检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

2,301 篇 会议
1,542 篇 期刊文献
22 册 图书

馆藏范围

3,865 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,190 篇 工学
- 1,361 篇 计算机科学与技术...
- 1,036 篇 软件工程
- 414 篇 信息与通信工程
- 349 篇 电子科学与技术（可...
- 327 篇 电气工程
- 279 篇 控制科学与工程
- 239 篇 生物工程
- 201 篇 生物医学工程（可授...
- 160 篇 光学工程
- 119 篇 材料科学与工程（可...
- 117 篇 化学工程与技术
- 111 篇 机械工程
- 109 篇 动力工程及工程热...
- 94 篇 仪器科学与技术
- 78 篇 核科学与技术
- 64 篇 力学（可授工学、理...
- 61 篇 建筑学
1,510 篇 理学
- 621 篇 数学
- 582 篇 物理学
- 312 篇 生物学
- 206 篇 统计学（可授理学、...
- 157 篇 化学
- 133 篇 系统科学
374 篇 管理学
- 216 篇 管理科学与工程(可...
- 164 篇 图书情报与档案管...
- 121 篇 工商管理
188 篇 医学
- 147 篇 临床医学
- 140 篇 基础医学(可授医学...
- 90 篇 药学(可授医学、理...
74 篇 法学
- 63 篇 社会学
59 篇 教育学
42 篇 农学
37 篇 经济学
13 篇 文学
8 篇 军事学
5 篇 艺术学
3 篇 哲学

主题

393 篇 computer science
111 篇 hardware
106 篇 hadron colliders
101 篇 application soft...
100 篇 delay
89 篇 costs
86 篇 computer archite...
77 篇 computational mo...
66 篇 bandwidth
57 篇 processor schedu...
51 篇 very large scale...
51 篇 algorithm design...
51 篇 machine learning
50 篇 protocols
49 篇 testing
48 篇 throughput
48 篇 clocks
44 篇 computer network...
42 篇 timing
41 篇 routing

机构

192 篇 department of co...
150 篇 centro brasileir...
150 篇 istanbul technic...
150 篇 yerevan physics ...
149 篇 national and kap...
148 篇 university of sp...
147 篇 universidad iber...
146 篇 brunel universit...
145 篇 indian institute...
144 篇 academy of scien...
143 篇 charles universi...
141 篇 university of de...
141 篇 department of co...
140 篇 rwth aachen univ...
139 篇 università di to...
139 篇 imperial college...
137 篇 department of ph...
136 篇 infn sezione di ...
132 篇 indian institute...
131 篇 zhejiang univers...

作者

113 篇 g. tonelli
113 篇 d. barney
113 篇 l. valencia palo...
113 篇 t. liu
113 篇 c. hensel
113 篇 a. garcia-bellid...
113 篇 a. steen
113 篇 n. cartiglia
113 篇 n. colino
113 篇 f. moortgat
113 篇 b. clerbaux
113 篇 g. sultanov
113 篇 m. a. ciocci
113 篇 k. lamichhane
113 篇 s. maselli
113 篇 e. migliore
112 篇 a. babaev
112 篇 v. karjavine
112 篇 p. avery
112 篇 l. silvestris

语言

3,689 篇 英文
157 篇 其他
20 篇 中文

检索条件"机构=Department of Computer Science and Engineering UC San Diego"

共 3865 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

FUTGA: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation 3

FUTGA: Towards Fine-grained Music Understanding through Temp...

