{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":29,"of":29,"of_with_code":9,"tagged_in_all":29,"counts":{"archive_papers_tagged":29,"with_a_code_link":9,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":29,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/emotion-recognition-in-audio-and-video-using","slug":"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","slug":"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":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mimamo-net-integrating-micro-and-macro-motion#ran","syntology_url":"https://syntology.ai/paper/1911.09784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.09784"}},"official":{"repos":["wtomin/MIMAMO-Net"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vaemo-efficient-representation-learning-for","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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},{"url":null,"slug":"visual-and-textual-prompts-for-enhancing","title":"Visual and textual prompts for enhancing emotion recognition in video","date":"2025-04-24","arxiv_id":"2504.17224","repositories_listed":0,"syntology":null},{"url":"/paper/vemoclap-a-video-emotion-classification-web","slug":"vemoclap-a-video-emotion-classification-web","title":"VEMOCLAP: A video emotion classification web application","date":"2024-10-22","arxiv_id":"2410.21303","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02421","title":"FE-Adapter: Adapting Image-based Emotion Classifiers to Videos","date":"2024-08-05","arxiv_id":"2408.02421","repositories_listed":0,"syntology":null},{"url":null,"slug":"mart-masked-affective-representation-learning","title":"MART: Masked Affective RepresenTation Learning via Masked Temporal Distribution Distillation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"emotion-recognition-by-video-a-review","title":"Affective Video Content Analysis: Decade Review and New Perspectives","date":"2023-10-26","arxiv_id":"2310.17212","repositories_listed":0,"syntology":null},{"url":null,"slug":"fuzzy-approach-for-audio-video-emotion","title":"Fuzzy Approach for Audio-Video Emotion Recognition in Computer Games for Children","date":"2023-08-31","arxiv_id":"2309.00138","repositories_listed":0,"syntology":null},{"url":"/paper/versatile-audio-visual-learning-for-handling","slug":"versatile-audio-visual-learning-for-handling","title":"Versatile audio-visual learning for emotion recognition","date":"2023-05-12","arxiv_id":"2305.07216","repositories_listed":0,"syntology":null},{"url":"/paper/representation-learning-through-multimodal","slug":"representation-learning-through-multimodal","title":"Representation Learning through Multimodal Attention and Time-Sync Comments for Affective Video Content Analysis","date":"2022-10-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"icanet-a-method-of-short-video-emotion","title":"ICANet: A Method of Short Video Emotion Recognition Driven by Multimodal Data","date":"2022-08-24","arxiv_id":"2208.11346","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-residual-perceptron-network-for","title":"Multi-modal Residual Perceptron Network for Audio-Video Emotion Recognition","date":"2021-07-21","arxiv_id":"2107.10742","repositories_listed":0,"syntology":null},{"url":"/paper/exploring-emotion-features-and-fusion","slug":"exploring-emotion-features-and-fusion","title":"Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition","date":"2020-12-27","arxiv_id":"2012.13912","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-video-emotion-recognition-in-the-wild","title":"Audio-video Emotion Recognition in the Wild using Deep Hybrid Networks","date":"2020-02-20","arxiv_id":"2002.09023","repositories_listed":0,"syntology":null},{"url":"/paper/an-end-to-end-visual-audio-attention-network","slug":"an-end-to-end-visual-audio-attention-network","title":"An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos","date":"2020-02-12","arxiv_id":"2003.00832","repositories_listed":0,"syntology":{"n":7,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/an-end-to-end-visual-audio-attention-network#ran","syntology_url":"https://syntology.ai/paper/2003.00832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00832"}},"official":null}},{"url":null,"slug":"multimodal-fusion-with-deep-neural-networks","title":"Multimodal Fusion with Deep Neural Networks for Audio-Video Emotion Recognition","date":"2019-07-06","arxiv_id":"1907.03196","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-fusion-an-attention-guided-factorized","title":"Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio-video Emotion Recognition","date":"2019-01-15","arxiv_id":"1901.04889","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-cascade-attention-based-rnn-for","title":"Context-aware Cascade Attention-based RNN for Video Emotion Recognition","date":"2018-05-30","arxiv_id":"1805.12098","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-recognition-of-facial-displays-of","title":"Automatic Recognition of Facial Displays of Unfelt Emotions","date":"2017-07-13","arxiv_id":"1707.04061","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatiotemporal-networks-for-video-emotion","title":"Spatiotemporal Networks for Video Emotion Recognition","date":"2017-04-03","arxiv_id":"1704.00570","repositories_listed":0,"syntology":null},{"url":null,"slug":"modelling-temporal-information-using-discrete","title":"Modelling Temporal Information Using Discrete Fourier Transform for Recognizing Emotions in User-generated Videos","date":"2016-03-20","arxiv_id":"1603.06568","repositories_listed":0,"syntology":null},{"url":"/paper/heterogeneous-knowledge-transfer-in-video","slug":"heterogeneous-knowledge-transfer-in-video","title":"Heterogeneous Knowledge Transfer in Video Emotion Recognition, Attribution and Summarization","date":"2015-11-16","arxiv_id":"1511.04798","repositories_listed":0,"syntology":null}],"syntology_records":2,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/video-emotion-recognition-on-crema-d","since_archive":"/sota/video-emotion-recognition-on-crema-d#since-judged","papers_judged":2,"placed":0}]},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/task/video-emotion-recognition/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/video-emotion-recognition/papers/ran/1","json":"/task/video-emotion-recognition/papers/ran/1.json","rows":2}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"19299008228fefd40ab39f08ed7a6baf9490d4efef78bcdfde29d527a7cc029e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}