Theme-Aware Aesthetic Distribution Prediction With Full-Resolution Photographs
文献类型：期刊论文
| 作者 | Jia, Gengyun3,4 ; Li, Peipei2; He, Ran1,4
|
| 刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
 |
| 出版日期 | 2022-03-03 |
| 页码 | 15 |
| 关键词 | Aesthetic quality assessment (AQA) full resolution region of image (RoM) pooling theme |
| ISSN号 | 2162-237X |
| DOI | 10.1109/TNNLS.2022.3151787 |
| 通讯作者 | He, Ran(rhe@nlpr.ia.ac.cn) |
| 英文摘要 | Aesthetic quality assessment (AQA) is a challenging task due to complex aesthetic factors. Currently, it is common to conduct AQA using deep neural networks (DNNs) that require fixed-size inputs. The existing methods mainly transform images by resizing, cropping, and padding or use adaptive pooling to alternately capture the aesthetic features from fixed-size inputs. However, these transformations potentially damage aesthetic features. To address this issue, we propose a simple but effective method to accomplish full-resolution image AQA by combining image padding with region of image (RoM) pooling. Padding turns inputs into the same size. RoM pooling pools image features and discards extra padded features to eliminate the side effects of padding. In addition, the image aspect ratios are encoded and fused with visual features to remedy the shape information loss of RoM pooling. Furthermore, we observe that the same image may receive different aesthetic evaluations under different themes, which we call the theme criterion bias. Hence, a theme-aware model that uses theme information to guide model predictions is proposed. Finally, we design an attention-based feature fusion module to effectively use both the shape and theme information. Extensive experiments prove the effectiveness of the proposed method over state-of-the-art methods. |
| WOS关键词 | IMAGE ; PHOTO |
| 资助项目 | National Natural Science Foundation of China[U20A20223] ; Beijing Nova Program[Z211100002121106] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000767831600001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China ; Beijing Nova Program |
| 源URL | [http://ir.ia.ac.cn/handle/173211/48020]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | He, Ran |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, CAS Ctr Excellence Brain Sci & Intelligence Tech, Natl Lab Pattern Recognit,Ctr Res Intelligent Per, Beijing 100190, Peoples R China 2.Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing 100876, Peoples R China 3.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Jia, Gengyun,Li, Peipei,He, Ran. Theme-Aware Aesthetic Distribution Prediction With Full-Resolution Photographs[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022:15. |
| APA | Jia, Gengyun,Li, Peipei,&He, Ran.(2022).Theme-Aware Aesthetic Distribution Prediction With Full-Resolution Photographs.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,15. |
| MLA | Jia, Gengyun,et al."Theme-Aware Aesthetic Distribution Prediction With Full-Resolution Photographs".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022):15. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。