{"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/deep-aesthetic-quality-assessment-with","title":"Deep Aesthetic Quality Assessment with Semantic Information","arxiv_id":"1604.04970","date":"2016-04-18","proceeding":null,"authors":["Yueying Kao","Ran He","Kaiqi Huang"],"abstract":"Human beings often assess the aesthetic quality of an image coupled with the\nidentification of the image's semantic content. This paper addresses the\ncorrelation issue between automatic aesthetic quality assessment and semantic\nrecognition. We cast the assessment problem as the main task among a multi-task\ndeep model, and argue that semantic recognition task offers the key to address\nthis problem. Based on convolutional neural networks, we employ a single and\nsimple multi-task framework to efficiently utilize the supervision of aesthetic\nand semantic labels. A correlation item between these two tasks is further\nintroduced to the framework by incorporating the inter-task relationship\nlearning. This item not only provides some useful insight about the correlation\nbut also improves assessment accuracy of the aesthetic task. Particularly, an\neffective strategy is developed to keep a balance between the two tasks, which\nfacilitates to optimize the parameters of the framework. Extensive experiments\non the challenging AVA dataset and Photo.net dataset validate the importance of\nsemantic recognition in aesthetic quality assessment, and demonstrate that\nmulti-task deep models can discover an effective aesthetic representation to\nachieve state-of-the-art results.","url_abs":"http://arxiv.org/abs/1604.04970v3","url_pdf":"http://arxiv.org/pdf/1604.04970v3.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":[],"tasks":[{"task_slug":"aesthetics-quality-assessment","task_name":"Aesthetics Quality Assessment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/aesthetics-quality-assessment-on-ava","task":"Aesthetics Quality Assessment","dataset":"AVA","model":"MTRLCNN","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy":"79.1%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}