检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Mo, Hanlin Hao, Hongxiang Zhao, Guoying Center for Machine Vision and Signal Analysis University of Oulu Finland Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

Rotational motion blur caused by the circular motion of the camera or/and object is common in life. Identifying objects from images affected by rotational motion blur is challenging because this image degradation severely impacts image quality. Therefore, it is meaningful to develop image invariant features under rotational motion blur and then use them in practical tasks, such as object classification and template matching. This paper proposes a novel method to generate image moment invariants under general rotational motion blur and provides some instances. Further, we achieve their invariance to similarity transform. To the best of our knowledge, this is the first time that moment invariants for rotational motion blur have been proposed in the literature. We conduct extensive experiments on various image datasets disturbed by similarity transform and rotational motion blur to test these invariants’ numerical stability and robustness to image noise. We also demonstrate their performance in image classification and handwritten digit recognition. Current state-of-the-art blur moment invariants and deep neural networks are chosen for comparison. Our results show that the moment invariants proposed in this paper significantly outperform other features in various tasks. 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

Design of Control Circuit for Active Metasurface Based on Varactor Diode

Design of Control Circuit for Active Metasurface Based on Va...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Yue Zhang Yuefei Liu Guohui Yang Kuang Zhang Yingsong Li School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

A control circuit for active metasurface based on varactor diode is designed in this paper. By varying the reverse bias voltage on the varactor diode, the designed circuit can regulate the additional phase of the active meta-atoms. The circuit adopts a form of one master and multiple slaves, which can simultaneously control the bias voltage of 960 meta-atoms. Each slave can control up to 64 channels. The control accuracy is 0.04V. The power consumption of a single slave is 160mW. Though experiment verification, the circuit has a good effect in controlling the beam deflection of the metasurface and generating OAM beams.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beyond MLE: convex learning for text generation 23

Beyond MLE: convex learning for text generation

引用

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Chenze Shao Zhengrui Ma Min Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences School of Future Science and Engineering Soochow University

Maximum likelihood estimation (MLE) is a statistical method used to estimate the parameters of a probability distribution that best explain the observed data. In the context of text generation, MLE is often used to train generative language models, which can then be used to generate new text. However, we argue that MLE is not always necessary and optimal, especially for closed-ended text generation tasks like machine translation. In these tasks, the goal of model is to generate the most appropriate response, which does not necessarily require it to estimate the entire data distribution with MLE. To this end, we propose a novel class of training objectives based on convex functions, which enables text generation models to focus on highly probable outputs without having to estimate the entire data distribution. We investigate the theoretical properties of the optimal predicted distribution when applying convex functions to the loss, demonstrating that convex functions can sharpen the optimal distribution, thereby enabling the model to better capture outputs with high probabilities. Experiments on various text generation tasks and models show the effectiveness of our approach. It enables autoregressive models to bridge the gap between greedy and beam search, and facilitates the learning of non-autoregressive models with a maximum improvement of 9+ BLEU points. Moreover, our approach also exhibits significant impact on large language models (LLMs), substantially enhancing their generative capability on various tasks. Source code is availab.e at https://***/ictnlp/Convex-Learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Patch Is Not All You Need

arXiv

引用

arXiv 2023年

作者： Li, Changzhen Zhang, Jie Wei, Yang Ji, Zhilong Bai, Jinfeng Shan, Shiguang Key Lab of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology China University of Chinese Academy of Sciences China Hangzhou lnstitute for Advanced Study UCAS School of Intelligent Scienceand Technology China Tomorrow Advancing Life China

Vision Transformers have achieved great success in computer visions, delivering exceptional performance across various tasks. However, their inherent reliance on sequential input enforces the manual partitioning of images into patch sequences, which disrupts the image’s inherent structural and semantic continuity. To handle this, we propose a novel Pattern Transformer (Patternformer) to adaptively convert images to pattern sequences for Transformer input. Specifically, we employ the Convolutional Neural Network to extract various patterns from the input image, with each channel representing a unique pattern that is fed into the succeeding Transformer as a visual token. By enabling the network to optimize these patterns, each pattern concentrates on its local region of interest, thereby preserving its intrinsic structural and semantic information. Only employing the vanilla ResNet and Transformer, we have accomplished state-of-the-art performance on CIFAR-10 and CIFAR-100, and have achieved competitive results on ImageNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutual information

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutua...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Jicun Li Xingjian Li Tianyang Wang Shi Wang Yanan Cao Chengzhong Xu Dejing Dou Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Big Data Lab Baidu Research State Key Lab of IOTSC University of Macau University of Alabama at Birmingham Institute of Information Engineering Chinese Academy of Sciences

Fine-tuning pre-trained language models, such as BERT, has shown enormous success among various NLP tasks. Though simple and effective, the process of fine-tuning has been found unstable, which often leads to unexpected poor performance. To increase stability and generalizability, most existing works resort to maintaining the parameters or representations of pre-trained models during fine-tuning. Nevertheless, very little work explores mining the reliable part of pre-learned information that can help to stabilize fine-tuning. To address this challenge, we introduce a novel solution in which we fine-tune BERT with stabilized cross-layer mutual information. Our method aims to preserve the reliable behaviors of cross-layer information propagation, instead of preserving the information itself, of the pre-trained model. Therefore, our method circumvents the domain conflicts between pre-trained and target tasks. We conduct extensive experiments with popular pre-trained BERT variants on NLP datasets, demonstrating the universal effectiveness and robustness of our method.

