全部 |
  • 全部
  • 题名
  • 作者
  • 机构
  • 关键词
  • NSTL主题词
  • 摘要
检索 二次检索 AI检索
外文文献 中文文献
筛选条件:

1. KuzushijiDiffuser: Japanese Kuzushiji Font Generation with FontDiffuser NSTL国家科技图书文献中心

Honghui Yuan |  Keiji Yanai -  《MultiMedia Modeling,Part II》 -  International Conference on MultiMedia Modeling - 2025, - 212~225 - 共14页

摘要:Kuzushiji characters were used in Japan |  hundreds of years ago, and many valuable ancient |  documents are written in Kuzushiji. Research into |  generating Kuzushiji characters increases the training data |  for recognizing these characters and enhances
关键词: Kuzushiji characters |  Font generation |  FontDiffuser

2. MLP-AMDC: A MLP Architecture for Adaptive-Mask-Based Dual-Camera Snapshot Hyperspectral Imaging NSTL国家科技图书文献中心

Zeyu Cai |  Can Zhang... -  《MultiMedia Modeling,Part II》 -  International Conference on MultiMedia Modeling - 2025, - 408~423 - 共16页

摘要:The coded Aperture Snapshot Spectral Imaging |  (CASSI) system has great advantages in dynamically |  acquiring Hyper-Spectral Image (HSI) compared to |  traditional measurement methods, but there are the following |  problems. 1) Traditional mask relies on random patterns
关键词: MLP |  Compressive sensing |  CASSI |  Snapshot

3. Innovative Lifelog Visualization and Exploration in Virtual Reality - A Comparative Study NSTL国家科技图书文献中心

Wolfgang Hurst |  Yannick Visser -  《MultiMedia Modeling,Part II》 -  International Conference on MultiMedia Modeling - 2025, - 141~154 - 共14页

摘要:Visual lifelogs, comprising images captured |  automatically throughout the day, present significant |  challenges for effective access and analysis due to their |  large volume and lack of context. This study evaluates |  three innovative visualization methods in virtual
关键词: Lifelog exploration |  Lifelogs in VR |  Lifelog visualization

4. MineTinyNet-YOLO: An Efficient Small Object Detection Method for Complex Underground Coal Mine Scenarios NSTL国家科技图书文献中心

Yaling Hao |  Wei Wu -  《MultiMedia Modeling,Part II》 -  International Conference on MultiMedia Modeling - 2025, - 364~378 - 共15页

摘要:The YOLO series of algorithms has become the |  primary method for real-time object detection. Many |  studies have enhanced the benchmark performance by |  adjusting model structures, updating training methods, and |  optimizing hyperparameters. However, in underground coal
关键词: Complex backgrounds |  Small target detection |  MineTinyNet-YOLO |  DBACL |  AIF-Net |  PUO

5. Hybrid Scalable Video Coding with Neural Compression and Enhancement for Streaming Media NSTL国家科技图书文献中心

Yuyao Ye |  Jiayu Yang... -  《MultiMedia Modeling,Part II》 -  International Conference on MultiMedia Modeling - 2025, - 74~86 - 共13页

摘要:Streaming media is important in modern |  information consumption industry. However the limited and |  varied computing resources and bandwidth of client |  devices pose challenges for video coding. To make a |  balance between speed and coding efficiency and provide
关键词: Video coding |  Scalable codec |  Video enhancement

6. Lightweight Dual Grouped Large-Kernel Convolutions for Salient Object Detection Network NSTL国家科技图书文献中心

Jiajie Liu |  Zhibin Zhang -  《MultiMedia Modeling,Part II》 -  International Conference on MultiMedia Modeling - 2025, - 240~253 - 共14页

摘要:Most existing Salient Object Detection (SOD | ) methods focus on achieving better performance, often |  resulting in models with a large number of parameters | . However, there is limited research on lightweight models |  in this field. To address this gap, our goal is to
关键词: Segmentation |  Matting |  Lightweight network

7. Grounding Deliberate Reasoning in Multimodal Large Language Models NSTL国家科技图书文献中心

Jiaxing Chen |  Yuxuan Liu... -  《MultiMedia Modeling,Part II》 -  International Conference on MultiMedia Modeling - 2025, - 17~30 - 共14页

摘要:The rise of Multimodal Large Language Models | , renowned for their advanced instruction-following and |  reasoning capabilities, has significantly propelled the |  field of visual reasoning. However, due to limitations |  in their image tokenization, most MLLMs struggle to
关键词: MLLMs |  Visual reasoning |  Deliberate reasoning

8. Image-Generation AI Model Retrieval by Contrastive Learning-Based Style Distance Calculation NSTL国家科技图书文献中心

Vu Thi Ngoc Anh |  Yoshiyuki Shoji... -  《MultiMedia Modeling,Part II》 -  International Conference on MultiMedia Modeling - 2025, - 101~114 - 共14页

摘要:This paper proposes a method for retrieving |  trained image-generation LoRA (Low-Rank Adaptation | ) models. This search algorithm takes a single arbitrary |  image input and then ranks the models in the order in |  which they will likely transform the image to the same
关键词: Metric learning |  Triplet network |  LoRA search

9. Mix-YOLONet: Deep Image Dehazing for Improving Object Detection NSTL国家科技图书文献中心

Xin Lim |  Lai-Kuan Wong... -  《MultiMedia Modeling,Part II》 -  International Conference on MultiMedia Modeling - 2025, - 379~393 - 共15页

摘要:Atmospheric haze significantly impairs the |  performance of computer vision tasks such as image dehazing |  and object detection. Existing methods often address |  these tasks independently, failing to provide an |  integrated solution that can effectively handle hazy
关键词: Object detection |  Image restoration |  Image dehazing |  Joint network |  Adverse weather condition

10. Making Strides Security in Multimodal Fake News Detection Models: A Comprehensive Analysis of Adversarial Attacks NSTL国家科技图书文献中心

Jiahua Si |  Youze Wang... -  《MultiMedia Modeling,Part II》 -  International Conference on MultiMedia Modeling - 2025, - 296~309 - 共14页

摘要:With the rise of social media as a crucial |  data source, fake news has proliferated, posing |  significant challenges to data accuracy and societal well | -being. Our research investigates the impact of |  multimedia on the rapid dissemination of fake news
关键词: Multimodal |  Fake news detection |  Adversarial attack
检索条件出处:MultiMedia Modeling,Part II
  • 检索词扩展

NSTL主题词

  • NSTL学科导航