检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jo, Sanghyun Lee, Ziseok Lee, Wooyeol Kim, Kyungsu OGQ Seoul Korea Republic of Department of Biomedical Sciences Seoul National University Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University Seoul Korea Republic of School of Transdisciplinary Innovations Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Achieving precise panoptic segmentation heavily relies on pixel-wise instance annotations, but obtaining such datasets is costly. Unsupervised instance segmentation (UIS) eliminates annotation requirements but struggles with adjacent instance merging and single-instance fragmentation, largely due to the limitations of DINO-based backbones, which lack strong instance separation cues. Weakly-supervised panoptic segmentation (WPS) reduces annotation costs by using sparse labels (e.g., points, boxes), yet these annotations remain expensive and introduce human bias and boundary errors, limiting performance. To address these challenges, we propose DiffEGG (Diffusion-Driven EdGe Generation), a fully annotation-free method that extracts instance-aware features from pretrained diffusion models to generate precise instance edge maps. DiffEGG fundamentally differs from prior UIS and WPS approaches by leveraging pretrained diffusion models as a backbone. Unlike DINO-based UIS methods, diffusion models inherently capture fine-grained, instance-aware features, enabling more precise boundary delineation. DiffEGG further enhances edge connectivity through self-supervised fine-tuning, progressively improving instance separation. For WPS, DiffEGG completely eliminates annotation costs and human bias by operating without any form of manual supervision, addressing the key limitations of prior best methods. Additionally, we introduce RIP, a post-processing technique that fuses DiffEGG’s edge maps with segmentation masks in a task-agnostic manner. This broad applicability allows DiffEGG to be seamlessly integrated into various segmentation frameworks. When applied to UIS, DiffEGG and RIP achieve an average +4.4 AP improvement over prior best UIS methods. When combined with weakly-supervised semantic segmentation (WSS), DiffEGG enables WPS without instance annotations, outperforming prior best point-supervised WPS methods by +1.7 PQ. These results demonstrate that DiffEGG’s edge maps serv

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Unavoidable multilevel biaxial symmetry breaking in chiral hybrid liquid crystals

引用

Physical Review E 2025年第4期111卷 045410-045410页

作者： Jin-Sheng Wu Marina Torres Lázaro Souvik Ghosh Haridas Mundoor Henricus H. Wensink Ivan I. Smalyukh Department of Physics and Chemical Physics Program University of Colorado Boulder Colorado 80309 USA Laboratoire de Physique des Solides–UMR 8502 Université Paris-Saclay and CNRS 91405 Orsay France International Institute for Sustainability with Knotted Chiral Meta Matter Hiroshima University Higashihiroshima Japan Department of Electrical Computer and Energy Engineering Materials Science and Engineering Program and Soft Materials Research Center University of Colorado Boulder Colorado 80309 USA Renewable and Sustainable Energy Institute National Renewable Energy Laboratory and University of Colorado Boulder Colorado 80309 USA

Chiral nematic or cholesteric liquid crystals (LCs) are fluid mesophases with long-ranged orientational order featuring a quasilayered periodicity imparted by a helical director configuration but lacking long-range positional order. Doping molecular cholesteric LCs with strongly anisotropic uniaxial colloidal particles adds another level of complexity because of the interplay between weak surface-anchoring boundary conditions and bulk-based elastic distortions near the particle-LC interface. Using cylindrical colloidal disks and rods with different geometric shapes and surface conditions, we demonstrate that these colloidal inclusions generically exhibit biaxial orientational probability distributions which may impart anomalously strong local biaxiality onto the hybrid cholesteric LC structure. Unlike nonchiral hybrid molecular-colloidal LCs, where biaxial order emerges only at critical colloid volume fractions exceeding some uniaxial-biaxial transition value, the orientational probability of the colloidal inclusions immersed in chiral nematic hosts is unambiguously biaxial even at infinite dilution. We demonstrate that the colloids induce local biaxial perturbations within the molecular orientational order of the LC host medium which strongly enhances the weak but native biaxial order of chiral nematic LC induced by the chiral symmetry breaking of the director field. With the help of analytical modeling and computer simulations based on the Landau–de Gennes free energy of the host LC around the colloids, we rationalize the observed multilevel biaxial order and conclude that it is not only unavoidable but also strongly enhanced compared to both achiral hybrid LCs and purely molecular cholesteric LCs.