关键词： Cross layer design Bit error rate Signal processing Stability analysis Robustness Acoustics Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

CoSign: Exploring Co-occurrence Signals in Skeleton-based Continuous Sign Language Recognition

CoSign: Exploring Co-occurrence Signals in Skeleton-based Co...

引用

International Conference on Computer Vision (ICCV)

作者： Peiqi Jiao Yuecong Min Yanan Li Xiaotao Wang Lei Lei Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Xiaomi Inc. China

The co-occurrence signals (e.g., hand shape, facial expression, and lip pattern) play a critical role in Continuous Sign Language Recognition (CSLR). Compared to RGB data, skeleton data provide a more efficient and concise option, and lay a good foundation for the co-occurrence exploration in CSLR. However, skeleton data are often used as a tool to assist visual grounding and have not attracted sufficient attention. In this paper, we propose a simple yet effective GCN-based approach, named CoSign, to incorporate Co-occurrence Signals and explore the potential of skeleton data in CSLR. Specifically, we propose a group-specific GCN to better exploit the knowledge of each signal and a complementary regularization to prevent complex co-adaptation across signals. Furthermore, we propose a two-stream framework that gradually fuses both static and dynamic information in skeleton data. Experimental results on three public CSLR datasets (PHOENIX14, PHOENIX14-T and CSL-Daily) show that the proposed CoSign achieves competitive performance with recent video-based approaches while reducing the computation cost during training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data

arXiv

引用

arXiv 2024年

作者： Chen, Yin Li, Jia Zhang, Yu Hu, Zhenzhen Shan, Shiguang Wang, Meng Hong, Richang School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Dynamic facial expression recognition (DFER) infers emotions from the temporal evolution of expressions, unlike static facial expression recognition (SFER), which relies solely on a single snapshot. This temporal analysis provides richer information and promises greater recognition capability. However, current DFER methods often exhibit unsatisfied performance largely due to fewer training samples compared to SFER. Given the inherent correlation between static and dynamic expressions, we hypothesize that leveraging the abundant SFER data can enhance DFER. To this end, we propose Static-for-Dynamic (S4D), a unified dual-modal learning framework that integrates SFER data as a complementary resource for DFER. Specifically, S4D employs dual-modal self-supervised pre-training on facial images and videos using a shared Vision Transformer (ViT) encoder-decoder architecture, yielding improved spatiotemporal representations. The pre-trained encoder is then fine-tuned on static and dynamic expression datasets in a multi-task learning setup to facilitate emotional information interaction. Unfortunately, vanilla multitask learning in our study results in negative transfer. To address this, we propose an innovative Mixture of Adapter Experts (MoAE) module that facilitates task-specific knowledge acquisition while effectively extracting shared knowledge from both static and dynamic expression data. Extensive experiments demonstrate that S4D achieves a deeper understanding of DFER, setting new state-of-the-art performance on FERV39K, MAFW, and DFEW benchmarks, with weighted average recall (WAR) of 53.65%, 58.44%, and 76.68%, respectively. Additionally, a systematic correlation analysis between SFER and DFER tasks is presented, which further elucidates the potential benefits of leveraging SFER. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

NetPrompt: Neural Network Prompting Enhances Event Extraction in Large Language Models

引用

IEEE Transactions on Big Data 2025年

作者： Mu, Lin Cheng, Yide Shen, Jun Zhang, Yiwen Zhong, Hong School of Computer Science and Technology Anhui University Anhui Hefei230601 China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education the Anhui Engineering Laboratory of IoT Security Technologies the School of Computer Science and Technology the Institute of Physical Science and Information Technology Anhui University Hefei230039 China

