咨询与建议

限定检索结果

文献类型

  • 1,817 篇 期刊文献
  • 1,448 篇 会议
  • 10 册 图书

馆藏范围

  • 3,275 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 2,064 篇 工学
    • 1,602 篇 计算机科学与技术...
    • 1,377 篇 软件工程
    • 487 篇 信息与通信工程
    • 327 篇 电气工程
    • 280 篇 生物工程
    • 238 篇 控制科学与工程
    • 236 篇 生物医学工程(可授...
    • 206 篇 光学工程
    • 153 篇 电子科学与技术(可...
    • 100 篇 机械工程
    • 91 篇 化学工程与技术
    • 89 篇 网络空间安全
    • 82 篇 安全科学与工程
    • 79 篇 交通运输工程
    • 77 篇 航空宇航科学与技...
    • 69 篇 土木工程
  • 1,163 篇 理学
    • 577 篇 数学
    • 330 篇 生物学
    • 308 篇 物理学
    • 215 篇 统计学(可授理学、...
    • 103 篇 化学
    • 87 篇 系统科学
  • 631 篇 管理学
    • 381 篇 管理科学与工程(可...
    • 280 篇 图书情报与档案管...
    • 206 篇 工商管理
  • 246 篇 医学
    • 216 篇 临床医学
    • 187 篇 基础医学(可授医学...
    • 123 篇 公共卫生与预防医...
    • 96 篇 药学(可授医学、理...
  • 114 篇 法学
    • 89 篇 社会学
  • 62 篇 经济学
  • 49 篇 农学
  • 40 篇 教育学
  • 6 篇 文学
  • 3 篇 艺术学
  • 2 篇 军事学

主题

  • 119 篇 accuracy
  • 112 篇 deep learning
  • 100 篇 training
  • 96 篇 feature extracti...
  • 79 篇 machine learning
  • 77 篇 predictive model...
  • 71 篇 real-time system...
  • 70 篇 computational mo...
  • 69 篇 data models
  • 63 篇 semantics
  • 63 篇 federated learni...
  • 58 篇 convolutional ne...
  • 57 篇 internet of thin...
  • 52 篇 optimization
  • 48 篇 deep reinforceme...
  • 46 篇 adaptation model...
  • 44 篇 reinforcement le...
  • 44 篇 contrastive lear...
  • 41 篇 image segmentati...
  • 39 篇 generative adver...

机构

  • 504 篇 college of compu...
  • 124 篇 nanyang technolo...
  • 95 篇 college of compu...
  • 65 篇 national enginee...
  • 65 篇 college of compu...
  • 61 篇 the college of c...
  • 57 篇 college of intel...
  • 57 篇 department of co...
  • 43 篇 college of compu...
  • 41 篇 data science ins...
  • 32 篇 college of compu...
  • 29 篇 fujian key labor...
  • 28 篇 fujian provincia...
  • 28 篇 department of br...
  • 28 篇 college of compu...
  • 27 篇 dipartimento di ...
  • 27 篇 college of infor...
  • 26 篇 the oskar klein ...
  • 25 篇 hiroshima astrop...
  • 24 篇 institut für ast...

作者

  • 235 篇 niyato dusit
  • 49 篇 tao dacheng
  • 46 篇 sun geng
  • 40 篇 wang jiacheng
  • 40 篇 du hongyang
  • 32 篇 kang jiawen
  • 27 篇 e. j. siskind
  • 27 篇 r. bellazzini
  • 27 篇 guo yike
  • 26 篇 dusit niyato
  • 26 篇 bai wenjia
  • 25 篇 p. spinelli
  • 25 篇 m. kuss
  • 25 篇 zhang ruichen
  • 24 篇 j. b. thayer
  • 24 篇 s. ciprini
  • 24 篇 s. guiriec
  • 24 篇 xiong zehui
  • 23 篇 p. a. caraveo
  • 23 篇 liu yang

