检索结果-内蒙古大学图书馆

Interpreting dense retrieval as mixture of topics

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhan, Jingtao Mao, Jiaxin Liu, Yiqun Guo, Jiafeng Zhang, Min Ma, Shaoping Department of Computer Science and Technology Institute for Artificial Intelligence Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success. Therefore, in this work, we conduct an interpretation study of recently proposed DR models. Specifically, we first discretize the embeddings output by the document and query encoders. Based on the discrete representations, we analyze the attribution of input tokens. Both qualitative and quantitative experiments are carried out on public test collections. Results suggest that DR models pay attention to different aspects of input and extract various high-level topic representations. Therefore, we can regard the representations learned by DR models as a mixture of high-level topics. Copyright © 2021, The Authors. All rights reserved.

关键词： Mixtures

Classification Based on Multilayer Extreme Learning Machine for Motor Imagery Task from EEG Signals

学校读者我要写书评

暂无评论

Procedia Computer science 2016年 88卷 176-184页

作者： Lijuan Duan Menghu Bao Jun Miao Yanhui Xu Juncheng Chen College of Computer Science and Technology Beijing University of Technology Beijing 100124 China Beijing Key Laboratory of Trusted Computing National Engineering Laboratory for Critical Technologies of Information Security Classified Protection Beijing 100124 China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing 100190 China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data Beijing 100124 China

Classification of motor imagery electroencephalogram (EEG) is one of the most important technologies for BCI. To improve the accuracy, this paper introduces a classification system based on Multilayer Extreme Learning Machine (ML-ELM). In the system, the combination of PCA and LDA is chosen as the method of feature extraction and the ML-ELM is used to classify. The ML-ELM has not only the advantage which ELM has but also better performance than ELM. In the experiment, our method is compared with the methods based on ELM, such as kernel-ELM, Constrained-ELM and V-ELM, and some state-of–the-art methods on the same dataset. The experimental results show that ML-ELM is much more suitable for motor imagery EEG data and has better performance than the others.

关键词： Electroencephalogram Classification Motor Imagery Extreme Learning Machine Multilayer Extreme Learning Machine

Learning discrete representations via constrained clustering for effective and efficient dense retrieval

学校读者我要写书评

暂无评论

arXiv 2021年

Dense Retrieval (DR) has achieved state-of-the-art first-stage ranking effectiveness. However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space. Therefore, we present RepCONC, a novel retrieval model that learns discrete Representations via CONstrained Clustering. RepCONC jointly trains dual-encoders and the Product Quantization (PQ) method to learn discrete document representations and enables fast approximate NNS with compact indexes. It models quantization as a constrained clustering process, which requires the document embeddings to be uniformly clustered around the quantization centroids and supports end-to-end optimization of the quantization method and dual-encoders. We theoretically demonstrate the importance of the uniform clustering constraint in RepCONC and derive an efficient approximate solution for constrained clustering by reducing it to an instance of the optimal transport problem. Besides constrained clustering, RepCONC further adopts a vector-based inverted file system (IVF) to support highly efficient vector search on CPUs. Extensive experiments on two popular ad-hoc retrieval benchmarks show that RepCONC achieves better ranking effectiveness than competitive vector quantization baselines under different compression ratio settings. It also substantially outperforms a wide range of existing retrieval models in terms of retrieval effectiveness, memory efficiency, and time efficiency. Copyright © 2021, The Authors. All rights reserved.

关键词： Signal encoding

A quantum-inspired classical algorithm for separable non-negative matrix factorization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chen, Zhihuai Li, Yinan Sun, Xiaoming Yuan, Pei Zhang, Jialin CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Centrum Wiskunde & Informatica and QuSoft Science Park 123 Amsterdam1098XG Netherlands

Non-negative Matrix Factorization (NMF) asks to decompose a (entry-wise) non-negative matrix into the product of two smaller-sized nonnegative matrices, which has been shown intractable in general. In order to overcome this issue, separability assumption is introduced which assumes all data points are in a conical hull. This assumption makes NMF tractable and is widely used in text analysis and image processing, but still impractical for huge-scale datasets. In this paper, inspired by recent development on dequantizing techniques, we propose a new classical algorithm for separable NMF problem. Our new algorithm runs in polynomial time in the rank and logarithmic in the size of input matrices, which achieves an exponential speedup in the low-rank setting. Copyright © 2019, The Authors. All rights reserved.

关键词： Non-negative matrix factorization

Account matching across heterogeneous networks

学校读者我要写书评

暂无评论

Account matching across heterogeneous networks

International Conference on Game Theory for networks, GameNets

作者： Qiang Liu Jingyuan Li Yuanzhuo Wang Guoliang Xing Yan Ren University of Chinese Academy of Sciences Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing China

ISBN: (纸本)9781479979035

Due to the development of web services, many social network sites, as well as online shopping sites have been booming in the past decade, where it is a common phenomenon that people are likely to use multiple services at the same time. Discovering the correspondence between accounts of a same individual is a crucial prerequisite for many interesting cross network applications, such as improving the recommendation performance of the online shopping sites by using extra information from social network services. In this paper, we propose a gametheoretic method to identify correlation accounts of individuals between social network sites and online shopping sites with stable matching model, incorporating accounts profiles as well as historical behaviors. The results show that our method identifies up to 70% of correlation accounts between Facebook and eBay, one of the most popular social network sites and online shopping sites in the world, respectively.

