检索结果-内蒙古大学图书馆

Research on Human Eyesight Tracking Algorithm Based on Monocular Vision 2nd

学校读者我要写书评

暂无评论

Research on Human Eyesight Tracking Algorithm Based on Monoc...

2nd World Conference on Intelligent and 3D Technologies, WCI3DT 2023

作者： Tang, Haochun Zhang, Jindong Yang, Jing College of Software Jilin University Changchun130012 China College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun130012 China

ISBN: (纸本)9789819970100

This paper focuses on the optimization and improvement of the line-of-sight tracking algorithm based on monocular vision, and aims to achieve a series of complex functions through image analysis based on line-of-sight tracking technology and more in-depth analysis of monocular images. Therefore, we use the webgaze framework and use face detection models and feature point recognition libraries to analyze the recognition rate and provide further development of the technology. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Face recognition

From Incomplete Coarse-Grained to Complete Fine-Grained: A Two-Stage Framework for Spatiotemporal Data Reconstruction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Ziyu Su, Haoyang Wang, En Yang, Funing Yang, Yongjian Liu, Wenbin The College of Computer Science and Technology Jilin University Changchun130012 China The Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

With the rapid development of various sensing devices, spatiotemporal data is becoming increasingly important nowadays. However, due to sensing costs and privacy concerns, the collected data is often incomplete and coarse-grained, limiting its application to specific tasks. To address this, we propose a new task called spatiotemporal data reconstruction, which aims to infer complete and fine-grained data from sparse and coarse-grained observations. To achieve this, we introduce a two-stage data inference framework, DiffRecon, grounded in the Denoising Diffusion Probabilistic Model (DDPM). In the first stage, we present Diffusion-C, a diffusion model augmented by ST-PointFormer, a powerful encoder designed to leverage the spatial correlations between sparse data points. Following this, the second stage introduces Diffusion-F, which incorporates the proposed T-PatternNet to capture the temporal pattern within sequential data. Together, these two stages form an end-to-end framework capable of inferring complete, fine-grained data from incomplete and coarse-grained observations. We conducted experiments on multiple real-world datasets to demonstrate the superiority of our method. © 2024, CC BY.

关键词： Spatio-temporal data

Reusable Generator Data-Free knowledge Distillation with Hard Loss Simulation for Image Classification

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Sun, Yafeng Wang, Xingwang Huang, Junhong Chen, Shilin Hou, Minghui College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

In many image classification scenarios where knowledge distillation (KD) is applied, multiple users need to train various student models that conform to the device's computational limitations at different times. However, due to security concerns, existing data-free KD (DFKD) methods discard the trained generator after completing a task, preventing its reuse in training subsequent students and resulting in wasted resources. Furthermore, the unlabeled nature of fake images eliminates the hard loss that plays a crucial role in data-driven KD. This paper introduces the reusable generator DFKD with hard loss simulation (RG-HLS) to address these challenges. RG-HLS employs a generator consisting of two generative networks and a decoder. The decoder and one of the generative networks can be reused in subsequent tasks. The adversarial example attack is also introduced to mimic the behavior of the teacher model in predicting real images, ensuring that DFKD exhibits a hard loss similar to that of data-driven KD. Extensive experiments across CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets validate the proposed method's superior performance. The reusable generator accelerates convergence without compromising security, and integrating the hard loss further boosts accuracy. Code is available at https://***/sunyafeng-jlu/RG-HLS. © 2024, The Authors. All rights reserved.

关键词： Image classification

VECLLF: A vehicle-edge collaborative lifelong learning framework for anomaly detection in VANETs

学校读者我要写书评

暂无评论

Computer Networks 2025年 265卷

作者： Wang, Yingqing Liang, Yanhua Huang, Yue Qin, Guihe Jilin University College of Computer Science and Technology Changchun130012 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China Jilin University Center for Computer Fundamental Education Changchun130012 China