语言

  • 2,831 篇 英文
  • 431 篇 其他
  • 23 篇 中文
  • 1 篇 斯洛文尼亚文
检索条件"机构=College of Computing and Data Science"
3275 条 记 录,以下是1-10 订阅
An Encoder-Agnostic Weakly Supervised Method For Describing Textures
An Encoder-Agnostic Weakly Supervised Method For Describing ...
收藏 引用
2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025
作者: Mao, Shangbo Rajan, Deepu College of Computing and Data Science Nanyang Technological University Singapore
Recent advances in Large Language Models (LLMs) have enabled the semantic description of textures in natural language, aiming to capture them in richer detail. However, most methods are confined to either depending on... 详细信息
来源: 评论
Finding Sets of Pareto Sets in Real-World Scenarios - A Multitask Multiobjective Perspective  13
Finding Sets of Pareto Sets in Real-World Scenarios - A Mult...
收藏 引用
13th IEEE Congress on Evolutionary Computation, CEC 2024
作者: Liu, Jiao Ong, Yew Soon Wong, Melvin College of Computing & Data Science Nanyang Technological University Singapore
Recently, evolutionary multitasking has been employed to generate a 'set of Pareto sets' (SOS) for machine learning models, addressing diverse task settings across heterogeneous environments. This involves cre... 详细信息
来源: 评论
Integrating data and Rules: A Hybrid Approach for Robust Lane Change Intention Prediction Under Distribution Shift  27
Integrating Data and Rules: A Hybrid Approach for Robust Lan...
收藏 引用
27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024
作者: Teng, Yao Long Naing, Htet Cai, Wentong College of Computing and Data Science Nanyang Technological University Singapore
Lane change intention prediction is critical in improving road safety. In general, this task is achieved via two distinct approaches: The data-based approach and the rule-based approach. Generally, the former outperfo... 详细信息
来源: 评论
Open-Vocabulary Object Detection via Language Hierarchy  38
Open-Vocabulary Object Detection via Language Hierarchy
收藏 引用
38th Conference on Neural Information Processing Systems, NeurIPS 2024
作者: Huang, Jiaxing Zhang, Jingyi Jiang, Kai Lu, Shijian College of Computing and Data Science Nanyang Technological University Singapore
Recent studies on generalizable object detection have attracted increasing attention with additional weak supervision from large-scale datasets with image-level labels. However, weakly-supervised detection learning of...
来源: 评论
Multilingual Sentiment Analysis for Investigating Perceptions of Globalization  24
Multilingual Sentiment Analysis for Investigating Perception...
收藏 引用
24th IEEE International Conference on data Mining Workshops, ICDMW 2024
作者: Ani, Anagha Cambria, Erik Nanyang Technological University College of Computing & Data Science Singapore
This paper aims to identify trends in perceptions on the topic of globalization by performing sentiment analysis on text data collected from social media posts. A novel methodology of extracting culture-informed senti... 详细信息
来源: 评论
Leveraging Prompt Engineering for Curriculum Design in Short-term Adult Training  4
Leveraging Prompt Engineering for Curriculum Design in Short...
收藏 引用
4th International Conference on Educational Technology, ICET 2024
作者: Wang, Hang Chen, Ping Ailiya Shen, Zhiqi Nanyang Technological University College of Computing and Data Science Singapore
This paper explores the integration of large language models (LLMs) into the curriculum design process for short-term adult training programs, highlighting the role of prompt engineering as a transformative tool. As a... 详细信息
来源: 评论
An Objective Metric Towards Music Mood Visualization  23
An Objective Metric Towards Music Mood Visualization
收藏 引用
23rd International Conference on Cyberworlds, CW 2024
作者: Wang, Hanqin Sourin, Alexei Nanyang Technological University College of Computing and Data Science Singapore
Music visualization is presented in different formats. The mainstream music visualization remains focused on providing animated images for visual pleasure or for enhancing the perception of sheet music with colors. St... 详细信息
来源: 评论
ECSeg: Edge-Cloud Switched Image Segmentation for Autonomous Vehicles  21
ECSeg: Edge-Cloud Switched Image Segmentation for Autonomous...
收藏 引用
21st Annual IEEE International Conference on Sensing, Communication, and Networking, SECON 2024
作者: Zhou, Siyuan Van Le, Duc Tan, Rui College of Computing and Data Science Nanyang Technological University Singapore
Existing autonomous vehicles have not utilized the cloud computing for execution of their deep learning-based driving tasks due to the long vehicle-to-cloud communication latency. Meanwhile, the vehicles are in genera... 详细信息
来源: 评论
Improving Temporal Action Segmentation and Detection with Hierarchical Task Grammar  27th
Improving Temporal Action Segmentation and Detection with ...
收藏 引用
27th International Conference on Pattern Recognition, ICPR 2024
作者: Yihui, Qiu Rajan, Deepu College of Computing and Data Science Nanyang Technological University Singapore Singapore
Human activities are inherently task-oriented, and integrating explicit task learning into action segmentation models is hypothesized to enhance performance. However, empirical evaluations using the Ego4D Goal Step da... 详细信息
来源: 评论
Diversify, Rationalize, and Combine: Ensembling Multiple QA Strategies for Zero-shot Knowledge-based VQA
Diversify, Rationalize, and Combine: Ensembling Multiple QA ...
收藏 引用
2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024
作者: Li, Miaoyu Li, Haoxin Du, Zilin Li, Boyang College of Computing and Data Science Nanyang Technological University Singapore
Knowledge-based Visual Qustion-answering (K-VQA) often requires the use of background knowledge beyond the image. However, we discover that a single knowledge generation strategy is often insufficient for all K-VQA qu... 详细信息
来源: 评论