检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yan, Dawei Li, Pengcheng Li, Yang Chen, Hao Chen, Qingguo Luo, Weihua Dong, Wei Yan, Qingsen Zhang, Haokui Shen, Chunhua School of Cybersecurity Northwestern Polytechnical University China AI Business Alibaba Group China College of Computer Science and Technology Zhejiang University China College of Information and Control Engineering Xi’an University of Architecture and Technology China School of Computer Science Northwestern Polytechnical University China

ISBN: (纸本)157735897X

Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the connector and enhancing the language model component, while neglecting improvements to the vision encoder itself. In contrast, we propose Text Guided LLaVA (TG-LLaVA) in this paper, which optimizes VLMs by guiding the vision encoder with text, offering a new and orthogonal optimization direction. Specifically, inspired by the purpose-driven logic inherent in human behavior, we use learnable latent embeddings as a bridge to analyze textual instruction and add the analysis results to the vision encoder as guidance, refining it. Subsequently, another set of latent embeddings extracts additional detailed text-guided information from high-resolution local patches as auxiliary information. Finally, with the guidance of text, the vision encoder can extract text-related features, similar to how humans focus on the most relevant parts of an image when considering a question. This results in generating better answers. Experiments on various datasets validate the effectiveness of the proposed method. Remarkably, without the need for additional training data, our proposed method can bring more benefits to the baseline (LLaVA-1.5) compared with other concurrent methods. Furthermore, the proposed method consistently brings improvement in different settings. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the Characteristics of Wordle Mini-Game Based on GA-BP Neural Network and K-Means Clustering Algorithm

Research on the Characteristics of Wordle Mini-Game Based on...

引用

Image Processing and computer Applications (ICIPCA), IEEE International Conference on

作者： Fan Ju Yongwei Ma Shengjie Yao College of Computer Science and Technology Shandong University of Architecture Jinan Shandong China

First, an ARIMA-based prediction model for the number of reported outcomes at future dates was developed. After processing the collected data, the smoothness of the number of reported outcomes was verified, and an intrinsic trend analysis of the data was performed to demonstrate the validity of the ARIMA model for predicting the number of reported outcomes at future dates, and the parameters of ARIMA were fitted using historical data to determine the final prediction model as ARIMA. secondly, one prediction model based on the GA-BP neural network algorithm was developed for the relevant percentages of future dates. At the same time, the GA algorithm was introduced for optimization to obtain the optimal initialization of the BP neural network. We use the frequency of letter occurrences together with the date as the input word feature and the correlation percentage as the output, and the prediction results are within the valid interval. Third, the word difficulty classification model and word scoring model were built based on the improved k-means clustering algorithm and PCA, respectively. To improve the drawback that the k- value in k-means algorithm cannot be determined, were introduced CH value, DB value. as indicators to evaluate the k- value, and combined the entropy weight method with Topsis to get the optimal number of clusters as 3 and the clustering index as the correlation percentage, and then applied the k-means algorithm to classify the words. We used the word difficulty ratio to determine the difficulty coefficient of each category, and also combined the score interval of each category obtained by PCA. Fourth, we found that the Wordle trivia game has the characteristic of viral spread in blocks, and more and more players choose the difficult mode as time goes by.

关键词：

来源：评论

学校读者我要写书评

暂无评论

X-ray Prohibited Items Recognition Based on Improved YOLOv5 20th

X-ray Prohibited Items Recognition Based on Improved YOLOv5

引用

Proceedings of the 20th Web Information Systems and Applications Conference, WISA 2023

作者： Li, Wei Li, Xiang Liu, Wanxin Liu, Zhihan Jia, Jing Li, Jiayi College of Computer Science and Technology Harbin Engineering University Harbin150001 China Faculty of Arts Design and Architecture School of Built Environment The University of New South Wales SydneyNSW2052 Australia School of Art and Design Jiangsu Institute of Technology Changzhou213001 China

ISBN: (纸本)9789819962211

Safety inspections play a crucial role in maintaining social stability and protecting the safety of public life and property. The X-ray security detector is an important scanning device in the security inspection of public transportation and express packages. However, current intelligent detection algorithms face problems such as a limited dataset of prohibited items, the imbalanced distribution of categories, variable target postures, and varying target scales, leading to the occurrence of false positives and missed detections. We propose an improved X-ray prohibited item recognition algorithm, named YOLOv5s-DAB. A deformable convolution module is designed to address the characteristics of different scales and postures of the same prohibited item in different samples. Besides, a multi-scale feature enhancement module SA-ASPP based on attention mechanism is designed, which can handle the problem of overlapping occlusion of multi-scale contraband. Experimental results in the real X-ray prohibited items dataset demonstrate that our model outperforms state-of-the-art methods in terms of detection accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

