{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/image-aesthetic-assessment-an-experimental","title":"Image Aesthetic Assessment: An Experimental Survey","arxiv_id":"1610.00838","date":"2016-10-04","proceeding":null,"authors":["Yubin Deng","Chen Change Loy","Xiaoou Tang"],"abstract":"This survey aims at reviewing recent computer vision techniques used in the\nassessment of image aesthetic quality. Image aesthetic assessment aims at\ncomputationally distinguishing high-quality photos from low-quality ones based\non photographic rules, typically in the form of binary classification or\nquality scoring. A variety of approaches has been proposed in the literature\ntrying to solve this challenging problem. In this survey, we present a\nsystematic listing of the reviewed approaches based on visual feature types\n(hand-crafted features and deep features) and evaluation criteria (dataset\ncharacteristics and evaluation metrics). Main contributions and novelties of\nthe reviewed approaches are highlighted and discussed. In addition, following\nthe emergence of deep learning techniques, we systematically evaluate recent\ndeep learning settings that are useful for developing a robust deep model for\naesthetic scoring. Experiments are conducted using simple yet solid baselines\nthat are competitive with the current state-of-the-arts. Moreover, we discuss\nthe possibility of manipulating the aesthetics of images through computational\napproaches. We hope that our survey could serve as a comprehensive reference\nsource for future research on the study of image aesthetic assessment.","url_abs":"http://arxiv.org/abs/1610.00838v2","url_pdf":"http://arxiv.org/pdf/1610.00838v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"image-aesthetic-assessment-an-experimental","repo_url":"https://github.com/AemikaChow/DATASOURCE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"survey","task_name":"Survey"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1610.00838","atlas_url":"https://app.syntology.ai/?focus=1610.00838","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}