{"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/heterogeneous-knowledge-transfer-in-video","title":"Heterogeneous Knowledge Transfer in Video Emotion Recognition, Attribution and Summarization","arxiv_id":"1511.04798","date":"2015-11-16","proceeding":null,"authors":["Baohan Xu","Yanwei Fu","Yu-Gang Jiang","Boyang Li","Leonid Sigal"],"abstract":"Emotion is a key element in user-generated videos. However, it is difficult\nto understand emotions conveyed in such videos due to the complex and\nunstructured nature of user-generated content and the sparsity of video frames\nexpressing emotion. In this paper, for the first time, we study the problem of\ntransferring knowledge from heterogeneous external sources, including image and\ntextual data, to facilitate three related tasks in understanding video emotion:\nemotion recognition, emotion attribution and emotion-oriented summarization.\nSpecifically, our framework (1) learns a video encoding from an auxiliary\nemotional image dataset in order to improve supervised video emotion\nrecognition, and (2) transfers knowledge from an auxiliary textual corpora for\nzero-shot recognition of emotion classes unseen during training. The proposed\ntechnique for knowledge transfer facilitates novel applications of emotion\nattribution and emotion-oriented summarization. A comprehensive set of\nexperiments on multiple datasets demonstrate the effectiveness of our\nframework.","url_abs":"http://arxiv.org/abs/1511.04798v2","url_pdf":"http://arxiv.org/pdf/1511.04798v2.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":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"video-emotion-recognition","task_name":"Video Emotion Recognition"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[{"slug":"ekman6","name":"Ekman6","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-emotion-recognition-on-ekman6","task":"Video Emotion Recognition","dataset":"Ekman6","model":"ITE","rank_in_archive_order":6,"of":6,"metrics":{"Accuracy":"51.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.04798","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}