引用

3rd Workshop on NLP for Music and Audio, NLP4MusA 2024, in conjunction with ISMIR 2024

作者： Wu, Junda Novack, Zachary Namburi, Amit Dai, Jiaheng Dong, Hao-Wen Xie, Zhouhang Chen, Carol McAuley, Julian Computer Science and Engineering UC San Diego United States Computer Science Department UC Los Angeles United States

We propose FUTGA, a model equipped with fined-grained music understanding capabilities through learning from generative augmentation with temporal compositions. We leverage existing music caption datasets and large language models (LLMs) to synthesize fine-grained music captions with structural descriptions and time boundaries for full-length songs. Augmented by the proposed synthetic dataset, FUTGA is enabled to identify the music’s temporal changes at key transition points and their musical functions, as well as generate detailed descriptions for each music segment. We further introduce a full-length music caption dataset generated by FUTGA, as the augmentation of the MusicCaps and the Song Describer datasets. The experiments demonstrate the better quality of the generated captions, which capture the time boundaries of long-form music. Generated temporal-aware music descriptions are illustrated in our demonstration https://***/***/. © 2024 NLP4MusA. All Rights Reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

(Invited Paper) White-box logic obfuscation: A Transparent Solution to Hardware Piracy and Reverse engineering 30

(Invited Paper) White-box logic obfuscation: A Transparent S...

引用

30th Asia and South Pacific Design Automation Conference, ASP-DAC 2025

作者： Li, Leon Orailoglu, Alex Department of Computer Science and Engineering Uc San Diego La Jolla CA United States

ISBN: (纸本)9798400706356

Reverse engineering the functional specification from a netlist is a challenging task that enables IP piracy and tampering. Traditional logic locking techniques, which depend on external activation with secrets stored in tamper-proof locations to thwart reverse engineering, have repeatedly been compromised by key recovery attacks. Their vulnerability highlights the flawed assumption of relying on tamper-proof secrets for building hardware security solutions, especially when activated devices are deployed in open environments where they are exposed to attackers for functional queries and probing. This paper presents white-box logic obfuscation (WBLO) as a novel solution to safeguard control logic from functional reverse engineering, even when attackers have full visibility of the operational netlist. WBLO eliminates the need for post-manufacturing activation and reliance on tamper-proof key storage by securing the design with keys that are autonomously updated internally through the legitimate sequential execution of the device. The proposed approach invalidates functional analysis under arbitrary probing and combinational queries. We examine the implementation challenges inherent in the WBLO process and identify critical design considerations that enhance security and efficiency. Building on these insights, we suggest a prioritization for various design transformation and synthesis rules that achieve robust security in the white-box attack model while minimizing implementation overheads. © 2025 Copyright held by the owner/author(s).

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

FUTGA-MIR: Enhancing Fine-grained and Temporally-aware Music Understanding with Music Information Retrieval

FUTGA-MIR: Enhancing Fine-grained and Temporally-aware Music...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wu, Junda Novack, Zachary Namburi, Amit Dong, Hao-Wen Chen, Carol Dai, Jiaheng McAuley, Julian Computer Science and Engineering UC San Diego United States Computer Science Department UC Los Angeles United States

ISBN: (纸本)9798350368741

Recent music large language models (music LLMs) have shown great potential in music understanding through large-scale multimodal pre-training. While some existing music LLMs have been augmented with temporally-aware music captions, music information retrieval (MIR) features conventionally do not exist in music caption datasets, thus neglected by music-LLMs. To bridge the gap between recent music LLMs and conventional music information retrieval tasks, we propose FUTGA-MIR (Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation with Music Information Retrieval) to enhance the existing music LLMs by augmenting them with MIR features and aligning with human feedback. We calibrate the original positional distribution of music clips in the created pre-training synthetic music captions, conditioned on MIR features. The redistributed synthetic dataset better respects realistic MIR distributions of music and is tightly aligned with realistic music captions as well. In addition, We incorporate human-annotated music captions and MIR features from the Harmonixset dataset for an additional fine-tuning step, which addresses sim-to-real domain gaps and improves performance on realistic music tracks. We further evaluate FUTGA-MIR on several downstream tasks, including music classification, retrieval, and generation, and demonstrate the versatile capacities of FUTGA-MIR and better generation quality compared with previous music captioning models. Generated temporal-aware music descriptions are illustrated in our demonstration https://***/***/. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inexact Augmented Lagrangian Methods for Conic Programs: Quadratic Growth and Linear Convergence 38

