检索结果-内蒙古大学图书馆

Multi-modal chorus recognition for improving song search

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Jiaan Li, Zhixu Gu, Binbin Zhang, Tingyi Liu, Qingsheng Chen, Zhigang School of Computer Science and Technology Soochow University Suzhou China iFLYTEK Research Suzhou China State Key Laboratory of Cognitive Intelligence iFLYTEK Hefei China University of California Irvine United States Anhui Toycloud Technology Hefei China

We discuss a novel task, Chorus Recognition, which could potentially benefit downstream tasks such as song search and music summarization. Different from the existing tasks such as music summarization or lyrics summarization relying on single-modal information, this paper models chorus recognition as a multi-modal one by utilizing both the lyrics and the tune information of songs. We propose a multi-modal Chorus Recognition model that considers diverse features. Besides, we also create and publish the first Chorus Recognition dataset containing 627 songs for public use. Our empirical study performed on the dataset demonstrates that our approach outperforms several baselines in chorus recognition. In addition, our approach also helps to improve the accuracy of its downstream task - song search by more than 10.6%. Copyright © 2021, The Authors. All rights reserved.

关键词： Modal analysis

Dynamic Task Offloading with Minority Game for Internet of Vehicles in Cloud-Edge Computing

学校读者我要写书评

暂无评论

Dynamic Task Offloading with Minority Game for Internet of V...

IEEE International Conference on Web Services (ICWS)

作者： Bowen Shen Xiaolong Xu Fei Dai Lianyong Qi Xuyun Zhang Wanchun Dou School of Computer and Software Nanjing University of Information Science and Technology Nanjing China School of Big Data and Intelligence Engineering Southwest Forestry University Kunming China School of Information Science and Engineering Qufu Normal University China Macquaire University Australia State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (数字)9781728187860

ISBN: (纸本)9781728187877

With the advent of the Internet of Vehicles (IoV), drivers are now provided with diverse time-sensitive vehicular services that usually require a large scale of computation. As civilian vehicles are generally insufficient in computational resources, their service requests are offloaded to cloud data centers and edge computing devices (ECDs) with ample computational resources to enhance the quality of service (QoS). However, ECDs are often overloaded with excessive service requests. In addition, as the network conditions and service compositions are complicated and dynamic, the centralized control of ECDs is hard to achieve. To tackle these challenges, a dynamic task offloading method with minority game (MG) in cloud-edge computing, named DOM, is proposed in this paper. Technically, MG is an effective tool with a distributed mechanism which can minimize the dependency on centralized control in resource allocation. In the MG, reinforcement learning (RL) is applied to optimize the distributed decision-making of participants. Finally, with a real-world dataset of IoV services, the effectiveness and adaptability of DOM are evaluated.

关键词： Cloud computing Games Quality of service Reinforcement learning Space exploration Task analysis Vehicle dynamics

SRH-Net: Stacked recurrent hourglass network for stereo matching

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Du, Hongzhi Li, Yanyan Sun, Yanbiao Zhu, Jigui Tombari, Federico State Key Laboratory of Precision Measuring Technology and Instruments Tianjin University Tianjin300072 China Dept. Computer Science Technical University of Munich Munich Germany Google Inc.

The cost aggregation strategy shows a crucial role in learning-based stereo matching tasks, where 3D convolutional filters obtain state of the art but require intensive computation resources, while 2D operations need less GPU memory but are sensitive to domain shift. In this paper, we decouple the 4D cubic cost volume used by 3D convolutional filters into sequential cost maps along the direction of disparity instead of dealing with it at once by exploiting a recurrent cost aggregation strategy. Furthermore, a novel recurrent module, Stacked Recurrent Hourglass (SRH), is proposed to process each cost map. Our hourglass network is constructed based on Gated Recurrent Units (GRUs) and down/upsampling layers, which provides GRUs larger receptive fields. Then two hourglass networks are stacked together, while multi-scale information is processed by skip connections to enhance the performance of the pipeline in textureless areas. The proposed architecture is implemented in an end-to-end pipeline and evaluated on public datasets, which reduces GPU memory consumption by up to 56.1% compared with PSMNet using stacked hourglass 3D CNNs without the degradation of accuracy. Then, we further demonstrate the scalability of the proposed method on several high-resolution pairs, while previously learned approaches often fail due to the memory constraint. The code is released at https://***/hongzhidu/SRHNet. © 2021, CC BY.

关键词： Convolution

A novel approach for air quality inference and prediction based on DBU-LSTM 3rd

学校读者我要写书评

暂无评论

A novel approach for air quality inference and prediction ba...