关键词： Cholesteric liquid crystals

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Intrinsic Neighborhood Semantic Structure for Domain Adaptation in EEG-based Emotion Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Yang, Yi Wang, Ze Song, Yu Jia, Ziyu Wang, Boyu Jung, Tzyy-Ping Wan, Feng Macau University of Science and Technology Macao Centre for Mathematical Sciences Respiratory Disease AI Laboratory on Epidemic Intelligence and Medical Big Data Instrument Applications Faculty of Innovation Engineering 999078 China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin300384 China Chinese Academy of Sciences Beijing Key Laboratory of Brainnetome and Brain-Computer Interface and Brainnetome Center Institute of Automation Beijing100045 China Western University Department of Computer Science Brain Mind Institute LondonONN6A 3K7 Canada University of California at San Diego Swartz Center for Computational Neuroscience Institute for Neural Computation La Jolla CA92093 United States University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology China University of Macau Centre for Cognitive and Brain Sciences Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation 999078 China

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios. The source code is available at https://***/YYingDL/NSAL-DGAT. © 2010-2012 IEEE.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

Rapid information gain explains cross-linguistic tendencies in numeral ordering 41

Rapid information gain explains cross-linguistic tendencies ...

引用

41st Annual Meeting of the cognitive science Society: Creativity + Cognition + Computation, CogSci 2019

作者： Liu, Emmy Xu, Yang Department of Computer Science Cognitive Science Program University of Toronto Canada

ISBN: (纸本)0991196775

One previously unexplained observation about numeral systems is the shared tendency in numeral expressions: Numerals greater than 20 often have the larger constituent number expressed before the smaller constituent number (e.g., twenty-four as opposed to four-twenty in English), and systems that originally adopt the reverse order of expression (e.g., four- and-twenty in Old English) tend to switch order over time. To explore these phenomena, we propose the view of Rapid Information Gain and contrast it with the established theory of Uniform Information Density. We compare the two theories in their ability to explain the shared tendency in the ordering of numeral expressions around 20. We find that Rapid Information Gain accounts for empirical patterns better than the alternative theory, suggesting that there is an emphasis on information front-loading as opposed to information smoothing in the design of large compound numerals. Our work shows that fine-grained generalizations about numeral systems can be understood in information-theoretic terms and offers an opportunity to characterize the design principles of lexical compounds through the lens of informative communication. © cognitive science Society: Creativity + Cognition + Computation, CogSci *** rights reserved.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

650 nm emitting InGaN red micro-LEDs with ITO n-electrodes

引用

Applied Physics Express 2025年第6期18卷 061001-061001页

作者： Cesur Altinkaya Rawan S. Jalmood Mohammed A. Najmi Daisuke Iida Kazuhiro Ohkawa Material Science and Engineering Program Physical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia Electrical and Computer Engineering Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia

InGaN red micro-LEDs were fabricated with indium tin oxide (ITO) and metal n-electrode designs. Micro-LEDs with ITO electrodes achieved a peak on-wafer external quantum efficiency of 2.1% (at 1.25 A cm⁻²) and wall-plug efficiency of 1.7% (at 0.64 A cm⁻²), representing 1.6 times and 1.5 times improvements compared to metal-based electrodes. Improved performance was attributed to the transparency of ITO, enabling light extraction, while metal electrodes block emission. Both configurations achieved a low leakage current density (≤ 10^–7 A cm⁻²) and a high peak emission wavelength around 650 nm. These results represent a strong potential for low-power consumption required/area-limited AR/VR applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gender convergence in the expressions of love: A computational analysis of lyrics 42

Gender convergence in the expressions of love: A computation...

