检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Shanshan Wang Minbin Hu Xingyi Zhang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China School of Computer Science and Technology Anhui University Hefei China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Unsupervised domain adaptation (UDA) aims to transfer the knowledge learned from the labeled source domain to the unlabeled target domain. Traditional methods often focus on minimizing the distribution gap between feature spaces of the two domains to achieve domain-invariant representations. However, this approach may not fully leverage the inherent class-specific information and could adversely affect decision boundaries in the target domain. In this paper, we introduce an adversarial contrastive self-training framework. The model integrates both intra-class and inter-class domain differences for better alignment between the source and target domains. Initially, we augment target domain samples using Fourier transformations, obtaining reliable samples and pseudo-labels through self-training. We then employ intra-domain contrastive learning on the reliable samples and pseudo-labels, alongside labeled source domain samples, to achieve intra-domain compactness. Finally, we utilize adversarial learning to achieve global alignment. This comprehensive approach ensures improved adaptation performance while also addressing the limitations of previous methods.

关键词： Adaptation models Neural networks Contrastive learning Adversarial machine learning Reliability

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

Non-monotonic latent alignments for CTC-based non-autoregressive machine translation 22

Non-monotonic latent alignments for CTC-based non-autoregres...

引用

Proceedings of the 36th International Conference on Neural information processing Systems

作者： Chenze Shao Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences

ISBN: (纸本)9781713871088

Non-autoregressive translation (NAT) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word positions. Latent alignment models relax the explicit alignment by marginalizing out all monotonic latent alignments with the CTC loss. However, they cannot handle non-monotonic alignments, which is non-negligible as there is typically global word reordering in machine translation. In this work, we explore non-monotonic latent alignments for NAT. We extend the alignment space to non-monotonic alignments to allow for the global word reordering and further consider all alignments that overlap with the target sentence. We non-monotonically match the alignments to the target sentence and train the latent alignment model to maximize the F1 score of nonmonotonic matching. Extensive experiments on major WMT benchmarks show that our method substantially improves the translation performance of CTC-based models. Our best model achieves 30.06 BLEU on WMT14 En-De with only one-iteration decoding, closing the gap between non-autoregressive and autoregressive models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation

arXiv

引用

arXiv 2024年

作者： Ma, Zhengrui Fang, Qingkai Zhang, Shaolei Guo, Shoutao Feng, Yang Zhang, Min Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of AI Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences China School of Future Science and Engineering Soochow University China

Simultaneous translation models play a crucial role in facilitating communication. However, existing research primarily focuses on text-to-text or speech-to-text models, necessitating additional cascade components to achieve speech-to-speech translation. These pipeline methods suffer from error propagation and accumulate delays in each cascade component, resulting in reduced synchronization between the speaker and listener. To overcome these challenges, we propose a novel non-autoregressive generation framework for simultaneous speech translation (NAST-S2x1), which integrates speech-to-text and speech-to-speech tasks into a unified end-to-end framework. We develop a non-autoregressive decoder capable of concurrently generating multiple text or acoustic unit tokens upon receiving fixed-length speech chunks. The decoder can generate blank or repeated tokens and employ CTC decoding to dynamically adjust its latency. Experimental results show that NAST-S2x outperforms state-of-the-art models in both speech-to-text and speech-to-speech tasks. It achieves high-quality simultaneous interpretation within a delay of less than 3 seconds and provides a 28× decoding speedup in offline generation. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

computing Flow Experience Based on Physiological Signals: A Systematic Literature Review

Computing Flow Experience Based on Physiological Signals: A ...