3rd APWeb and WAIM Joint Conference on Web and Big Data, APWeb-WAIM 2019

作者： Ge, Liang Zhou, Aoli Liu, Junling Li, Hang College of Computer Science Chongqing University Chongqing China Chongqing Key Laboratory of Software Theory and Technology Chongqing China

ISBN: (纸本)9783030260712

The inference and prediction of fine-grained air quality are two important directions in urban air computing. Solving these two problems can provide useful information for urban environmental governance and residents' health improvement. In this paper, we propose a general approach to solve these two problems with one model, while most other existing works use different models to solve them. Our model is based on deep bidirectional and unidirectional long short-term memory (DBU-LSTM) neural network, which can capture bidirectional temporal dependencies and spatial correlation from time series data containing spatial information. To infer and predict the air quality of the target region, we use the historical meteorological data of the target region and the historical air quality data of regions which are similar to the target. Urban heterogeneous data such as point of interest (POI) and road network are used to evaluate the similarities between urban regions. We also use a tensor decomposition method to complete the missing historical air quality data onto monitoring stations, which reduces the error of our model. We evaluated our approach on real data sources obtained in Beijing, and the results show its advantages over recent literature. © 2019, Springer Nature Switzerland AG.

关键词： Forecasting

Associative memories via predictive coding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Salvatori, Tommaso Song, Yuhang Hong, Yujian Frieder, Simon Sha, Lei Xu, Zhenghua Bogacz, Rafal Lukasiewicz, Thomas Department of Computer Science University of Oxford United Kingdom State Key Laboratory Hebei University of Technology Tianjin China Mrc Brain Network Dynamics Unit University of Oxford United Kingdom

Associative memories in the brain receive and store patterns of activity registered by the sensory neurons, and are able to retrieve them when necessary. Due to their importance in human intelligence, computational models of associative memories have been developed for several decades now. They include autoassociative memories, which allow for storing data points and retrieving a stored data point s when provided with a noisy or partial variant of s, and heteroassociative memories, able to store and recall multi-modal data. In this paper, we present a novel neural model for realizing associative memories, based on a hierarchical generative network that receives external stimuli via sensory neurons. This model is trained using predictive coding, an error-based learning algorithm inspired by information processing in the cortex. To test the capabilities of this model, we perform multiple retrieval experiments from both corrupted and incomplete data points. In an extensive comparison, we show that this new model outperforms in retrieval accuracy and robustness popular associative memory models, such as autoencoders trained via backpropagation, and modern Hopfield networks. In particular, in completing partial data points, our model achieves remarkable results on natural image datasets, such as ImageNet, with a surprisingly high accuracy, even when only a tiny fraction of pixels of the original images is presented. Furthermore, we show that this method is able to handle multi-modal data, retrieving images from descriptions, and vice versa. We conclude by discussing the possible impact of this work in the neuroscience community, by showing that our model provides a plausible framework to study learning and retrieval of memories in the brain, as it closely mimics the behavior of the hippocampus as a memory index and generative model. Copyright © 2021, The Authors. All rights reserved.

关键词： Associative processing

Analysis of Commonly and Specifically Dysregulated Pathways in Three Women Cancers

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2018年第5期27卷 1043-1049页

作者： LIU Xiyang AN Yingying YU Baoguo QIN Guimin School of Software Xidian University School of Computer Science and Technology Xidian University State Key Laboratory of Satellite Navigation System and Equipment Technology

Breast, ovarian and endometrial cancer are three most prevalent gynaecological malignancies. Identifying their common and specific biomarkers is significant for cancer prediction and therapy in females. We propose a method to identify dysregulated pathways in cancer through scoring pathways based on the molecular interaction data and genomic data. Commonly and specifically dysregulated pathways are analyzed across the above three female cancers, which have not been studied as a whole to the best of our knowledge. Our results demonstrate that all the three cancers have close relationships with Type II diabetes and cell cycle-related biology processes. Breast cancer is specifically related to immune system while ovarian cancer and endometrial cancer are associated with blood vascular-related systems such as renin-angiotensin system and coagulation system. In addition, dysregulated pathways are used to predict potential driver genes effectively according to their topological structure and biological information.