引用

42nd Annual Meeting of the cognitive science Society: Developing a Mind: Learning in Humans, Animals, and Machines, CogSci 2020

作者： El Sanyoura, Lana Xu, Yang Department of Computer Science Cognitive Science Program University of Toronto Canada

Love is a central theme in modern music, but do women and men differ in their expressions of love? Results from empirical studies on gender differences in love attitudes have evolved from showing consistent differences to more similarities over time and witnessed gender convergence in relationship expectations, housework responsibilities, and sexual attitudes. Independently, pop culture studies have shown how music can be used as a contextual artifact whose lyrics can reflect a culture's changing psychological processes and ideologies. We combine these two research areas to explore whether the gender convergence reported in psychological studies is mirrored in love songs. Using a corpus of lyrics and song metadata from 1960 to 2009, we present a computational analysis of the lexical distribution of lyrics across genre, gender and time. We show that love songs between vocalists who are men vs. women have become significantly more similar in their lyrical expressions of love. © 2020 The Author(s)

关键词： Computational methods

来源：评论

学校读者我要写书评

暂无评论

GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model – Bringing Motion Generation to the Clinical Domain

arXiv

引用

arXiv 2025年

作者： Adeli, Vida Mehraban, Soroush Mirmehdi, Majid Whone, Alan Filtjens, Benjamin Dadashzadeh, Amirhossein Fasano, Alfonso Iaboni, Andrea Taati, Babak University of Toronto Computer Science Department Canada Vector Institute Canada KITE Research Institute UHN Canada University of Toronto Institute of Biomedical Engineering Canada University of Bristol School of Computer Science United Kingdom University of Bristol Translational Health Science United Kingdom University of Toronto Data Sciences Institute Canada University of Toronto Department of Medicine Division of Neurology Canada Krembil Research Institute UHN Canada Edmond J. Safra Program in Parkinson’s Disease UHN Canada University of Toronto Department of Psychiatry Canada Centre for Mental Health UHN Canada

Gait analysis is crucial for the diagnosis and monitoring of movement disorders like Parkinson’s Disease. While computer vision models have shown potential for objectively evaluating parkinsonian gait, their effectiveness is limited by scarce clinical datasets and the challenge of collecting large and well-labelled data, impacting model accuracy and risk of bias. To address these gaps, we propose GAITGen, a novel framework that generates realistic gait sequences conditioned on specified pathology severity levels. GAITGen employs a Conditional Residual Vector Quantized Variational Autoencoder to learn disentangled representations of motion dynamics and pathology-specific factors, coupled with Mask and Residual Transformers for conditioned sequence generation. GAITGen generates realistic, diverse gait sequences across severity levels, enriching datasets and enabling large-scale model training in parkinsonian gait analysis. Experiments on our new PD-GaM (real) dataset demonstrate that GAITGen outperforms adapted state-of-the-art models in both reconstruction fidelity and generation quality, accurately capturing critical pathology-specific gait features. A clinical user study confirms the realism and clinical relevance of our generated sequences. Moreover, incorporating GAITGen-generated data into downstream tasks improves parkinsonian gait severity estimation, highlighting its potential for advancing clinical gait analysis. © 2025, CC BY-NC-SA.

