{"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/vemoclap-a-video-emotion-classification-web","title":"VEMOCLAP: A video emotion classification web application","arxiv_id":"2410.21303","date":"2024-10-22","proceeding":null,"authors":["Serkan Sulun","Paula Viana","Matthew E. P. Davies"],"abstract":"We introduce VEMOCLAP: Video EMOtion Classifier using Pretrained features, the first readily available and open-source web application that analyzes the emotional content of any user-provided video. We improve our previous work, which exploits open-source pretrained models that work on video frames and audio, and then efficiently fuse the resulting pretrained features using multi-head cross-attention. Our approach increases the state-of-the-art classification accuracy on the Ekman-6 video emotion dataset by 4.3% and offers an online application for users to run our model on their own videos or YouTube videos. We invite the readers to try our application at serkansulun.com/app.","url_abs":"https://arxiv.org/abs/2410.21303v1","url_pdf":"https://arxiv.org/pdf/2410.21303v1.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":"classification-1","task_name":"Classification"},{"task_slug":"emotion-classification","task_name":"Emotion Classification"},{"task_slug":"video-emotion-recognition","task_name":"Video Emotion Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-emotion-recognition-on-ekman6","task":"Video Emotion Recognition","dataset":"Ekman6","model":"VEMOCLAP","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"65.28"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}