With the rapid development of intelligent connected vehicles, Vehicular Ad Hoc Network (VANET) is widely used in intelligent transportation systems. VANETs are vulnerable to attacks in their operating environments, such as denial of service (DoS) attacks and injection attacks. Thus, the development of an efficient anomaly detection framework is a promising solution. Most existing methods can only detect known attacks, are less efficient in detecting unknown attacks, and fail to deal with them. To solve these problems, the lifelong learning framework (LLF) is introduced, which aims to store and label suspicious data by applying blockchain and then retrain the model. However, existing LLFs are overly idealized as they do not adequately consider the key issues of label budget and storage space. To improve the practicality of existing methods, this paper proposes a novel LLF based on the existing LLF, called Vehicle Edge Collaborative Lifelong Learning Framework (VECLLF), which can deploy the model update task on the edge server. Specifically, the proposed anomaly detection module based on ensemble active learning is used to achieve high-performance detection under a limited label budget, the proposed incremental learning module based on a sample library continuously learns the model by replaying representative samples within limited storage space, the proposed optimization-based feature selection module is used to remove redundant and interfering features, and the explainable artificial intelligence (XAI) module is used to explain the model to ensure its interpretability. In addition, the blockchain-based database (BC-DB) module is used to help store suspicious data and interact with security agencies to label it. We conducted experiments on two public datasets, AWID2 and CICIDS2017, and the results show that VECLLF outperforms state-of-the-art anomaly detection models and existing LLF, with F1-scores exceeding 97% on both datasets. Furthermore, we collect data from th

关键词： Rapid transit

Learning Interpretable Network Dynamics via Universal Neural symbolic Regression

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Jiao Cui, Jiaxu Yang, Bo College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

Discovering governing equations of complex network dynamics is a fundamental challenge in contemporary science with rich data, which can uncover the mysterious patterns and mechanisms of the formation and evolution of complex phenomena in various fields and assist in decision-making. In this work, we develop a universal computational tool that can automatically, efficiently, and accurately learn the symbolic changing patterns of complex system states by combining the excellent fitting ability from deep learning and the equation inference ability from pre-trained symbolic regression. We conduct intensive experimental verifications on more than ten representative scenarios from physics, biochemistry, ecology, epidemiology, etc. Results demonstrate the outstanding effectiveness and efficiency of our tool by comparing with the state-of-the-art symbolic regression techniques for network dynamics. The application to real-world systems including global epidemic transmission and pedestrian movements has verified its practical applicability. We believe that our tool can serve as a universal solution to dispel the fog of hidden mechanisms of changes in complex phenomena, advance toward interpretability, and inspire more scientific discoveries. Copyright © 2024, The Authors. All rights reserved.

关键词： Economic and social effects

Toward Time-Continuous Data Inference in Sparse Urban CrowdSensing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Ziyu Su, Haoyang Sun, Hanqi Wang, En Liu, Wenbin The College of Computer Science and Technology Jilin University Changchun130012 China The Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

Mobile Crowd Sensing (MCS) is a promising paradigm that leverages mobile users and their smart portable devices to perform various real-world tasks. However, due to budget constraints and the inaccessibility of certain areas, Sparse MCS has emerged as a more practical alternative, collecting data from a limited number of target subareas and utilizing inference algorithms to complete the full sensing map. While existing approaches typically assume a time-discrete setting with data remaining constant within each sensing cycle, this simplification can introduce significant errors, especially when dealing with long cycles, as real-world sensing data often changes continuously. In this paper, we go from fine-grained completion, i.e., the subdivision of sensing cycles into minimal time units, towards a more accurate, time-continuous completion. We first introduce Deep Matrix Factorization (DMF) as a neural network-enabled framework and enhance it with a Recurrent Neural Network (RNN-DMF) to capture temporal correlations in these finer time slices. To further deal with the continuous data, we propose TIME-DMF, which captures temporal information across unequal intervals, enabling time-continuous completion. Additionally, we present the Query-Generate (Q-G) strategy within TIME-DMF to model the infinite states of continuous data. Extensive experiments across five types of sensing tasks demonstrate the effectiveness of our models and the advantages of time-continuous completion. Copyright © 2024, The Authors. All rights reserved.

