{"url":"/task/video-emotion-recognition","name":"Video Emotion Recognition","slug":"video-emotion-recognition","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":29,"papers_with_code":9,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-emotion-recognition-on-ekman6","slug":"video-emotion-recognition-on-ekman6","dataset":"Ekman6","dataset_url":"/dataset/ekman6","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VEMOCLAP","paper_title":"VEMOCLAP: A video emotion classification web application","paper_url":"/paper/vemoclap-a-video-emotion-classification-web","paper_date":"2024-10-22","arxiv_id":"2410.21303","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-emotion-recognition-on-crema-d","slug":"video-emotion-recognition-on-crema-d","dataset":"CREMA-D","dataset_url":"/dataset/crema-d","rows_in_archive":4,"metrics":["Accuracy","WAR"],"first_row_in_archive_order":{"model":"VAEmo","paper_title":"VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection","paper_url":"/paper/vaemo-efficient-representation-learning-for","paper_date":"2025-05-05","arxiv_id":"2505.02331","code_links":[{"title":"MSA-LMC/VAEmo","url":"https://github.com/MSA-LMC/VAEmo"}],"syntology":null}}],"datasets":[{"url":"/dataset/crema-d","name":"CREMA-D","full_name":"CREMA-D","num_papers_in_archive":28},{"url":"/dataset/ravdess","name":"RAVDESS","full_name":"Ryerson Audio-Visual Database of Emotional Speech and Song","num_papers_in_archive":27},{"url":"/dataset/ekman6","name":"Ekman6","full_name":"","num_papers_in_archive":11},{"url":"/dataset/candor-corpus-1","name":"CANDOR Corpus","full_name":"CANDOR = Conversation: A Naturalistic Dataset of Online Recordings","num_papers_in_archive":1},{"url":"/dataset/l-svd","name":"L-SVD","full_name":"Large-Scale Selfie Video Dataset (L-SVD): A Benchmark for Emotion Recognition","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/emotion-recognition","name":"Emotion Recognition"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":9,"of":9,"tagged_in_all":29,"items":[{"url":"/paper/emotion-recognition-in-audio-and-video-using","title":"Emotion Recognition in Audio and Video Using Deep Neural Networks","date":"2020-06-15","arxiv_id":"2006.08129","repositories_listed":2,"syntology":null},{"url":"/paper/mimamo-net-integrating-micro-and-macro-motion","title":"MIMAMO Net: Integrating Micro- and Macro-motion for Video Emotion Recognition","date":"2019-11-21","arxiv_id":"1911.09784","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/vaemo-efficient-representation-learning-for","title":"VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection","date":"2025-05-05","arxiv_id":"2505.02331","repositories_listed":1,"syntology":null},{"url":"/paper/mtcae-dfer-multi-task-cascaded-autoencoder","title":"MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition","date":"2024-12-25","arxiv_id":"2412.18988","repositories_listed":1,"syntology":null},{"url":"/paper/multimae-der-multimodal-masked-autoencoder","title":"MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition","date":"2024-04-28","arxiv_id":"2404.18327","repositories_listed":1,"syntology":null},{"url":"/paper/emotions-a-large-scale-dataset-for-emotion","title":"Towards Emotion Analysis in Short-form Videos: A Large-Scale Dataset and Baseline","date":"2023-11-29","arxiv_id":"2311.17335","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-video-emotion-detection-and","title":"Weakly Supervised Video Emotion Detection and Prediction via Cross-Modal Temporal Erasing Network","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fv2es-a-fully-end2end-multimodal-system-for","title":"FV2ES: A Fully End2End Multimodal System for Fast Yet Effective Video Emotion Recognition Inference","date":"2022-09-21","arxiv_id":"2209.10170","repositories_listed":1,"syntology":null},{"url":"/paper/technical-report-for-valence-arousal","title":"Technical Report for Valence-Arousal Estimation on Affwild2 Dataset","date":"2021-05-04","arxiv_id":"2105.01502","repositories_listed":1,"syntology":null}],"syntology_records":1,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}