检索结果-内蒙古大学图书馆

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Wang, Tiantian Lu, Xiaoqi Inner Mongolia University of Science and Technology School of Information Engineering Baotou014010 China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Baotou014010 China Inner Mongolia University of Technology Institute of Information Engineering Hohhot010051 China

ISBN: (纸本)9798350302455

DeepFakes blur the boundaries between reality and forgery, resulting in the collapse of exiting credit system, causing immeasurable consequences for national security and social order. Through analysis of existing face forgery techniques, it is found that most generation techniques rely on random noise distribution, and global information will be lost after up sampling. Therefore, we propose a deepfake detection algorithm based on improved MobileViT, which uses CNN local space biasing and the global space representation of the Transformer network to learn the local features and global representation of forged faces, respectively. Coordinate attention is introduced to obtain directional perception and position sensitive information, making the model locate synthetic traces of fake faces better and fusion local and global representation more effectively. For the improved generalization of the model, with the GELU activation function to solve the problem of neuron death. Our model achieved 96.2% on FF++(C23) datasets, and 93.7%,94.1%,96.3%,87.9% on DF, F2F, FS, and NT datasets, respectively. Comparing with previous methods, our model has shown detection robustness and better generalization. © 2023 IEEE.

关键词： National security

来源：评论

学校读者我要写书评

暂无评论

ATCA: AN ARC TRAJECTORY BASED MODEL WITH CURVATURE ATTENTION FOR VIDEO FRAME INTERPOLATION

arXiv

引用

arXiv 2022年

作者： Liu, Jinfeng Kong, Lingtong Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Video frame interpolation is a classic and challenging low-level computer vision task. Recently, deep learning based methods have achieved impressive results, and it has been proven that optical flow based methods can synthesize frames with higher quality. However, most flow-based methods assume a line trajectory with a constant velocity between two input frames. Only a little work enforces predictions with curvilinear trajectory, but this requires more than two frames as input to estimate the acceleration, which takes more time and memory to execute. To address this problem, we propose an arc trajectory based model (ATCA), which learns motion prior from only two consecutive frames and also is lightweight. Experiments show that our approach performs better than many SOTA methods with fewer parameters and faster inference speed. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Fre-Yolo: Feature Refinement Extraction Network with Yolo for Blade Tip Small Point Light Detection

SSRN

引用

SSRN 2024年

作者： Zheng, Wenhao Xiong, Bangshu Yi, Hui Au, Qiaofeng Chen, Jiujiu Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang330063 China China Helicopter Research and Development Institute China

Detecting blade tip point light sources based on airborne computer vision is a critical step in measuring blade tip distance for coaxial unmanned helicopters. However, detecting blade tip point light sources quickly and highly accurately in a helicopter airborne environment is a challenge due to the extremely tiny imaging size of the blade tip point light sources. To this end, we propose a FRE-YOLO for detecting blade tip point light sources based on the YOLO network structure. In this work, we focus on designing a Feature Refinement Extraction network (FRE), which can greatly enrich the feature information of small targets during Backbone downsampling. Secondly, we also design a new paradigm Smooth Gaussian Distance (SmoothGD) which measures the degree of target bounding box matching. SmoothGD is mainly applied to regression loss calculation and label assigner, which can effectively improve the small target detection accuracy. Meanwhile, we construct the Blade Tip Point Light (BTPL) dataset for the network training. In addition, in order to evaluate the effectiveness of the proposed method more fairly, this paper conducts the same experiments on BTPL and the small target dataset VisDrone on MMYOLO. A large amount of experimental data shows that the proposed method has a positive impact on the detection of tiny point sources at the tip of the blade. It is also at the advanced level in the field of generalized small object detection. © 2024, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Variational Hierarchical N-BEATS Model for Long-term Time-series Forecasting

TechRxiv

引用

TechRxiv 2023年

作者： Yang, Runze Li, Jianxun Yang, Jie Cao, Longbing The Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China School of Computing Macquarie University Australia