关键词： Budget control

AWEQ: Post-Training Quantization with Activation-Weight Equalization for Large Language Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Baisong Wang, Xingwang Xu, Haixiao School of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University China

Large language models(LLMs) excellent performance across a variety of tasks, but they come with significant computational and storage costs. Quantizing these models is an effective way to alleviate this issue. However, existing methods struggle to strike a balance between model accuracy and hardware efficiency. This is where we introduce AWEQ, a post-training method that requires no additional training overhead. AWEQ excels in both ultra-low-bit quantization and 8-bit weight and activation (W8A8) quantization. There is an observation that weight quantization is less challenging than activation quantization. AWEQ transfers the difficulty of activation quantization to weights using channel equalization, achieving a balance between the quantization difficulties of both, and thereby maximizing performance. We have further refined the equalization method to mitigate quantization bias error, ensuring the robustness of the model. Extensive experiments on popular models such as LLaMA and OPT demonstrate that AWEQ outperforms all existing post-training quantization methods for large models. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical activation

Stochastic Block Models for Complex Network Analysis: A Survey

学校读者我要写书评

暂无评论

ACM Transactions on knowledge Discovery from Data 2025年第3期19卷 1-35页

作者： Liu, Xueyan Song, Wenzhuo Musial, Katarzyna Li, Yang Zhao, Xuehua Yang, Bo College of Computer Science and Technology Jilin University Changchun China School of Information Science and Technology Northeast Normal University Changchun China Complex Adaptive Systems Lab Data Science Institute University of Technology Sydney Sydney Australia Aviation University of the Air Force Changchun China School of Digital Media Shenzhen Institute of Information Technology Shenzhen China Key Laboratory of Symbolic Computation and Knowledge Engineer Jilin University Ministry of Education Changchun China

Complex networks enable to represent and characterize the interactions between entities in various complex systems which widely exist in the real world and usually generate vast amounts of data about all the elements, their behaviors and interactions over time. The studies concentrating on new network analysis approaches and methodologies are vital because of the diversity and ubiquity of complex networks. The stochastic block model (SBM), based on Bayesian theory, is a statistical network model. SBMs are essential tools for analyzing complex networks since SBMs have the advantages of interpretability, expressiveness, flexibility and generalization. Thus, designing diverse SBMs and their learning algorithms for various networks has become an intensively researched topic in network analysis and data mining. In this article, we review, in a comprehensive and in-depth manner, SBMs for different types of networks (i.e., model extensions), existing methods (including parameter estimation and model selection) for learning optimal SBMs for given networks and SBMs combined with deep learning. Finally, we provide an outlook on the future research directions of SBMs. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Complex Networks Structural Pattern Discovery Stochastic Block models Learning Methods of SBMs

AHMSA-Net: Adaptive Hierarchical Multi-Scale Attention Network for Micro-Expression Recognition

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Lijun Zhang, Yifan Tang, Weicheng Sun, Xinzhi Wang, Xiaomeng Li, Zhanshan College of Computer Science and Technology Jilin University Changchun Jilin130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun Jilin130012 China

Micro-expression recognition (MER) presents a significant challenge due to the transient and subtle nature of the motion changes involved. In recent years, deep learning methods based on attention mechanisms have made some breakthroughs in MER. However, these methods still suffer from the limitations of insufficient feature capture and poor dynamic adaptation when coping with the instantaneous subtle movement changes of micro-expressions. Therefore, in this paper, we design an Adaptive Hierarchical Multi-Scale Attention Network (AHMSA-Net) for MER. Specifically, we first utilize the onset and apex frames of the micro-expression sequence to extract threedimensional (3D) optical flow maps, including horizontal optical flow, vertical optical flow, and optical flow strain. Subsequently, the optical flow feature maps are inputted into AHMSA-Net, which consists of two parts: an adaptive hierarchical framework and a multi-scale attention mechanism. Based on the adaptive downsampling hierarchical attention framework, AHMSA-Net captures the subtle changes of micro-expressions from different granularities (fine and coarse) by dynamically adjusting the size of the optical flow feature map at each layer. Based on the multi-scale attention mechanism, AHMSA-Net learns micro-expression action information by fusing features from different scales (channel and spatial). These two modules work together to comprehensively improve the accuracy of MER. Additionally, rigorous experiments demonstrate that the proposed method achieves competitive results on major micro-expression databases, with AHMSA-Net achieving recognition accuracy of up to 78.21% on composite databases (SMIC, SAMM, CASMEII) and 77.08% on the CASME3 database. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep learning