SaaP: Rearchitect SoC-as-a-Processor to Orchestrate Hardware Heterogeneity

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Jin, Pengwei Fan, Zhe Zhao, Yongwei Du, Zidong Guo, Hongrui Nan, Ziyuan Hao, Yifan Li, Chongxiao Ma, Tianyun Zhang, Zhenxing Li, Xiaqing Li, Wei Hu, Xing Guo, Qi Xu, Zhiwei Chen, Tianshi Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Cambricon Technologies Beijing China CAS SKL of Processors ICT Beijing100190 China Shanghai200235 China Hefei230027 China Beijing Jiaotong University Department of Computer Science and Technology Beijing100044 China

Due to the end of Moore’s Law and Dennard Scaling, Domain-Specific Accelerators (DSAs) have come to a Cambrian explosion. Especially when advancing into the intelligent era, more and more DSAs are integrated into Systemon-Chips (SoCs) as intellectual property (IP) blocks to provide high performance and efficiency. Currently, IPs usually expose IP-dependent hardware interfaces, requiring SoCs to manage them as isolated devices with software running on the host CPU. However, such software-managed heterogeneity in CPU-centric SoCs leads to low IP utilization. This inefficiency arises from the dependence on software optimization, coupled with the control and data exchange overheads. To improve IP utilization of heterogeneous SoCs, in this paper, we rearchitect the SoC as a processor (i.e., SaaP) to orchestrate hardware heterogeneity. SaaP features an orchestration pipeline where DSAs are integrated as execution units and managed directly by the hardware pipeline to conceal the hardware heterogeneity from software. Moreover, SaaP re-designs the register file and data paths to implement an IP-level data-forwarding mechanism, avoiding the costly control and data exchange in the CPU-centric execution model. block data dependence among different DSAs is carefully resolved to exploit mixed-level parallelism and inter-IP data exchange. SaaP abstracts tasks as mixed-scale instructions, where each instruction can be mapped to different IPs. Experimental results show that compared against Xavier on six fully software-optimized benchmarks from different domains, SaaP-rearchitected Xavier achieves a 2.08× speedup, with an 8.21% area reduction and only 2.98% increase in power consumption. © 1982-2012 IEEE.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Towards High-quality HDR Deghosting with Conditional Diffusion Models

arXiv

引用

arXiv 2023年

作者： Yan, Qingsen Hu, Tao Sun, Yuan Tang, Hao Zhu, Yu Dong, Wei Van Gool, Luc Zhang, Yanning School of Computer Science Northwestern Polytechnical University China School of Computer Science Xi’an University of Architecture and Technology China School of Computer Science ETH Zurich Switzerland

High Dynamic Range (HDR) images can be recovered from several Low Dynamic Range (LDR) images by existing Deep Neural Networks (DNNs) techniques. Despite the remarkable progress, DNN-based methods still generate ghosting artifacts when LDR images have saturation and large motion, which hinders potential applications in real-world scenarios. To address this challenge, we formulate the HDR deghosting problem as an image generation that leverages LDR features as the diffusion model’s condition, consisting of the feature condition generator and the noise predictor. Feature condition generator employs attention and Domain Feature Alignment (DFA) layer to transform the intermediate features to avoid ghosting artifacts. With the learned features as conditions, the noise predictor leverages a stochastic iterative denoising process for diffusion models to generate an HDR image by steering the sampling process. Furthermore, to mitigate semantic confusion caused by the saturation problem of LDR images, we design a sliding window noise estimator to sample smooth noise in a patch-based manner. In addition, an image space loss is proposed to avoid the color distortion of the estimated HDR results. We empirically evaluate our model on benchmark datasets for HDR imaging. The results demonstrate that our approach achieves state-of-the-art performances and well generalization to real-world images. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Boosting Urban Prediction via Addressing Spatial-Temporal Distribution Shift

Boosting Urban Prediction via Addressing Spatial-Temporal Di...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Xuanming Hu Wei Fan Kun Yi Pengfei Wang Yuanbo Xu Yanjie Fu Pengyang Wang School of Computing and Augmented Intelligence Arizona State University Tempe USA SKL-IOTSC University of Macau Department of CIS SKL-IOTSC University of Macau Macau S.A.R. China School of Computer Science and Technology Beijing Institute of Technology Beijing China Computer Network Information Center Chinese Academy of Sciences Beijing China College of Computer Science and Technology Jilin University Changchun China

