmentation method specifically designed to optimize the speed of instance segmentation for autonomous driving *** on the You Only Look Once version 8 nano(YOLOv8n)framework,we introduce a lightweight convolutional module and design a lightweight layer aggrega-tion module called Reparameterization convolution and Partial convolution Efficient Layer Aggregation Networks(RPELAN).This module effectively reduces the impact of redundant information generated by traditional convolutional stacking on the network size and detection speed while enhancing the capability to process feature *** experimentally verified that our generalized one-stage detection network lightweight method based on Grouped Spatial Convolution(GSconv)enhances the detection speed while maintaining accuracy across various state-of-the-art(SOTA)*** experiments conducted on the publicly available Cityscapes dataset demonstrated that YOLO-LF maintained the same accuracy as yolov8n(mAP@0.537.9%),the model volume decreased by 14.3%from 3.259 to=2.804 M,and the Frames Per Second(FPS)increased by 14.48%from 57.47 to 65.79 compared with YOLOv8n,thereby demonstrating its potential for real-time instance segmentation on edge devices.

关键词： Automatic driving convolution deep learning real-time instance segmentation

来源：评论

学校读者我要写书评

暂无评论

MST-Adapter: Multi-Scaled Spatio-Temporal Adapter for Parameter-Efficient Image-to-Video Transfer Learning

引用

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences 2025年第5期E108.A卷 736-745页

作者： Chang, Chenrui Lu, Tongwei Yao, Feng Hubei Key Laboratory of Intelligent Robot School of Computer Science and Engineering Wuhan Institute of Technology Wuhan430205 China

Large-scale image pre-training models have recently demonstrated strong representation capabilities in spatial information contexts. Prior works apply these models to video action recognition through fully fine-tuning, which is expensive and resource-intensive. To reduce computational costs, some studies have shifted their focus to efficient parameter fine-tuning methods. However, existing efficient fine-tuning methods lack exploration of multi-scale information in videos. In this work, the Multi-scale spatio-temporal Adapter (MST-Adapter) is proposed for parameter-efficient Image-to-Video transfer learning. By freezing the pretrained models and adding the lightweight adapters, we only need to update few parameters, which is highly efficient. In addition, extensive experiments on two video action recognition benchmarks show that our method can learn high-quality video spatio-temporal representations and achieve competitive or even better performance than prior works. Copyright © 2025 The Institute of Electronics, Information and Communication Engineers.

关键词： multi-scale spatio-temporal adapter parameter-efficient image-to-video transfer learning video action recognition video spatiotemporal representations

来源：评论

学校读者我要写书评

暂无评论

DSSNet: a transformer-based network for dense scene text detection and recognition in complex environments 5

DSSNet: a transformer-based network for dense scene text det...

引用

5th International Conference on Signal Processing and Computer Science, SPCS 2024

作者： Li, Jing Zhou, Huabing College of Computer Science and Engineering Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (数字)9781510686731

ISBN: (纸本)9781510686724

This paper presents a novel approach for dense scene text detection called DSSNet (Dense Script Spotter Network). The network leverages ResNet and FPN for feature extraction, employing multi-scale feature fusion and Transformer-based feature processing to enhance text recognition across varying sizes. The method generates text instance shapes using Bézier central curves and performs text recognition by integrating positional query information. Experimental results on the DSTD1500 and ICDAR2015 datasets demonstrate that DSSNet outperforms existing methods in terms of text localization accuracy, recognition accuracy, and annotation flexibility. © 2025 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Accelerated inference for thyroid nodule recognition in ultrasound imaging using FPGA

引用

Physical and Engineering Sciences in Medicine 2025年 1-9页

作者： Ma, Wei Wu, Xiaoxiao Zhang, Qing Li, Xiang Wu, Xinglong Wang, Jun School of Computer Science and Engineering Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China School of Computer Science and Artificial Intelligence Wuhan Textile University Wuhan China