引用

2025 CHI Conference on Human Factors in computing Systems, CHI EA 2025

作者： Hong, Yichen Zhou, Chao Liu, Zelu Zifeng, Ni Liu, Juan Li, Xiangxian Yang, Chenglei Bian, Yulong Shandong University Weihai China Human Computer Interaction Technology and Intelligent Information Processing Laboratory Institute of Software Chinese Academy of Sciences Beijing China Shandong University School of Mechanical Electrical & Information Engineering Weihai China Shandong University Jinan China School of Software Shandong University Jinan China Shandong Key Laboratory of Intelligent Electronic Packaging Testing and Application Shandong University Shandong Weihai China Shandong Key Laboratory of Intelligent Electronic Packaging Testing and Application China

ISBN: (纸本)9798400713958

Flow experience is a key user experience in human-computer interaction (HCI). Compared with traditional subjective measurements, physiological signal-based methods (i.e. physiological computation of flow experience) can measure flow experience in a more objective and real-time way without interrupting the ongoing activity of the user. Despite scattered studies, a systematic review of research in this field is absent. Synthesizing key aspects of this field, including the conceptualization of flow experience, prevalent theoretical models, foundational research steps for experiment, computerized tasks for inducing flow, commonly used physiological signals, methods for analyzing flow state, and application in HCI. Finally, we discuss the potential of this field to propel HCI and user experience evaluation technologies, while projecting future research avenues. This paper is expected to help researchers grasp existing work in physiological signal-based flow computing and inspire subsequent explorations. © 2025 Copyright held by the owner/author(s).

关键词： Deep learning Flow experience Flow model Machine learning Physiological signals

来源：评论

学校读者我要写书评

暂无评论

Consistency of Compositional Generalization Across Multiple Levels 39

Consistency of Compositional Generalization Across Multiple ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Chuanhao Li, Zhen Jing, Chenchen Fan, Xiaomeng Ye, Wenbo Wu, Yuwei Jia, Yunde Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China School of Computer Science Zhejiang University China

ISBN: (纸本)157735897X

Compositional generalization is the capability of a model to understand novel compositions composed of seen concepts. There are multiple levels of novel compositions including phrase-phrase level, phrase-word level, and word-word level. Existing methods achieve promising compositional generalization, but the consistency of compositional generalization across multiple levels of novel compositions remains unexplored. The consistency refers to that a model should generalize to a phrase-phrase level novel composition, and phrase-word/word-word level novel compositions that can be derived from it simultaneously. In this paper, we propose a meta-learning based framework, for achieving consistent compositional generalization across multiple levels. The basic idea is to progressively learn compositions from simple to complex for consistency. Specifically, we divide the original training set into multiple validation sets based on compositional complexity, and introduce multiple meta-weight-nets to generate sample weights for samples in different validation sets. To fit the validation sets in order of increasing compositional complexity, we optimize the parameters of each meta-weight-net independently and sequentially in a multilevel optimization manner. We build a GQA-CCG dataset to quantitatively evaluate the consistency. Experimental results on visual question answering and temporal video grounding, demonstrate the effectiveness of the proposed framework. © 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

MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation

arXiv

引用

arXiv 2024年

作者： Huang, Langlin Bu, Mengyu Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of AI Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences China Washington University St. Louis United States

Byte-based machine translation systems have shown significant potential in massively multilingual settings. Unicode encoding, which maps each character to specific byte(s), eliminates the emergence of unknown words, even in new languages. This avoids out-of-vocabulary risk in multilingual translation and enables broad language scalability. However, byte-level tokenization results in sequences that are hard to interpret due to limited semantic information per byte. Local contextualization has proven effective in assigning initial semantics to tokens, improving sentence comprehension. Nevertheless, variations in encoding rules across languages necessitate an adaptive approach for effective contextualization. To this end, we propose Mixture of Contextualization Experts (MoCE), adaptively selecting and mixing attention heads, which are treated as contextualization experts. This enhances the flexibility of contextualization scales and allows models to search for better contextualization combinations. Experiment results show that our method outperforms existing methods without extensive manual adjustment of hyper-parameters and surpasses subword-based models with fewer parameters in Ted-59 dataset. Our code is available at https://***/ictnlp/MoCE. © 2024, CC BY-NC-ND.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

A 220-GHz Miniaturized Antenna-Coupled Mixer Based on $\mathbf{Bi}_{2} \mathbf{Sr}_{2} \mathbf{CaCu}_{2} \mathbf{O}_{8}$ Josephson Junction Array

A 220-GHz Miniaturized Antenna-Coupled Mixer Based on $\math...