Inexact Augmented Lagrangian Methods for Conic Programs: Qua...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Liao, Feng-Yi Ding, Lijun Zheng, Yang Department of Electrical and Computer Engineering UC San Diego United States Department of Mathematics UC San Diego United States

Augmented Lagrangian Methods (ALMs) are widely employed in solving constrained optimizations, and some efficient solvers are developed based on this framework. Under the quadratic growth assumption, it is known that the dual iterates and the Karush-Kuhn-Tucker (KKT) residuals of ALMs applied to semidefinite programs (SDPs) converge linearly. In contrast, the convergence rate of the primal iterates has remained elusive. In this paper, we resolve this challenge by establishing new quadratic growth and error bound properties for primal and dual SDPs under the strict complementarity condition. Our main results reveal that both primal and dual iterates of the ALMs converge linearly contingent solely upon the assumption of strict complementarity and a bounded solution set. This finding provides a positive answer to an open question regarding the asymptotically linear convergence of the primal iterates of ALMs applied to semidefinite optimization. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Future Is Rosie?: Disempowering Arguments about Automation and What to Do about It 25

The Future Is Rosie?: Disempowering Arguments about Automati...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Riek, Laurel D. Irani, Lilly Computer Science and Engineering UC San Diego San Diego CA United States Department of Communication UC San Diego San Diego CA United States

ISBN: (纸本)9798400713941

Many technologists who work in robotics and AI bristle at the idea that human worker displacement is problematic. Others wish to account for workers' needs, but face pervasive myths about the impacts of these technologies. This paper aims to clear the air by refuting five common arguments for automation: 1) the jobs being automated are undesirable, 2) labor shortages necessitate automation, 3) by "augmenting rather than automating"labor displacement will be prevented, 4) there will be new and better job creation, and 5) automation will give us all more leisure time. The advent of foundational models has led to an industrial gold rush, accelerating deployment without careful consideration of responsible and sustaiable design and deployment of these technologies. Despite technologists' best intentions, this path of pervasive automation we are on is not a good one, and we offer suggestions for how technologists, designers, and decision makers can push for worker-centered technological change moving forward. © 2025 Copyright held by the owner/author(s).

关键词： AI automation critical computing ethics future of work labor robotics social theory

来源：评论

学校读者我要写书评

暂无评论

CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation

CoLLAP: Contrastive Long-form Language-Audio Pretraining wit...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wu, Junda Li, Warren Novack, Zachary Namburi, Amit Chen, Carol McAuley, Julian Computer Science and Engineering UC San Diego La Jolla United States Computer Science Department UC Los Angeles Los Angeles United States

ISBN: (纸本)9798350368741

Modeling temporal characteristics plays a significant role in the representation learning of audio waveform. We propose Contrastive Long-form Language-Audio Pretraining (CoLLAP) to significantly extend the perception window for both the input audio (up to 5 minutes) and the language descriptions (exceeding 250 words), while enabling contrastive learning across modalities and temporal dynamics. Leveraging recent Music-LLMs to generate long-form music captions for full-length songs, augmented with musical temporal structures, we collect 51.3K audio-text pairs derived from the large-scale AudioSet training dataset, where the average audio length reaches 288 seconds. We propose a novel contrastive learning architecture that fuses language representations with structured audio representations by segmenting each song into clips and extracting their embeddings. With an attention mechanism, we capture multimodal temporal correlations, allowing the model to automatically weigh and enhance the final fusion score for improved contrastive alignment. Finally, we develop two variants of the CoLLAP model with different types of backbone language models. Through comprehensive experiments on multiple long-form music-text retrieval datasets, we demonstrate consistent performance improvement in retrieval accuracy compared with baselines. We also show the pretrained CoLLAP models can be transferred to various music information retrieval tasks, with heterogeneous long-form multimodal contexts. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HDXpose: Harnessing Hyperdimensional Computing’s Explainability for Adversarial Attacks 24

HDXpose: Harnessing Hyperdimensional Computing’s Explainabi...

