Photographs are characterized by different compositional attributes like the Rule of Thirds, depth of field, vanishing-lines etc. The presence or absence of one or more of these attributes contributes to the overall artistic value of an image. In this work, we analyze the ability of deep learning based methods to learn such photographic style attributes. We observe that although a standard CNN learns the texture and appearance based features reasonably well, its understanding of global and geometric features is limited by two factors. First, the data-augmentation strategies (cropping, warping, etc.) distort the composition of a photograph and affect the performance. Secondly, the CNN features, in principle, are translation-invariant and appearance-dependent. But some geometric properties important for aesthetics, e.g. the Rule of Thirds (RoT), are position-dependent and appearance-invariant. Therefore, we propose a novel input representation which is geometry-sensitive, position-cognizant and appearance-invariant. We further introduce a two-column CNN architecture that performs better than the state-of-the-art (SoA) in photographic style classification. From our results, we observe that the proposed network learns both the geometric and appearance-based attributes better than the SoA.
Personalized Image Filter: Mastering Your Photographic Style
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（国家通用人工智能重点实验室，智能科学与技术学院，北京大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；State Key Laboratory of Multimedia Information Processing and National Engineering Research Center of Visual Technology, School of Computer Science, Peking University（多媒体信息处理国家重点实验室和视觉技术国家工程研究中心，计算机科学学院，北京大学）；School of Artificial Intelligence, Beijing University of Posts and Telecommunications（人工智能学院，北京邮电大学）
SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
ROSE Lab, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore（南洋理工大学罗思实验室，跨学科研究生项目，新加坡）；ROSE Lab, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore（南洋理工大学罗思实验室，电子与电气工程学院，新加坡）；City University of Hong Kong, Hong Kong SAR（香港城市大学，香港特别行政区）；Shanghai Jiao Tong University, China（上海交通大学，中国）；Singapore University of Technology and Design, Singapore（新加坡科技设计大学，新加坡）；VinUniversity, Hanoi, Vietnam（越南文大学，河内，越南）
AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generation
South China University of Technology（华南理工大学）；Ludwig Maximilian University of Munich（慕尼黑大学）；Swiss Federal Institute of Technology（苏黎世联邦理工学院）；CRRC Institute（中车研究院）；The Hong Kong Polytechnic University（香港理工大学）；Anyang Normal University（安阳师范学院）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
University of California, Berkeley（加州大学伯克利分校）；Adobe（Adobe公司）
图像的风格在人们如何看待它方面起着重要的作用，但风格在计算机视觉研究中很少受到关注。我们描述了一种预测图像风格的方法，并对这些任务的不同图像特征进行了全面的评估。我们发现，在多层网络中学习的特征通常表现最好-即使是在使用对象类（而不是样式）标签进行训练时。我们的大规模学习方法在现有的美学评级和摄影风格注释数据集上获得了最佳的公开表现。我们提出了两个新的数据集：80 K Flickr的照片与20策展风格标签注释，和85 K的绘画与25风格/流派标签注释。我们的方法在两个数据集上都表现出了出色的分类性能。我们使用学习的分类器来扩展传统的基于标签的图像搜索，以考虑风格约束，并展示跨数据集的风格理解。
An easy zero-shot learning combination: Texture Sensitive Semantic Segmentation IceHrNet and Advanced Style Transfer Learning Strategy
Hohai University（河海大学）；Nanjing Research Institute of Hydrology and Water Conservation Automation, Ministry of Water Resources（水利部南京水利水文自动化研究所）；Nanjing Zhongyu Intelligent Water Conservancy Research Institute Co., Ltd（南京中禹智慧水利研究院有限公司）
Learning Invariant Inter-pixel Correlations for Superpixel Generation
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；Beijing Key Laboratory of Advanced Information Science and Network Technology（北京市高级信息科学与网络技术重点实验室）；Frontiers Science Center for Smart High-speed Railway System, Beijing Jiaotong University（北京交通大学智慧高铁系统前沿科学中心）；DaoAI Robotics Inc.（道智机器人公司）