Long-term time-series forecasting (LTSF) has received an increasing attention for its significant challenges and real-world applications. However, the previous studies under-explore the hierarchical timestamp information in LTSF. This information is crucial, especially for LTSF as failing to incorporate it may result in missing the global perspective of time series and important long-term trending effects, such as weekly and seasonal patterns. Therefore, we propose an interpretable hierarchical model called VH-NBEATS, which advances the NBEATS model by addressing the aforementioned problem. VH-NBEATS comprises two essential blocks: the hierarchical timestamp block and the harmonic seasonal block to capture multidiluted and trending effects. To address the high variability of time series, VH-NBEATS involves a stochastic autoencoder which significantly improves the standard deterministic approach. The experimental results are evaluated on five real-world datasets, showing state-of-the-art results for LTSF. We also prove that the VH-NBEATS framework can be easily incorporated into other ones, such as PathTST, leading to enhanced performance. © 2023, CC BY.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A Vision-Based Counter System for Children’s Dribble 23

A Vision-Based Counter System for Children’s Dribble

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Jingxin, Liang Chengqi, Liang Xufeng, Ling Jie, Yang Shanghai Normal University Tianhua College AI School No. 1661 North Sheng Xin Road *** China Gaozhou Middle School Guangdong Province Gaozhou China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University 800 Dongchuan Road 200240 China

ISBN: (纸本)9781450399029

In this paper, a vision-based counter system for children’s dribble based on Google MediaPipe’s human posture recognition algorithm and YOLOv5 object recognition algorithm is introduced. Firstly, the hands’ coordinates of the child is located using MediaPipe, and the coordinates of the ball is found using YOLOv5;by the relative positions of the hands and the ball in the multi-frame images of the video, an action sequence of ball holding, touching and ball bouncing is recognized and used to count the number of dribble. The experimental results show that the system can count a single child’s dribble accurately. © 2023 Copyright held by the owner/author(s).

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Ocean archaea PPI prediction with pretraining models 25

Ocean archaea PPI prediction with pretraining models

引用

Proceedings of the 2025 5th International Conference on Bioinformatics and Intelligent Computing

作者： Ying Zhang Yuan Liu Xiaoyong Pan Hongbin Shen Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798400712203

Protein-Protein Interaction (PPI) provides important insights into the metabolic mechanisms of different biological processes. Although PPIs in some organisms have been investigated systematically, PPIs in the ocean archaea remain largely unexplored. But such species have special investigation value since their adaptation to extreme living conditions may generate unique PPIs. In this paper, we aim to characterize and predict PPIs in ocean archaea to advance understanding of their metabolic networks. First, we collect all ocean archaea PPIs with high confidence from STRING database and analyze the PPI network features, including centrality and enrichment analysis. The functional enrichment results of the largest connecting subgraph in the PPI network show most PPIs in our constructed dataset is related to the translation and transcription processes. Then, we generate an equal number of negative PPI pairs, whose members have either different subcellular locations or GO terms. We also use the generated dataset to test the performance of three pretraining methods and their ensemble methods in the binary PPI prediction task. Our results suggest the ensemble methods could be applied to further improve models’ performance. Fine-tuned models trained on the ocean archaea dataset are expected to predict the other ocean archaea PPIs that are not included in the STRING database and get more understanding about the ocean archaea PPI universe.

关键词： Binary PPI prediction

来源：评论

学校读者我要写书评

暂无评论

Family Doctor Model Training Based on Large Language Model Tuning 1st

Family Doctor Model Training Based on Large Language Model T...

引用

1st International Conference on pattern Analysis and Machine Intelligence, ICPAMI 2024

作者： Zhu, Yu Li, Wangtao Ling, Xufeng Yang, Jie Shanghai China School of AI Shanghai Normal University Tianhua College Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9789819633487

As society increasingly focuses on health issues, the importance of the role of family doctors becomes more apparent. The question of how to use cutting-edge technology to improve the accessibility and efficiency of medical services is a critical topic. Generative large language models, with their excellent capabilities in natural language processing, offer new possibilities for the implementation of intelligent family doctor systems. This study focuses on the application of generative large language models in family doctor systems, selecting the ChatGLM2-6B model as the base model for this research. Through a custom-written data collection program, a dataset containing 170,000 high-quality medical question-and-answer entries was constructed. The LoRA method was used to tune the base model, and the performance of the original and tuned models in medical question-and-answer tasks was examined. The practical results of this study show that the generatively tuned large language model has achieved a 70% improvement in ROUGE scores compared to the untuned model, validating the effectiveness of large language model tuning in the family doctor field. Furthermore, this study has open-sourced the collected dataset and program, providing a technical reference for deploying efficient and accurate question-and-answer systems in similar vertical fields in the future. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