关键词： Dysregulated pathway Female cancers Driver gene

Advanced Maximal Biclique Enumeration on GPUs Using Bitmaps

学校读者我要写书评

暂无评论

IEEE Transactions on computers 2025年

作者： Pan, Zhe He, Shuibing Li, Xu Zhang, Xuechen Wang, Rui Yin, Yanlong Chen, Gang Zhejiang University State Key Laboratory of Blockchain and Data Security Hangzhou310027 China Zhejiang University College of Computer Science and Technology Hangzhou310027 China Hangzhou310051 China Washington State University Vancouver School of Engineering and Computer Science VancouverWA98686 United States

Maximal biclique enumeration (MBE) in bipartite graphs is an important problem in data mining with many real-world applications. Parallel MBE algorithms for GPUs are needed for MBE acceleration leveraging its many computing cores. However, enumerating maximal bicliques using GPUs has three main challenges including large memory requirement, thread divergence, and load imbalance. In this paper, we propose GMBE+, an advanced GPU solution for the MBE problem. To overcome the challenges, we design (1) a node-reuse approach to reduce GPU memory usage with advanced node pruning, (2) a bitmap-based set intersection approach to minimize thread divergence, and (3) a load-aware task scheduling framework to achieve load balance among threads within GPU warps, facilitated by a novel set union approach. Our experiments reveal that GMBE+ is 1.2× faster than the latest GPU-based MBE algorithm GMBE on average when running on the same NVIDIA A100 GPU. © 1968-2012 IEEE.

关键词： Memory architecture

APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Zhuguanyu Zhang, Jiayi Chen, Jiaxin Guo, Jinyang Huang, Di Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University China School of Computer Science and Engineering Beihang University Beijing China School of Artificial Intelligence Beihang University Beijing China

Vision Transformers (ViTs) have become one of the most commonly used backbones for vision tasks. Despite their remarkable performance, they often suffer significant accuracy drops when quantized for practical deployment, particularly by post-training quantization (PTQ) under ultra-low bits. Recently, reconstruction-based PTQ methods have shown promising performance in quantizing Convolutional Neural Networks (CNNs). However, they fail when applied to ViTs, primarily due to the inaccurate estimation of output importance and the substantial accuracy degradation in quantizing post-GELU activations. To address these issues, we propose APHQ-ViT, a novel PTQ approach based on importance estimation with Average Perturbation Hessian (APH). Specifically, we first thoroughly analyze the current approximation approaches with Hessian loss, and propose an improved average perturbation Hessian loss. To deal with the quantization of the post-GELU activations, we design an MLP Reconstruction (MR) method by replacing the GELU function in MLP with ReLU and reconstructing it by the APH loss on a small unlabeled calibration set. Extensive experiments demonstrate that APHQ-ViT using linear quantizers outperforms existing PTQ methods by substantial margins in 3-bit and 4-bit across different vision tasks. The source code is available at https://***/GoatWu/APHQ-ViT. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

DIAS: A Dataset and Benchmark for Intracranial Artery Segmentation in DSA sequences

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Wentao Tian, Tong Wang, Lemeng Xu, Weijin Li, Lei Li, Haoyuan Zhao, Wenyi Tian, Siyu Pan, Xipeng Deng, Yiming Gao, Feng Yang, Huihua Wang, Xin Su, Ruisheng School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment School of Aeronautics and Astronautics Dalian University of Technology Dalian China Department of Interventional Neuroradiology Beijing Tiantan Hospital Capital Medical University Beijing China Ultrasonic Department The Fourth Hospital of Hebei Medical University Hebei Tumor Hospital Shijiazhuang China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Department of Radiology The Netherlands Cancer Institute Amsterdam Netherlands Department of Radiology & Nuclear Medicine Erasmus MC University Medical Center Rotterdam Netherlands Medical Image Analysis group Department of Biomedical Engineering Eindhoven University of Technology Eindhoven Netherlands

The automated segmentation of Intracranial Arteries (IA) in Digital Subtraction Angiography (DSA) plays a crucial role in the quantification of vascular morphology, significantly contributing to computer-assisted stroke research and clinical practice. Current research primarily focuses on the segmentation of single-frame DSA using proprietary datasets. However, these methods face challenges due to the inherent limitation of single-frame DSA, which only partially displays vascular contrast, thereby hindering accurate vascular structure representation. In this work, we introduce DIAS, a dataset specifically developed for IA segmentation in DSA sequences. We establish a comprehensive benchmark for evaluating DIAS, covering full, weak, and semi-supervised segmentation methods. Specifically, we propose the vessel sequence segmentation network, in which the sequence feature extraction module effectively captures spatiotemporal representations of intravascular contrast, achieving intracranial artery segmentation in 2D+Time DSA sequences. For weakly-supervised IA segmentation, we propose a novel scribble learning-based image segmentation framework, which, under the guidance of scribble labels, employs cross pseudo-supervision and consistency regularization to improve the performance of the segmentation network. Furthermore, we introduce the random patch-based self-training framework, aimed at alleviating the performance constraints encountered in IA segmentation due to the limited availability of annotated DSA data. Our extensive experiments on the DIAS dataset demonstrate the effectiveness of these methods as potential baselines for future research and clinical applications. The dataset and code are publicly available at https://***/10.5281/zenodo.11396520 and https://***/lseventeen/DIAS. Copyright © 2023, The Authors. All rights reserved.

关键词： Image segmentation