引用

43rd International Conference on computer-Aided Design, ICCAD 2024

作者： Asgarinejad, Fatemeh Pozina, Flavio Gungor, Onat Rosing, Tajana Aksanli, Baris Department of Computer Science and Engineering UC San Diego La Jolla CA92093 United States Department of Electrical and Computer Engineering SDSU CA92182 United States

ISBN: (纸本)9798400710773

Hyperdimensional Computing (HDC), a promising alternative to address the limitations of edge devices, is not exempt from the security challenges confronted by machine learning algorithms, in particular, adversarial attacks. The limited body of research exploring the security implications of HDC overlooks its inherent algorithm. In this paper, we propose a novel and effective adversarial attack technique targeting HDC. Our approach analyzes and prioritizes the impact of input features as well as encoded elements on decision boundaries and perturbs the input towards incorrect decisions in a guided manner. We evaluate our method on different datasets and attack models (i.e., untargeted/targeted, white-box/gray-box). Experimental results indicate that our proposed design, HDXpose, significantly outperforms the state-of-the-art attack techniques by achieving higher success rate with smaller distortion and execution time, rendering its efficacy for real-time attack generation. © 2024 Copyright is held by the owner/author(s).

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Online Consistency of the Nearest Neighbor Rule 38

Online Consistency of the Nearest Neighbor Rule

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Dasgupta, sanjoy So, Geelon Department of Computer Science UC San Diego La Jolla CA92023 United States

In the realizable online setting, a learner is tasked with making predictions for a stream of instances, where the correct answer is revealed after each prediction. A learning rule is online consistent if its mistake rate eventually vanishes. The nearest neighbor rule (Fix and Hodges, 1951) is a fundamental prediction strategy, but it is only known to be consistent under strong statistical or geometric assumptions-the instances come i.i.d. or the label classes are well-separated. We prove online consistency for all measurable functions in doubling metric spaces under the mild assumption that the instances are generated by a process that is uniformly absolutely continuous with respect to a finite, upper doubling measure. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multipole Source Capture Using Multiple Dictionary Sparse Bayesian Learning 58

Multipole Source Capture Using Multiple Dictionary Sparse Ba...

引用

58th Asilomar Conference on Signals, Systems and computers, ACSSC 2024

作者： Tung, Alex Gerstoft, Peter Uc San Diego Department of Electrical and Computer Engineering La Jolla CA United States

ISBN: (纸本)9798350354058

A novel method of acoustic holography is introduced by expanding the equivalent source method (ESM) to include multipole equivalent sources and obtaining an optimal solution in a two-stage manner: Sparse Bayesian learning (SBL) is first used to estimate a broadband distribution of spherical harmonic sources, in which prior covariances for each frequency are transformed by its corrsponding dictionary. A per-frequency refinement is performed by a reduced-order inversion of the subset of sources. The estimated sources are able to be represented in a more compact manner and manipulated using common multipole techniques, such as higher-order Ambisonics (HOA). Simulated results for a finite quadrupole are obtained, and the reconstruction accuracy using several arrangements of spherical microphone arrays are compared. © 2024 IEEE.

关键词： Acoustic holography

来源：评论

学校读者我要写书评

暂无评论

QUADRATIC MODELS FOR UNDERSTANDING CATAPULT DYNAMICS OF NEURAL NETWORKS 12

QUADRATIC MODELS FOR UNDERSTANDING CATAPULT DYNAMICS OF NEUR...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Zhu, Libin Liu, Chaoyue Radhakrishnan, Adityanarayanan Belkin, Mikhail Department of Computer Science UC San Diego United States Halicioglu Data Science Institute UC San Diego United States Harvard & Broad Institute of MIT and Harvard United States

While neural networks can be approximated by linear models as their width increases, certain properties of wide neural networks cannot be captured by linear models. In this work we show that recently proposed Neural Quadratic Models can exhibit the "catapult phase" (Lewkowycz et al., 2020) that arises when training such models with large learning rates. We then empirically show that the behaviour of neural quadratic models parallels that of neural networks in generalization, especially in the catapult phase regime. Our analysis further demonstrates that quadratic models can be an effective tool for analysis of neural networks. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共387页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：