{"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/learning-grimaces-by-watching-tv","title":"Learning Grimaces by Watching TV","arxiv_id":"1610.02255","date":"2016-10-07","proceeding":null,"authors":["Samuel Albanie","Andrea Vedaldi"],"abstract":"Differently from computer vision systems which require explicit supervision,\nhumans can learn facial expressions by observing people in their environment.\nIn this paper, we look at how similar capabilities could be developed in\nmachine vision. As a starting point, we consider the problem of relating facial\nexpressions to objectively measurable events occurring in videos. In\nparticular, we consider a gameshow in which contestants play to win significant\nsums of money. We extract events affecting the game and corresponding facial\nexpressions objectively and automatically from the videos, obtaining large\nquantities of labelled data for our study. We also develop, using benchmarks\nsuch as FER and SFEW 2.0, state-of-the-art deep neural networks for facial\nexpression recognition, showing that pre-training on face verification data can\nbe highly beneficial for this task. Then, we extend these models to use facial\nexpressions to predict events in videos and learn nameable expressions from\nthem. The dataset and emotion recognition models are available at\nhttp://www.robots.ox.ac.uk/~vgg/data/facevalue","url_abs":"http://arxiv.org/abs/1610.02255v1","url_pdf":"http://arxiv.org/pdf/1610.02255v1.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":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"face-verification","task_name":"Face Verification"},{"task_slug":"facial-expression-recognition-1","task_name":"Facial Expression Recognition"},{"task_slug":"facial-expression-recognition","task_name":"Facial Expression Recognition (FER)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/facial-expression-recognition-on-static","task":"Facial Expression Recognition (FER)","dataset":"Static Facial Expressions in the Wild","model":"VGG-VD-16","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"54.82%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.02255","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}