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Optimal Routing in a Small-World Network

引用

Journal of computer science & Technology 2006年第4期21卷 476-481页

作者：曾坚阳许文经 School of Computer Engineering Nanyang Technological University Singapore 639798 Computer Science Program Singapore-MIT Alliance (SMA) Program Singapore 117576

Substantial research has been devoted to the modelling of the small-world phenomenon that arises in nature as well as human society. Earlier work has focused on the static properties of various small-world models. To examine the routing aspects, Kleinberg proposes a model based on a d-dimensional toroidal lattice with long-range links chosen at random according to the d-harmonic distribution. Kleinberg shows that, by using only local information, the greedy routing algorithm performs in O（lg^2 n） expected number of hops. We extend Kleinberg＇s small-world model by allowing each node x to have two more random links to nodes chosen uniformly and randomly within （lg n）2/d Manhattan distance from x. Based on this extended model, we then propose an oblivious algorithm that can route messages between any two nodes in O（lg n） expected number of hops. Our routing algorithm keeps only O（（lgn）β＋1） bits of information on each node, where 1 〈 β 〈 2, thus being scalable w.r.t, the network size. To our knowledge, our result is the first to achieve the optimal routing complexity while still keeping a poly-logarithmic number of bits of information stored on each node in the small-world networks.

关键词： small-world model augmented local awareness decentralized routing analysis of algorithms distributedsystems

来源：评论

学校读者我要写书评

暂无评论

Scaling Up Single Image Dehazing Algorithm by Cross-Data Vision Alignment for Richer Representation Learning and Beyond

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Shi, Yukai Weng, Zhipeng Lin, Yupei Shi, Cidan Guo, Xingyuan Yang, Xiaojun Lin, Liang Guangdong University of Technology School of Information Engineering Guangzhou510006 China Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Hefei230601 China Southern Power Grid Ltd. Guangzhou510000 China Ministry of Education of China Key Laboratory of Photonic Technology for Integrated Sensing and Communication Guangdong Guangzhou510006 China Sun Yat-sen University School of Computer Science Guangzhou510006 China

In recent years, deep neural network tasks have increasingly relied on high-quality image inputs. With the development of high-resolution representation learning, the task of image dehazing has received significant attention. Previously, many methods collected diverse image data for large-scale training to boost the performance on a target scene. Ignoring the domain gap between different data, former dehazing methods simply adopt multiple datasets for explicit large-scale training, which often makes the methods themselves violated. To address this problem, we propose a novel method of cross-data vision alignment for richer representation learning to improve the existing dehazing methodology. Specifically, we call for the internal and external knowledge should be further adapted in a self-supervised manner to fill up the domain gap. By using cross-data external alignment, the datasets inherit samples from different domains that are firmly aligned, making the model learn more robust and generalizable features. By using the internal augmentation method, the model can fully exploit local information within the images and then obtain more image details. To demonstrate the effectiveness of our proposed method, we conduct training on the natural image dataset (NID). Experimental results show that our method clearly resolves the domain gap in different dehazing datasets and presents a new pipeline for large-scale training in the dehazing task. Our approach significantly outperforms other advanced methods in dehazing and produces dehazed images that are closest to real haze-free images. © 1963-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Bootstrapping in miniature language acquisition

引用

cognitive Systems Research 2002年第1期3卷 15-23页

作者： Desai, Rutvik Computer Science Department The Cognitive Science Program Indiana University Bloomington IN 47405 United States

Given the difficulties in learning meanings of words by observing the referent, it has been suggested that children use the syntactic context of the word to predict part of its meaning, a hypothesis known as syntactic bootstrapping. Semantic bootstrapping is the opposite theory that the knowledge of semantics helps in acquiring syntax. While there is evidence that children can apply their knowledge of correlations between syntax and semantics to perform bootstrapping, it is not clear how they come to know about these correlations in the first place. Here, a connectionist network is presented that learns to comprehend a miniature language by associating sentences with the corresponding scenes. In doing so, it learns the syntactic/semantic correlations and exhibits bootstrapping behavior. It is argued that such specialized phenomena can emerge when general mechanisms are applied to a specific task, and it is not always necessary to endow the learner with pre-existing specialized mechanisms. © 2002 Elsevier science B.V. All rights reserved.

关键词： Connectionist modeling Emergence Language acquisition Semantic bootstrapping Syntactic bootstrapping

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：