Urban prediction tasks that aim to model the complicated spatial and temporal patterns of urban indicators (such as weather, vehicle charging demand, etc.) for accurate prediction, have been increasingly important in constructing smart cities and accelerating the urbanization process in the modern era. However, most existing works of urban prediction have only concentrated on spatial and temporal correlations, but ignored the effect of distribution shift from spatial and temporal perspectives; this could largely hinder the performance of urban prediction tasks. In order to solve this problem, in this paper, we propose a Shift-Aware Urban Prediction (SAUP) framework to eliminate the inherent shift effect among spatial-temporal urban time series data. Specifically, SAUP starts with a Shift Elimination Module, built upon our proposed Spatial-Temporal Attention Flows (STAF) composed of invertible attentions and coupling layers of normalizing flows in order to transform the raw shifted data into a unified distribution to remove the spatiotemporal shift. After the shift effect is eliminated, the Correlation Processing Module of SAUP further captures the core correlations to learn spatiotemporal dependencies, in which topological correlations and geographic correlations are jointly learned by GCN and CNN based on pre-defined graphs and extracted POI information. In addition, SAUP includes a model-agnostic Forecasting Module, which can be employed as any forecasting architecture to accomplish the predictions. To recover the raw distribution information, the output of the Forecasting Module is further taken for the inverse transformation of the Shift Elimination Module to produce the final forecasts. We have conducted extensive experiments in the SAUP framework, coupled with six state-of-the-art spatiotemporal forecasting models on two real-world datasets. Experimental results have demonstrated the consistent improvements of SAUP over the baseline algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Deep Neural Network for Detecting Broken and Scattered Power Lines in Complex Aerial Images 3

A Deep Neural Network for Detecting Broken and Scattered Pow...

引用

3rd International Conference on Artificial Intelligence and computer Information technology, AICIT 2024

作者： Pei, Qiugen Lai, Yuxuan Wei, Nianxing Wu, Shiting Guangdong Power Grid Co. Ltd. Enterprise Architecture and Digitalization Department Guangzhou China Guangdong University of Technology Dept. School of Computer Science Guangzhou China Guangdong Power Grid Co. Ltd. Huizhou Boluo Power Supply Bureau Huizhou China

ISBN: (纸本)9798350365443

Object detection algorithms constitute a pivotal task in the realm of computer vision, aiming to precisely identify and locate objects within images across diverse scenarios. In power systems, especially in aerial images used to detect wire breaks or scattered anomalies, object detection faces significant challenges. The distribution of wires is often uneven, appearing in different sizes in high-resolution images, and the diversity of fault shapes and sizes makes it difficult for traditional object detection models to recognize accurately. Moreover, the detection of small targets also limits the precision of traditional methods. To address the issue of diversity in fault shapes and sizes in high-resolution images, which makes it difficult for traditional object detection models to recognize accurately, first, we collect fault images of wire breaks and scatter under common scenarios, constructing the 'EWF _detection' (Electric wire fault) dataset, and propose a Pyramid Multi-scale Object Detection Model, establishing the Hybrid Spatial Attention Pooling module, HSAP, which significantly enhances the multi-scale feature extraction capability. It not only improves the model's ability to focus on key features, but also suppresses unnecessary features, enhancing the expressiveness of the network, and effectively adapting to complex backgrounds, variable lighting conditions, and different line scales and directions for transmission line detection needs. This improvement makes our model perform exceptionally well in detecting rare faults in wires and accurately locate fault positions. These achievements provide reliable technical support for wire anomaly detection in the power industry and indicate a broad prospect of application in future power scenarios. Our method not only improves detection accuracy, but also maintains efficient detection speed, reducing reliance on a large number of fault line images. These advantages make our model an important technical tool for pow

关键词： Aerial photography

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Pedestrian Social Distancing Risk Alert System for COVID-19

引用

computer Systems science & Engineering 2023年第10期47卷 937-954页

作者： Zhihan Liu Xiang Li Siqi Liu Wei Li Xiangxu Meng Jing Jia College of Computer Science and Technology Harbin Engineering UniversityHarbin150001China Department of Clinical Laboratory Harbin Medical University Cancer HospitalHarbinHeilongjiang150081China Faculty of Arts Design and ArchitectureSchool of Built EnvironmentThe University of New South WalesSydneyNSW 2052Australia