引用

IEEE International Workshop on Radio-Frequency Integration technology (RFIT)

作者： Dan Qiao Xiang Gao Ziru Chen Huanxin Li Heng Liu Xiangyuan Bu Jianping An School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China School of Information and Electronics Beijing Institute of Technology Beijing China

ISBN: (数字)9798331541095

ISBN: (纸本)9798331541101

This paper presents the design and simulation of a 220-GHz miniaturized slot-antenna-coupled high-temperature superconducting (HTS) mixer, which integrates the HTS junction and the choke filter on one single substrate. The presented mixer utilizes $\mathbf{Bi_{2}}\mathbf{Sr_{2}}\mathbf{CaCu}2\mathbf{O_{8}}$ (BSCCO) intrinsic Josephson junction array as the nonlinear mixing device. To compensate the parasitic capacitance of the BSCCO junction, a short transmission line is used as an inductance for improving impedance matching between the slot antenna and the BSCCO Josephson junction array. The simulation results show that the proposed mixer achieves a conversion gain and noise temperature of -6.74 dB and 266.28 K @ 50K, respectively.

关键词： Wireless communication High-temperature superconductors Noise Josephson junctions Superconducting filters Junctions Mixers Gain Antenna arrays Transmission line antennas

来源：评论

学校读者我要写书评

暂无评论

AutoSketch: automatic sketch-oriented compiler for query-driven network telemetry 24

AutoSketch: automatic sketch-oriented compiler for query-dri...

引用

Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation

作者： Haifeng Sun Qun Huang Jinbo Sun Wei Wang Jiaheng Li Fuliang Li Yungang Bao Xin Yao Gong Zhang National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Institute of Computing Technology CAS Northeastern University China Huawei Theory Department

ISBN: (纸本)9781939133397

Recent network telemetry witnesses tremendous progress in two directions: query-driven telemetry that targets expressiveness as the primary goal, and sketch-based algorithms that address resource-accuracy trade-offs. In this paper, we propose AutoSketch that aims to integrate the advantages of both classes. In a nutshell, AutoSketch automatically compiles high-level operators into sketch instances that can be readily deployed with low resource usage and incur limited accuracy drop. However, there remains a gap between the expressiveness of high-level operators and the underlying realization of sketch algorithms. AutoSketch bridges this gap in three aspects. First, AutoSketch extends its interface derived from existing query-driven telemetry such that users can specify the desired telemetry accuracy. The specified accuracy intent will be utilized to guide the compiling procedure. Second, AutoSketch leverages various techniques, such as syntax analysis and performance estimation, to construct efficient sketch instances. Finally, AutoSketch automatically searches for the most suitable parameter configurations that fulfill the accuracy intent with minimum resource usage. Our experiments demonstrate that AutoSketch can achieve high expressiveness, high accuracy, and low resource usage compared to state-of-the-art telemetry solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Conformal AMC-Backed Array of Moderate Gain, Broad Coverage and Wide Bandwidth

A Conformal AMC-Backed Array of Moderate Gain, Broad Coverag...

引用

IEEE Asia-Pacific Conference on Antennas and Propagation (APCAP)

作者： Chuanfei Ding Xiang Gao Heng Liu Xiangyuan Bu Jianping An School of Information and Electronics Beijing Institute of Technology Beijing China School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (数字)9798350351019

ISBN: (纸本)9798350351026

This paper presents a conformal array antenna for emergency communication applications. The array consists of six conformal AMC-backed Yagi antennas, for which approximately half-space beam coverage can be achieved via one-dimensional full-azimuthal beam switching. The Yagi antenna is comprised of a bowtie-shaped driven dipole and three directors with optimized lengths and spacing to achieve the desired radiation characteristics. To increase the gain and generate the oblique directional beam, the Yagi antenna is backed by an AMC reflector. To validate the design, a prototype of conformal array element was fabricated and measured. Experimental results have shown the proposed conformal antenna exhibit a bandwidth of 570 MHz at the $2.4-\text{GHz}$ band, a gain of 7.5 dBi and approximately half-space beam coverage. The superior performance has shown its huge potential in balloon-based emergency communication stations.

关键词： Antenna measurements Dipole antennas Communication systems Prototypes Bandwidth Switches Directive antennas Reflector antennas Antenna arrays

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：