{"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/predicting-first-impressions-with-deep","title":"Predicting First Impressions with Deep Learning","arxiv_id":"1610.08119","date":"2016-10-25","proceeding":null,"authors":["Mel McCurrie","Fernando Beletti","Lucas Parzianello","Allen Westendorp","Samuel Anthony","Walter Scheirer"],"abstract":"Describable visual facial attributes are now commonplace in human biometrics\nand affective computing, with existing algorithms even reaching a sufficient\npoint of maturity for placement into commercial products. These algorithms\nmodel objective facets of facial appearance, such as hair and eye color,\nexpression, and aspects of the geometry of the face. A natural extension, which\nhas not been studied to any great extent thus far, is the ability to model\nsubjective attributes that are assigned to a face based purely on visual\njudgements. For instance, with just a glance, our first impression of a face\nmay lead us to believe that a person is smart, worthy of our trust, and perhaps\neven our admiration - regardless of the underlying truth behind such\nattributes. Psychologists believe that these judgements are based on a variety\nof factors such as emotional states, personality traits, and other physiognomic\ncues. But work in this direction leads to an interesting question: how do we\ncreate models for problems where there is no ground truth, only measurable\nbehavior? In this paper, we introduce a new convolutional neural network-based\nregression framework that allows us to train predictive models of crowd\nbehavior for social attribute assignment. Over images from the AFLW face\ndatabase, these models demonstrate strong correlations with human crowd\nratings.","url_abs":"http://arxiv.org/abs/1610.08119v2","url_pdf":"http://arxiv.org/pdf/1610.08119v2.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":"predicting-first-impressions-with-deep","repo_url":"https://github.com/mel-2445/Predicting-First-Impressions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}