Event Extraction involves extracting event-related information such as event types and event arguments from context, which has long been tackled through well-designed neural networks or fine-tuned pre-trained language models. These approaches require substantial annotated data for tuning parameters and are resource-intensive. Recently, Prompting strategies with frozen parameters, such as Chain-of-Thought and Self-Consistency, have delivered success in NLP using LLMs by generating intermediate thought steps. However, they suffer from the challenge of error propagation and lack of interaction between different thoughts. In this paper, we propose Neural Network-based Prompting (NetPrompt), a novel network-structured prompting strategy for event extraction. The core idea behind NetPrompt is to imitate the excellent information integration capabilities of neural network structures. Specifically, we first decompose the event extraction problem into diverse intermediate subtasks, and each subtask is represented as a node in different layers of the network, the output of the nodes in the preceding layer is fed into the subsequent layer. Secondly, we propose pruning strategies to adapt the reasoning overhead to different problems. Finally, we have conducted extensive experiments on two widely used event extraction benchmarks to evaluate NetPrompt. The results demonstrated that NetPrompt significantly improved the event extraction performance compared to previous methods. ©2015 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency Maximization in RISs-Assisted UAVs-Based Edge computing Network Using Deep Reinforcement Learning

引用

Big Data Mining and Analytics 2024年第4期7卷 1065-1083页

作者： Chuanwen Luo Jian Zhang Jianxiong Guo Yi Hong Zhibo Chen Shuyang Gu School of Information Science and Technology Beijing Forestry UniversityBeijing 100083Chinaand also with the Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland AdministrationBeijing 100083China Advanced Institute of Natural Sciences Beijing Normal UniversityZhuhai 519087Chinaand also with the Guangdong Key Lab of AI and Multi-Modal Data ProcessingBNU-HKBU United International CollegeZhuhai 519087China Department of Computer Information Systems Texas A&M University-Central TexasKilleenTX 76549USA

Edge computing(EC)pushes computational capability to the Terrestrial Devices(TDs),providing more efficient and faster computing *** Aerial Vehicles(UAVs)equipped with EC servers can be flexibly deployed,even in complex terrains,to provide mobile computing services at all ***,UAVs can establish an air-to-ground line-of-sight link with TDs to improve the quality of communication ***,the UAV-to-TD link may be obstructed by ground obstacles such as buildings or trees,leading to sub-optimal data transmission *** surmount this issue,Reconfigurable intelligent Surfaces(RISs)emerge as a promising technology capable of intelligently reflecting signals to enhance communication quality between UAVs and *** this paper,we consider the RISs-assisted multi-UAVs collab.rative edge computing Network(RUCN)in urban environment,in which we study the computational offloading *** goal is to maximize the overall energy efficiency of UAVs by jointly optimizing the flight duration and trajectories of UAVs,and the phase shifts of *** is worth noting that this problem has been formally established as ***,we propose the Deep Deterministic Policy Gradients based UAV Trajectory and RIS Phase shift optimization algorithm(UTRP-DDPG)to solve this complex optimization *** results of extensive numerical experiments show that the proposed algorithm outperforms the other benchmark algorithms under various parameter ***,the UTRP-DDPG algorithm improves the UAV energy efficiency by at least 2%compared to DQN algorithm.

关键词： edge computing computing offloading Unmanned Aerial Vehicle(UAV) Reconfigurable intelligent Surface(RIS) deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment

arXiv

引用

arXiv 2024年

作者： Zhang, Shaolei Zhang, Kehao Fang, Qingkai Guo, Shoutao Zhou, Yan Liu, Xiaodong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences ICT CAS China Key Laboratory of AI Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China Research Center of Distributed Systems Institute of Computing Technology Chinese Academy of Sciences ICT CAS China

Large language models (LLMs), with their powerful generative capabilities and vast knowledge, empower various tasks in everyday life. However, these abilities are primarily concentrated in high-resource languages, leaving low-resource languages with weaker generative capabilities and relatively limited knowledge. Enhancing the multilingual capabilities of LLMs is therefore crucial for serving over 100 linguistic communities worldwide. An intuitive approach to enhance the multilingual capabilities would be to construct instruction data for various languages, but constructing instruction data for over 100 languages is prohibitively costly. In this paper, we introduce BayLing 2, which efficiently transfers generative capabilities and knowledge from high-resource languages to low-resource languages through language alignment. To achieve this, we constructed a dataset of 3.2 million instructions, comprising high-resource language instructions (Chinese and English) and cross-lingual instructions for 100+ languages and performed instruction tuning based on the dataset to facilitate the capability transfer between languages. Using Llama as the foundation model, we developed BayLing-2-7B, BayLing-2-13B, and BayLing-2-8B, and conducted a comprehensive evaluation of BayLing. For multilingual translation across 100+ languages, BayLing shows superior performance compared to open-source models of similar scale. For multilingual knowledge and understanding benchmarks, BayLing achieves significant improvements across over 20 low-resource languages, demonstrating its capability of effective knowledge transfer from high-resource to low-resource languages. Furthermore, results on English benchmarks indicate that BayLing maintains high performance in high-resource languages while enhancing the performance in low-resource languages. Demo2, homepage3, code4 and models5of BayLing are availab.e. © 2024, CC BY-NC-ND.

关键词： Benchmarking

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：