关键词： Games Lead

ProtoEM: A Prototype-Enhanced Matching Framework for Event Relation Extraction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Zhilei Li, Zixuan Xu, Daozhu Bai, Long Jin, Cheng Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China State Key Laboratory of Geo-Information Engineering Xi’an710054 China Xi’an Research Institute of Surveying and Mapping Xi’an710054 China

Event Relation Extraction (ERE) aims to extract multiple kinds of relations among events in texts. However, existing methods singly categorize event relations as different classes, which are inadequately capturing the intrinsic semantics of these relations. To comprehensively understand their intrinsic semantics, in this paper, we obtain prototype representations for each type of event relation and propose a Prototype-Enhanced Matching (ProtoEM) framework for the joint extraction of multiple kinds of event relations. Specifically, ProtoEM extracts event relations in a two-step manner, i.e., prototype representing and prototype matching. In the first step, to capture the connotations of different event relations, ProtoEM utilizes examples to represent the prototypes corresponding to these relations. Subsequently, to capture the interdependence among event relations, it constructs a dependency graph for the prototypes corresponding to these relations and utilized a Graph Neural network (GNN)-based module for modeling. In the second step, it obtains the representations of new event pairs and calculates their similarity with those prototypes obtained in the first step to evaluate which types of event relations they belong to. Experimental results on the MAVEN-ERE dataset demonstrate that the proposed ProtoEM framework can effectively represent the prototypes of event relations and further obtain a significant improvement over baseline models. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Group RandAugment: Video Augmentation for Action Recognition 5

学校读者我要写书评

暂无评论

Group RandAugment: Video Augmentation for Action Recognition

5th International Conference on data science and Information technology, DSIT 2022

作者： An, Fengmin Zhang, Bingbing Wang, Zhenwei Dong, Wei Zhang, Jianxin School of Computer Science and Engineering Dalian Minzu University Dalian China Institute of Machine Intelligence and Bio-computing Dalian Minzu University Dalian China SEAC Key Lab of Big Data Applied Technology Dalian Minzu University Dalian China School of Information and Communication Engineering Dalian University of Technology Dalian China

ISBN: (数字)9781665498685

ISBN: (纸本)9781665498685

data augmentation, as a critical strategy in deep learning, well improves the sample diversity for network training, leading to the obvious improvement of model generalization ability. Besides, automatic data augmentation, while sparking in image tasks, has attracted too little attention in video recognition task. Therefore, this work explores a novel group random augmentation (GRA) that automatically augments video data for recognition. GRA first collects 21 augmentation transformations to enrich the sample diversity, and then divides these transformations into four groups (i.e., pixel-transform, rigidtransform, erasing-transform, environment-transform) to reduce the excessive regularization caused by similar augmentation. To reduce the computational cost of finding the optimal setting, GRA adopts the combination form to select the optimal situation. For frames in the same video clip, GRA uses synchronous GRA. Additionally, the proposed GRA can be integrated into any existing video frameworks. To prove the effectiveness of GRA, we conduct experiments on two commonly used video action recognition benchmarks (Something-Something V1 & V2) and three typical frameworks (TSM, GSM, and TEA), whose results demonstrate GRA can improve performance in all cases without adding additional computational cost. © 2022 IEEE.

关键词： Deep learning

Continuous Distributed Processing of Software Defined Radar

学校读者我要写书评

暂无评论

Continuous Distributed Processing of Software Defined Radar

IEEE International Conference on Radar

作者： Bing Li Qiang Qiu Shiqi Gong Yongjun Liu Yu Lei CAS Key Lab of Network Data Science and Technology Chinese Academy of Sciences Institute of Computing Technology Beijing China State Key Laboratory of Internet of Things for Smart City University of Macau Macau China National Laboratory of Radar Signal Processing Xidian University Xi'an China Golaxy Data Technology Co. Ltd. Beijing China

ISBN: (纸本)9781665468893

Software-defined radar has been an active research field for more than ten years. However, the low performance and low scalability of the traditional processing techniques of SDR make it hard to deal with complex radar tasks. The stream processing engine is a software that supports low latency and high scalability distributed data processing. It is widely used in log, image, and video processing scenarios but rarely used in radar applications. This paper reviews processing software-defined radar data by using the stream processing engine, and we illustrate the differences between processing log data and radar data. Furthermore, we discuss some optimizations for stream processing engines to get better performance in the radar data processing.

关键词： Protocols Scalability Streaming media Radar imaging data processing Software Hardware

Reverse Perspective network for Perspective-Aware Object Counting

学校读者我要写书评

暂无评论

Reverse Perspective Network for Perspective-Aware Object Cou...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yifan Yang Guorong Li Zhe Wu Li Su Qingming Huang Nicu Sebe School of Computer Science and Technology UCAS Beijing China Key Lab of Big Data Mining and Knowledge Management UCAS Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China University of Trento Trento Italy

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

One of the critical challenges of object counting is the dramatic scale variations, which is introduced by arbitrary perspectives. We propose a reverse perspective network to solve the scale variations of input images, instead of generating perspective maps to smooth final outputs. The reverse perspective network explicitly evaluates the perspective distortions, and efficiently corrects the distortions by uniformly warping the input images. Then the proposed network delivers images with similar instance scales to the regressor. Thus the regression network doesn't need multi-scale receptive fields to match the various scales. Besides, to further solve the scale problem of more congested areas, we enhance the corresponding regions of ground-truth with the evaluation errors. Then we force the regressor to learn from the augmented ground-truth via an adversarial process. Furthermore, to verify the proposed model, we collected a vehicle counting dataset based on Unmanned Aerial Vehicles (UAVs). The proposed dataset has fierce scale variations. Extensive experimental results on four benchmark datasets show the improvements of our method against the state-of-the-arts.

关键词： Distortion Training Feature extraction Estimation Convolution Kernel Adaptation models