Thyroid cancer is the most prevalent malignant tumour in the endocrine system, with its incidence steadily rising in recent years. Current central processing units (CPUs) and graphics processing units (GPUs) face significant challenges in terms of processing speed, energy consumption, cost, and scalability in the identification of thyroid nodules, making them inadequate for the demands of future green, efficient, and accessible healthcare. To overcome these limitations, this study proposes an efficient quantized inference method using a field-programmable gate array (FPGA). We employ the YOLOv4-tiny neural network model, enhancing software performance with the K-means + + optimization algorithm and improving hardware performance through techniques such as 8-bit weight quantization, batch normalization, and convolutional layer fusion. The study is based on the ZYNQ7020 FPGA platform. Experimental results demonstrate an average accuracy of 81.44% on the Tn3k dataset and 81.20% on the internal test set from a Chinese tertiary hospital. The power consumption of the FPGA platform, CPU (Intel Core i5-10200 H), and GPU (NVIDIA RTX 4090) were 3.119 watts, 45 watts, and 68 watts, respectively, with energy efficiency ratios of 5.45, 0.31, and 5.56. This indicates that the FPGA’s energy efficiency is 17.6 times that of the CPU and 0.98 times that of the GPU. These results show that the FPGA not only significantly outperforms the CPU in speed but also consumes far less power than the GPU. Moreover, using mid-to-low-end FPGAs yields performance comparable to that of commercial-grade GPUs. This technology presents a novel solution for medical imaging diagnostics, with the potential to significantly enhance the speed, accuracy, and environmental sustainability of ultrasound image analysis, thereby supporting the future development of medical care. © Australasian College of Physical Scientists and Engineers in Medicine 2025.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Exploration and Prospects of Large Language Models with ReAct Integration in Maritime Risk Identification

Exploration and Prospects of Large Language Models with ReAc...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Chen, Chen Shu, Zhong-Cheng Guo, Lei Chen, Yu-Han School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9789819639601

Maritime risk identification technology is more and more important for ships sailing on the sea, and can ensure the safety of ships sailing on the sea. However, traditional risk identification methods rely on historical data and qualitative experience, which is difficult to deal with complex and changeable environment. Recently, advancements in artificial intelligence, particularly large language models, have introduced new solutions to these challenges. While these models excel in data processing and pattern recognition, their effective application within the maritime domain remains problematic. This paper presents the ReAct (Reasoning and Acting) model, which enhances the adaptability of large language models by simulating human reasoning and actions. This paper first reviews the traditional methods and existing problems of maritime risk identification, and then discusses the basic principle of ReAct model and its potential in risk identification. Finally, the study proposes the integration of ReAct with large language models, highlighting the advantages and future prospects of this approach. This research aims to provide new theoretical and technological support for maritime risk identification, ultimately contributing to improved risk management and accident prevention. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Rethinking-based Code Summarization with Chain of Comments 31

Rethinking-based Code Summarization with Chain of Comments

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Cao, Liuwen He, Hongkui Huang, Hailin Wang, Jiexin Cai, Yi School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

ISBN: (纸本)9798891761964

Automatic code summarization aims to generate concise natural language descriptions (summary) for source code, which can free software developers from the heavy burden of manual commenting and software maintenance. Existing methods focus on learning a direct mapping from pure code to summaries, overlooking the significant heterogeneity gap between code and summary. Moreover, existing methods lack a human-like re-check process to evaluate whether the generated summaries match well with the code. To address these two limitations, we introduce RBCoSum, a novel framework that incorporates the generated Chain Of Comments (COC) as auxiliary intermediate information for the model to bridge the gap between code and summaries. Also, we propose a rethinking process where a learned ranker trained on our constructed ranking dataset scores the extent of matching between the generated summary and the code, selecting the highest-scoring summary to achieve a re-check process. We conduct extensive experiments to evaluate our approach and compare it with other automatic code summarization models as well as multiple code Large Language Models (LLMs). The experimental results show that RBCoSum is effective and outperforms baselines by a large margin. The human evaluation also proves the summaries generated with RBCoSum are more natural, informative, useful, and truthful. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

GCN Rewarded Reinforcement Learning for Action Segmentation 24

GCN Rewarded Reinforcement Learning for Action Segmentation

引用

4th International Joint Conference on robotics and Artificial Intelligence, JCRAI 2024

作者： Wang, Liangliang Liu, Jiayao Hu, Xujun Huo, Guanglei Wuhan University of Technology Wuhan China Beijing Jiaotong University Beijing China Institute of Advanced Manufacturing Technology Fujian Key Laboratory of Intelligent Operation and Maintenance Robot Technology Quanzhou China

ISBN: (纸本)9798400710100

Action recognition is a very basic topic for human-robot visual interaction. To enable action recognition for real-world applications, at the core is the problem of action segmentation, which aims to segment action slices from long videos. Existing action segmentation approaches rely heavily on hand-crafted techniques, which are limited on accuracy due to the spatio-temporal complexity of actions across videos. To this end, we formulate action segmentation as a Markov decision process rewarded by observing the action recognition results, and build a reinforcement learning framework to adjust the segmenting procedure iteratively according to the rewards. In particular, to perceive the segmented actions for reinforcement learning, we propose a temporal graph convolutional network (GCN) by representing the context relationships of neighboring action slices, whose states are initialized by considering the consistency of actions, and updated by computing their temporal similarity fusing the tIoU and center distance. Convolutional neural network (CNN) backbone features are used as the nodes of GCN, and the edges of GCN are calculated utilizing the context relationships for spatially and temporally representation. By designing an observation and objective module within the reinforcement learning framework based on GCN representations, we finish the network training for. Finally, we conduct extensive experiments on two public datasets, and by comparisons with some state-of-the-art results, our method is demonstrated. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-Prior Guided Spatial and Fourier Transformer for Nighttime Flare Removal