The COVID-19 virus is usually spread by small droplets when talking,coughing and sneezing,so maintaining physical distance between people is necessary to slow the spread of the *** World Health Organization(WHO)recommends maintaining a social distance of at least six *** this paper,we developed a real-time pedestrian social distance risk alert system for COVID-19,whichmonitors the distance between people in real-time via video streaming and provides risk alerts to the person in charge,thus avoiding the problem of too close social distance between pedestrians in public *** design a lightweight convolutional neural network architecture to detect the distance between people more *** addition,due to the limitation of camera placement,the previous algorithm based on flat view is not applicable to the social distance calculation for cameras,so we designed and developed a perspective conversion module to reduce the image in the video to a bird’s eye view,which can avoid the error caused by the elevation view and thus provide accurate risk indication to the *** selected images containing only person labels in theCOCO2017 dataset to train our *** experimental results show that our network model achieves 82.3%detection accuracy and performs significantly better than other mainstream network architectures in the three metrics of Recall,Precision and mAP,proving the effectiveness of our system and the efficiency of our technology.

关键词： Convolutional neural network pedestrian detection social distancing COVID-19

来源：评论

学校读者我要写书评

暂无评论

IAAT: A Input-Aware Adaptive Tuning framework for Small GEMM 27

IAAT: A Input-Aware Adaptive Tuning framework for Small GEMM

引用

27th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2021

作者： Yao, Jianyu Shi, Boqian Xiang, Chunyang Jia, Haipeng Li, Chendi Cao, Hang Zhang, Yunquan Institute of Computing Technology Chinese Academy of Sciences SKL of Computer Architecture Beijing China University of Chinese Academy of Sciences Beijing China Indiana University BloomingtonIN United States

ISBN: (纸本)9781665408783

GEMM with the small size of input matrices is becoming widely used in many fields like HPC and machine learning. Although many famous BLAS libraries already supported small GEMM, they cannot achieve near-optimal performance. This is because the costs of pack operations are high and frequent boundary processing cannot be neglected. This paper proposes an input-aware adaptive tuning framework(IAAT) for small GEMM to overcome the performance bottlenecks in state-of-the-art implementations. IAAT consists of two stages, the install-time stage and the run-time stage. In the run-time stage, IAAT tiles matrices into blocks to alleviate boundary processing. This stage utilizes an input-aware adaptive tile algorithm and plays the role of runtime tuning. In the install-time stage, IAAT auto-generates hundreds of kernels of different sizes to remove pack operations. Finally, IAAT finishes the computation of small GEMM by invoking different kernels, which corresponds to the size of blocks. The experimental results show that IAAT gains better performance than other BLAS libraries on ARMv8 platform. © 2021 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Implementation of MapReduce parallel computing framework based on multi-data fusion sensors and GPU cluster

引用

Eurasip Journal on Advances in Signal Processing 2021年第1期2021卷 1-14页

作者： Chang, Dajun Li, Li Chang, Ying Qiao, Zhangquan College of Computer Science and Technology Changchun University of Science and Technology Changchun 130022 Jilin China School of Electrical Information Changchun University of Architecture and Civil Engineering Changchun 130604 Jilin China School of Computer Science and Engineering Jilin University of Architecture and Technology Changchun 130114 Jilin China

Nowadays, with the rapid growth of data volume, massive data has become one of the factors that plague the development of enterprises. How to effectively process data and reduce the concurrency pressure of data access has become the driving force for the continuous development of big data solutions. This article mainly studies the MapReduce parallel computing framework based on multiple data fusion sensors and GPU clusters. This experimental environment uses a Hadoop fully distributed cluster environment, and the entire programming of the single-source shortest path algorithm based on MapReduce is implemented in Java language. 8 ordinary physical machines are used to build a fully distributed cluster, and the configuration environment of each node is basically the same. The MapReduce framework divides the request job into several mapping tasks and assigns them to different computing nodes. After the mapping process, a certain intermediate file that is consistent with the final file format is generated. At this time, the system will generate several reduction tasks and distribute these files to different cluster nodes for execution. This experiment will verify the changes in the running time of the PSON algorithm when the size of the test data set gradually increases while keeping the hardware level and software configuration of the Hadoop platform unchanged. When the number of computing nodes increases from 2 to 4, the running time is significantly reduced. When the number of computing nodes continues to increase, the reduction in running time will become less and less significant. The results show that NESTOR can complete the basic workflow of MapReduce, and simplifies the process of user development of GPU positive tree order, which has a significant speedup for applications with large amounts of calculations. © 2021, The Author(s).

关键词： Data scheduling GPU cluster Load balancing MapReduce parallel computing Multi-data fusion sensor

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：