Visual knowledge: an attempt to explore machine creativity
- 28 May 2021
- journal article
- editorial
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 22 (5), 619-624
- https://doi.org/10.1631/fitee.2100116
Abstract
概要 长期以来困扰人工智能领域的一个问题是: 人工智能是否具有创造力, 或者说, 算法的推理过程是否可以具有创造性. 本文从思维科学的角度探讨人工智能创造力的问题. 首先, 列举形象思维推理的相关研究; 然后, 重点介绍一种特殊的视觉知识表示形式, 即视觉场景图; 最后, 详细介绍视觉场景图构造问题与潜在应用. 所有证据表明, 视觉知识和视觉思维不仅可以改善当前人工智能任务的性能, 而且可以用于机器创造力的实践.This publication has 23 references indexed in Scilit:
- Multiple Knowledge Representation of Artificial IntelligenceEngineering, 2019
- On visual knowledgeFrontiers of Information Technology & Electronic Engineering, 2019
- Graph R-CNN for Scene Graph GenerationPublished by Springer Science and Business Media LLC ,2018
- Image Generation from Scene GraphsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- Visual Relationship Detection with Internal and External Linguistic Knowledge DistillationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Visual Translation Embedding Network for Visual Relation DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image AnnotationsInternational Journal of Computer Vision, 2017
- Automatic Generation of Visual-Textual Presentation LayoutACM Transactions on Multimedia Computing, Communications, and Applications, 2016
- Imagery and ThinkingPublished by Springer Science and Business Media LLC ,1991
- The Split Brain in ManScientific American, 1967