FASTC: A Fast Attentional Framework for Semantic Traversability Classification Using Point Cloud

arXiv

引用

arXiv 2024年

作者： Chen, Yirui Wei, Pengjin Liu, Zhenhuan Wang, Bingchao Yang, Jie Liu, Wei Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University China Key Laboratory of System Control and Information Processing Ministry of Education China

Producing traversability maps and understanding the surroundings are crucial prerequisites for autonomous navigation. In this paper, we address the problem of traversability assessment using point clouds. We propose a novel pillar feature extraction module that utilizes PointNet to capture features from point clouds organized in vertical volume and a 2D encoder-decoder structure to conduct traversability classification instead of the widely used 3D convolutions. This results in less computational cost while even better performance is achieved at the same time. We then propose a new spatio-temporal attention module to fuse multi-frame information, which can properly handle the varying density problem of LIDAR point clouds, and this makes our module able to assess distant areas more accurately. Comprehensive experimental results on augmented Semantic KITTI and RELLIS-3D datasets show that our method is able to achieve superior performance over existing approaches both quantitatively and quantitatively. Our code is publicly available at https://***/chenyirui/FASTC. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Video Compression Artifacts Removal With Spatial-Temporal Attention-Guided Enhancement

引用

IEEE Transactions on Multimedia 2024年 26卷 5657-5669页

作者： Jiang, Nanfeng Chen, Weiling Lin, Jielian Zhao, Tiesong Lin, Chia-Wen Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fuzhou350108 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology Xiamen361024 China Fujian Science and Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou350116 China Department of Electrical Engineering National Tsing Hua University Hsinchu30013 Taiwan Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan

Recently, many compression algorithms are applied to decrease the cost of video storage and transmission. This will introduce undesirable artifacts, which severely degrade visual quality. Therefore, Video Compression Artifacts Removal (VCAR) aims at reconstructing a high-quality video from its corrupted version of compression. Generally, this task is considered as a vision-related instead of media-related problem. In vision-related research, the visual quality has been significantly improved while the computational complexity and bitrate issues are less considered. In this work, we review the performance constraints of video coding and transfer to evaluate the VCAR outputs. Based on the analyses, we propose a Spatial-Temporal Attention-Guided Enhancement Network (STAGE-Net). First, we employ dynamic filter processing, instead of conventional optical flow method, to reduce the computational cost of VCAR. Second, we introduce self-attention mechanism to design Sequential Residual Attention Blocks (SRABs) to improve visual quality of enhanced video frames with bitrate constraints. Both quantitative and qualitative experimental results have demonstrated the superiority of our proposed method, which achieves high visual qualities and low computational costs. © 2023 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Online Continual Learning via Logit Adjusted Softmax

arXiv

引用

arXiv 2023年

作者： Huang, Zhehao Li, Tao Yuan, Chenhe Wu, Yingwen Huang, Xiaolin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Department of Automation Shanghai Jiao Tong University China

Online continual learning is a challenging problem where models must learn from a non-stationary data stream while avoiding catastrophic forgetting. Inter-class imbalance during training has been identified as a major cause of forgetting, leading to model prediction bias towards recently learned classes. In this paper, we theoretically analyze that inter-class imbalance is entirely attributed to imbalanced class-priors, and the function learned from intra-class intrinsic distributions is the optimal classifier that minimizes the class-balanced error. To that end, we present that a simple adjustment of model logits during training can effectively resist prior class bias and pursue the corresponding optimum. Our proposed method, Logit Adjusted Softmax, can mitigate the impact of inter-class imbalance not only in class-incremental but also in realistic scenarios that sum up class and domain incremental learning, with little additional computational cost. We evaluate our approach on various benchmarks and demonstrate significant performance improvements compared to prior arts. For example, our approach improves the best baseline by 4.6% on CIFAR10. Codes are available at https://***/K1nght/online_CL_logit_adjusted_softmax. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

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：