NSTL国家科技图书文献中心

1. LayoutFlow: Flow Matching for Layout Generation NSTL国家科技图书文献中心

Julian Jorge Andrade... | Naoto Inoue ... - 《Computer Vision - ECCV 2024,Part XXXVI》 - European Conference on Computer Vision - 2025, - 56～72 - 共17页

摘要：Finding a suitable layout represents a crucial task for diverse applications in graphic design. Motivated by simpler and smoother sampling trajectories, we explore the use of Flow Matching as an alter...

关键词： Layout generation | Flow matching | Generative models

2. Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation NSTL国家科技图书文献中心

Daichi Horita | Naoto Inoue ... - 《2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition》 - IEEE/CVF Conference on Computer Vision and Pattern Recognition - 2024, - 67～76 - 共10页

摘要：Content-aware graphic layout generation aims to automatically arrange visual elements along with a given content, such as an e-commerce product image. In this paper, we argue that the current layout g...

关键词： Visualization | Computer vision | Layout | Training data | Computer architecture | Transformers | Generators

3. LayoutDM: Discrete Diffusion Model for Controllable Layout Generation NSTL国家科技图书文献中心

Naoto Inoue | Kotaro Kikuchi ... - 《2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition: CVPR 2023, Vancouver, British Columbia, Canada, 18-22 June 2023, [v.11]》 - IEEE/CVF Conference on Computer Vision and Pattern Recognition - 2023, - 10167～10176 - 共10页

摘要：Controllable layout generation aims at synthesizing plausible arrangement of element bounding boxes with optional constraints, such as type or position of a specific element. In this work, we try to s...

关键词： Computer vision | Codes | Computational modeling | Layout | Data models | Pattern recognition | Task analysis

4. Generative Colorization of Structured Mobile Web Pages NSTL国家科技图书文献中心

Kotaro Kikuchi | Naoto Inoue ... - 《2023 IEEE/CVF Winter Conference on Applications of Computer Vision: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 02-07 January 2023, Waikoloa, HI, USA》 - IEEE/CVF Winter Conference on Applications of Computer Vision - 2023, - 3639～3648 - 共10页

摘要：Color is a critical design factor for web pages, affecting important factors such as viewer emotions and the overall trust and satisfaction of a website. Effective coloring requires design knowledge a...

关键词： Data-driven modeling | Computer vision | Protocols | Codes | Image color analysis | Message passing | Web pages

5. Towards Flexible Multi-modal Document Models NSTL国家科技图书文献中心

Naoto Inoue | Kotaro Kikuchi ... - 《2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition: CVPR 2023, Vancouver, British Columbia, Canada, 18-22 June 2023, [v.11]》 - IEEE/CVF Conference on Computer Vision and Pattern Recognition - 2023, - 14287～14296 - 共10页

摘要：Creative workflows for generating graphical documents involve complex inter-related tasks, such as aligning elements, choosing appropriate fonts, or employing aesthetically harmonious colors. In this ...

关键词： Graphics | Computer vision | Codes | Image color analysis | Computational modeling | Buildings | Computer architecture

6. Learning From Synthetic Shadows for Shadow Detection and Removal SCOPUS Scopus数据库 EI 工程索引 SCIE Web of Science核心 NSTL国家科技图书文献中心

Naoto Inoue | Toshihiko Yamasaki - 《IEEE Transactions on Circuits and Systems for Video Technology》 - 2021,31(11) - 4187～4197 - 共11页 - 被引量：21

摘要：Shadow removal is an essential task in computer vision and computer graphics. Recent shadow removal approaches all train convolutional neural networks (CNN) on real paired shadow/shadow-free or shadow...

关键词： Lighting | Attenuation | Pipelines | Computational modeling | Cameras | Three-dimensional displays | Shape | Shadow removal | shadow detection

7. Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation NSTL国家科技图书文献中心

Takehiko Ohkawa | Naoto Inoue ... - 《25th International Conference on Pattern Recognition: 25th International Conference on Pattern Recognition (ICPR), 10–15 January 2021, Milan, Italy》 - International Conference on Pattern Recognition - 2021, - 362～369 - 共8页

摘要：Unpaired image-to-image (I2I) translation has received considerable attention in pattern recognition and computer vision because of recent advancements in generative adversarial networks (GANs). Howev...

关键词： Training | Computer vision | Computational modeling | Semisupervised learning | Generative adversarial networks | Pattern recognition | Image reconstruction

NSTL主题词： cyclic

8. Ecological, physiological, and biomechanical differences between gametophytes and sporophytes of Chondrus ocellatus (Gigartinales, Rhodophyta)1 NSTL国家科技图书文献中心

Mitsunobu Kamiya | Naoto Inoue ... - 《Journal of phycology》 - 2021,57(5) - 1590～1603 - 共14页 - 被引量：4

摘要：Although variation among habitats in the ratio of gametophytes to sporophytes has been reported in various gigartinacean species, factors controlling the phase ratio remain poorly understood. Over 18 ...

关键词： carrageenan | desiccation tolerance | fertility | flexibility | growth rate | isomorphic life cycle | phase ratio | stiffness | wave exposure

9. Learning from Synthetic Shadows NSTL国家科技图书文献中心

Naoto INOUE | Toshihiko YAMASAKI - 《電子情報通信学会技術研究報告. 情報システムソサイエティ各誌》 - 2020,120(409) - 133～138 - 共6页

摘要：Shadow removal is essential for some downstream tasks in computer vision and computer graphics. Recent shadow removal approaches all train convolutional neural networks (CNN) on real paired shadow/sha...

关键词： Shadow removal | Shadow detection | CNN

10. Fast Instance Segmentation for Line Drawing Vectorization NSTL国家科技图书文献中心

Naoto Inoue | Toshihiko Yamasaki - 《2019 IEEE Fifth International Conference on Multimedia Big Data: BigMM 2019, Singapore, 11-13 September 2019》 - IEEE International Conference on Multimedia Big Data - 2019, - 262～265 - 共4页

摘要：In this paper, we present a fast raster-to-vector method for line art images based on a convolutional neural network (CNN). State-of-the-art approaches for vectorization are very slow because they mos...