{"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/enriched-long-term-recurrent-convolutional","title":"Enriched Long-term Recurrent Convolutional Network for Facial Micro-Expression Recognition","arxiv_id":"1805.08417","date":"2018-05-22","proceeding":null,"authors":["Huai-Qian Khor","John See","Raphael C. -W. Phan","Weiyao Lin"],"abstract":"Facial micro-expression (ME) recognition has posed a huge challenge to\nresearchers for its subtlety in motion and limited databases. Recently,\nhandcrafted techniques have achieved superior performance in micro-expression\nrecognition but at the cost of domain specificity and cumbersome parametric\ntunings. In this paper, we propose an Enriched Long-term Recurrent\nConvolutional Network (ELRCN) that first encodes each micro-expression frame\ninto a feature vector through CNN module(s), then predicts the micro-expression\nby passing the feature vector through a Long Short-term Memory (LSTM) module.\nThe framework contains two different network variants: (1) Channel-wise\nstacking of input data for spatial enrichment, (2) Feature-wise stacking of\nfeatures for temporal enrichment. We demonstrate that the proposed approach is\nable to achieve reasonably good performance, without data augmentation. In\naddition, we also present ablation studies conducted on the framework and\nvisualizations of what CNN \"sees\" when predicting the micro-expression classes.","url_abs":"http://arxiv.org/abs/1805.08417v1","url_pdf":"http://arxiv.org/pdf/1805.08417v1.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":"enriched-long-term-recurrent-convolutional","repo_url":"https://github.com/IcedDoggie/Micro-Expression-with-Deep-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"enriched-long-term-recurrent-convolutional","repo_url":"https://github.com/mg515/lie-detektor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"micro-expression-recognition-1","task_name":"Micro Expression Recognition"},{"task_slug":"micro-expression-recognition","task_name":"Micro-Expression Recognition"},{"task_slug":"specificity","task_name":"Specificity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.08417","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}