Actively Learning Human Gaze Shifting Paths for Semantics-Aware Photo Cropping
文献类型：期刊论文
| 作者 | Zhang, Luming1; Gao, Yue2; Ji, Rongrong3; Xia, Yingjie4; Dai, Qionghai2; Li, Xuelong5
|
| 刊名 | ieee transactions on image processing
 |
| 出版日期 | 2014-05-01 |
| 卷号 | 23期号:5页码:2235-2245 |
| 关键词 | Photo cropping semantics active graphlet path aesthetics |
| ISSN号 | 1070-986x |
| 英文摘要 | photo cropping is a widely used tool in printing industry, photography, and cinematography. conventional cropping models suffer from the following three challenges. first, the deemphasized role of semantic contents that are many times more important than low-level features in photo aesthetics. second, the absence of a sequential ordering in the existing models. in contrast, humans look at semantically important regions sequentially when viewing a photo. third, the difficulty of leveraging inputs from multiple users. experience from multiple users is particularly critical in cropping as photo assessment is quite a subjective task. to address these challenges, this paper proposes semantics-aware photo cropping, which crops a photo by simulating the process of humans sequentially perceiving semantically important regions of a photo. we first project the local features (graphlets in this paper) onto the semantic space, which is constructed based on the category information of the training photos. an efficient learning algorithm is then derived to sequentially select semantically representative graphlets of a photo, and the selecting process can be interpreted by a path, which simulates humans actively perceiving semantics in a photo. furthermore, we learn a prior distribution of such active graphlet paths from training photos that are marked as aesthetically pleasing by multiple users. the learned priors enforce the corresponding active graphlet path of a test photo to be maximally similar to those from the training photos. experimental results show that: 1) the active graphlet path accurately predicts human gaze shifting, and thus is more indicative for photo aesthetics than conventional saliency maps and 2) the cropped photos produced by our approach outperform its competitors in both qualitative and quantitative comparisons. |
| WOS标题词 | science & technology ; technology |
| 类目[WOS] | computer science, artificial intelligence ; engineering, electrical & electronic |
| 研究领域[WOS] | computer science ; engineering |
| 关键词[WOS] | object retrieval ; recognition ; classification ; manifold |
| 收录类别 | SCI ; EI |
| 语种 | 英语 |
| WOS记录号 | WOS:000334677900003 |
| 公开日期 | 2015-03-18 |
| 源URL | [http://ir.opt.ac.cn/handle/181661/22375]  |
| 专题 | 西安光学精密机械研究所_光学影像学习与分析中心 |
| 作者单位 | 1.Natl Univ Singapore, Sch Comp, Singapore 117548, Singapore 2.Tsinghua Univ, Tsinghua Natl Lab Informat Sci & Technol, Dept Automat, Beijing 100084, Peoples R China 3.Xiamen Univ, Sch Informat Sci & Engn, Dept Cognit Sci, Xiamen 361000, Peoples R China 4.Hangzhou Normal Univ, Hangzhou Inst Serv Engn, Hangzhou, Zhejiang, Peoples R China 5.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr Opt IMagery Anal & Learning OPTIMAL, State Key Lab Transient Opt & Photon, Xian 710119, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Luming,Gao, Yue,Ji, Rongrong,et al. Actively Learning Human Gaze Shifting Paths for Semantics-Aware Photo Cropping[J]. ieee transactions on image processing,2014,23(5):2235-2245. |
| APA | Zhang, Luming,Gao, Yue,Ji, Rongrong,Xia, Yingjie,Dai, Qionghai,&Li, Xuelong.(2014).Actively Learning Human Gaze Shifting Paths for Semantics-Aware Photo Cropping.ieee transactions on image processing,23(5),2235-2245. |
| MLA | Zhang, Luming,et al."Actively Learning Human Gaze Shifting Paths for Semantics-Aware Photo Cropping".ieee transactions on image processing 23.5(2014):2235-2245. |
入库方式： OAI收割
来源：西安光学精密机械研究所
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。