引用

IEEE Transactions on Automation Science and Engineering 2025年 22卷 11996-12011页

作者： Ma, Tianlei Kai, Zhiqiang Miao, Xikui Liang, Jing Peng, Jinzhu Wang, Yaonan Wang, Hao Liu, Xinhao Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China State Key Laboratory of Intelligent Agricultural Power Equipment Luoyang471039 China Key Laboratory of Electro-Optical Countermeasures Test and Evaluation Technology Luoyang471000 China Hunan University College of Robot and the College of Electrical and Information Engineering Changsha410082 China

When capturing scenes with intense light sources, extensive flare artifacts often obscure the background and degrade image quality. Most flare removal methods directly process the flare-corrupted image as the optimization target, limiting the model's understanding and generalization in complex real-world scenarios. In this paper, we propose a novel Self-prior Guided Spatial and Fourier Transformer (SGSFT) for nighttime flare removal. Specifically, we first establish a Self-prior Extraction Network to capture inherent priors in different scenes. Subsequently, we introduce a Semantic Contrast Enhancement Strategy to reinforce the semantic irrelevance between flare and light source, enabling the flare removal network to learn pattern differences between them and thus preserve light source. Finally, we build a Spatial and Frequency Flare Removal Network with Spatial Contextual Attention Block (SCAB) and Frequency Global Information Adjustment Block (FGIAB) to generate flare-free image. SCAB can perceive rich contextual information from self-prior guided regions and infer reasonable content. FGIAB captures global luminance representation in the frequency domain to maintain luminance consistency between the inferred regions and the flare-free areas. Extensive experiments demonstrate that the proposed approach achieves optimal performance in real nighttime scenes and exhibits robust generalization across various flare scenarios captured by different electronic devices. Note to Practitioners - The motivation of this paper is to remove flare artifacts in imaging. Flares degrade image quality and impact the performance of advanced vision tasks such as semantic segmentation and depth estimation in autonomous driving. Existing methods that indiscriminately extract contextual information from the entire image limit the model's understanding of flares. This study proposes a self-prior guided flare removal network. The network first extracts self-prior information from flare-damag

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

An efficient and scalable semi-supervised framework for semantic segmentation

引用

Neural Computing and Applications 2025年第7期37卷 5481-5497页

作者： Hao, Huazheng Xiao, Hui Xiong, Junjie Dong, Li Yan, Diqun Liang, Dongtai Zhuang, Jiayan Peng, Chengbin Ningbo University Ningbo China Zhejiang Rural Commercial Digital Technology Co. Ltd Hangzhou China Zhejiang Key Laboratory of Intelligent Operation and Maintenance Robot Hangzhou Shenhao Technology Co. Ltd Hangzhou China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo China

Semantic segmentation has succeeded remarkably in various applications, such as autonomous vehicles and robotic systems. However, the training process for such techniques necessitates a significant amount of labeled data. Although semi-supervised frameworks can alleviate this issue, advanced approaches typically require multiple baseline models to form a dual model, which is costly in space computation complexity. To relieve the undesired computational cost for systems with precious computation and memory resources, we propose an efficient and scalable semi-supervised learning framework to significantly improve the performance with a few additional parameters concerning the baseline models. This framework includes a pseudo-dual module and a self-rectification module. The overall structure comprises three parts: an encoder, a shallow decoder, and a deep decoder. The deep decoder is connected to a deep layer of the encoder, and the shallow decoder is connected to a shallow layer. As knowledge distillation transfers knowledge from one model to another, the pseudo-dual module can distill knowledge from the ensemble of two decoders to improve the encoder, which can implicitly form a pseudo-dual model. The self-rectification module calculates class-wise likelihoods according to the similarity between features and class prototypes learned from different decoders and rectifies low-confidence pseudo-labels. The effectiveness of such rectification is justified theoretically and numerically. In our experiments with DeepLabV2, our methods outperform others in mIoU by over 1.21% with 1/8 labeled data using the Cityscapes dataset and by 0.38% with 1/8 labeled data using PASCAL VOC 2012 datasets. In most cases, our approach can also save more than 30% of memory costs during training. Nevertheless, the effectiveness of the proposed approach also depends on the quality of pseudo-labels generated by backbone models and may encounter challenges when handling data with highly imbalance

关键词： Semantic Segmentation

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：