{"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":"/dataset/cmu-mosei","name":"CMU-MOSEI","full_name":null,"description_markdown":"CMU Multimodal Opinion Sentiment and Emotion Intensity (**CMU-MOSEI**) is the largest dataset of sentence-level sentiment analysis and emotion recognition in online videos. CMU-MOSEI contains over 12 hours of annotated video from over 1000 speakers and 250 topics.","description_withheld":null,"homepage":"","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/multimodal-language-analysis-in-the-wild-cmu","title":"Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph","first_author":"AmirAli Bagher Zadeh","url":null},"license":{"name":"Custom","url":"https://github.com/A2Zadeh/CMU-MultimodalSDK/blob/master/LICENSE.txt"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Facial Expression Recognition","url":"/task/facial-expression-recognition-1","datasets_with_task":"/datasets/task/facial-expression-recognition-1"},{"name":"Emotion Classification","url":"/task/emotion-classification","datasets_with_task":"/datasets/task/emotion-classification"},{"name":"Multimodal Emotion Recognition","url":"/task/multimodal-emotion-recognition","datasets_with_task":"/datasets/task/multimodal-emotion-recognition"},{"name":"Multimodal Sentiment Analysis","url":"/task/multimodal-sentiment-analysis","datasets_with_task":"/datasets/task/multimodal-sentiment-analysis"},{"name":"Video Emotion Detection","url":"/task/video-emotion-detection","datasets_with_task":"/datasets/task/video-emotion-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CMU-MOSEI"],"data_loaders":[{"repo":"https://github.com/lobracost/MultimodalSDK_loader","url":"https://github.com/lobracost/MultimodalSDK_loader","frameworks":[]}],"num_papers_in_archive":190,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multimodal-sentiment-analysis-on-cmu-mosei-1","task":"Multimodal Sentiment Analysis","dataset_variant":"CMU-MOSEI","rows":15,"metrics":["Accuracy","MAE","F1","Acc-5","Acc-7","Corr"],"first_row_in_archive_order":{"model":"SeMUL-PCD","paper":"/paper/multi-label-emotion-analysis-in-conversation","metrics":{"Accuracy":"88.62","F1":"89.04"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/emotion-classification-on-cmu-mosei","task":"Emotion Classification","dataset_variant":"CMU-MOSEI","rows":4,"metrics":["Accuracy","Weighted Accuracy"],"first_row_in_archive_order":{"model":"MARLIN (ViT-L)","paper":"/paper/marlin-masked-autoencoder-for-facial-video","metrics":{"Accuracy":"80.63"},"code_links":[{"title":"ControlNet/MARLIN","url":"https://github.com/ControlNet/MARLIN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/facial-expression-recognition-on-cmu-mosei","task":"Facial Expression Recognition","dataset_variant":"CMU-MOSEI","rows":1,"metrics":["Weighted Accuracy"],"first_row_in_archive_order":{"model":"ConCluGen","paper":"/paper/multi-task-multi-modal-self-supervised","metrics":{"Weighted Accuracy":"66.48"},"code_links":[{"title":"tub-cv-group/conclugen","url":"https://github.com/tub-cv-group/conclugen"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":14,"of":14,"counts":{"papers_with_a_benchmark_row":14,"with_a_code_link":10,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":14,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/multi-task-multi-modal-self-supervised","slug":"multi-task-multi-modal-self-supervised","title":"Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition","date":"2024-04-16","arxiv_id":"2404.10904","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multi-label-emotion-analysis-in-conversation","slug":"multi-label-emotion-analysis-in-conversation","title":"Multi-label Emotion Analysis in Conversation via Multimodal Knowledge Distillation","date":"2023-10-27","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-language-guided-adaptive-hyper","slug":"learning-language-guided-adaptive-hyper","title":"Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis","date":"2023-10-09","arxiv_id":"2310.05804","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modality-multi-loss-fusion-network","slug":"multi-modality-multi-loss-fusion-network","title":"Multimodal Multi-loss Fusion Network for Sentiment Analysis","date":"2023-08-01","arxiv_id":"2308.00264","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/speech-text-dialog-pre-training-for-spoken","slug":"speech-text-dialog-pre-training-for-spoken","title":"Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment","date":"2023-05-19","arxiv_id":"2305.11579","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unimse-towards-unified-multimodal-sentiment","slug":"unimse-towards-unified-multimodal-sentiment","title":"UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition","date":"2022-11-21","arxiv_id":"2211.11256","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/marlin-masked-autoencoder-for-facial-video","slug":"marlin-masked-autoencoder-for-facial-video","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","date":"2022-11-12","arxiv_id":"2211.06627","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/mmlatch-bottom-up-top-down-fusion-for","slug":"mmlatch-bottom-up-top-down-fusion-for","title":"MMLatch: Bottom-up Top-down Fusion for Multimodal Sentiment Analysis","date":"2022-01-24","arxiv_id":"2201.09828","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-multimodal-language","slug":"unsupervised-multimodal-language","title":"Unsupervised Multimodal Language Representations using Convolutional Autoencoders","date":"2021-10-06","arxiv_id":"2110.03007","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/modulated-fusion-using-transformer-for","slug":"modulated-fusion-using-transformer-for","title":"Modulated Fusion using Transformer for Linguistic-Acoustic Emotion Recognition","date":"2020-10-05","arxiv_id":"2010.02057","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-transformer-based-joint-encoding-for-1","slug":"a-transformer-based-joint-encoding-for-1","title":"A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis","date":"2020-06-29","arxiv_id":"2006.15955","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-transformer-based-joint-encoding-for-1#ran","syntology_url":"https://syntology.ai/paper/2006.15955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15955"}}}},{"paper":"/paper/gated-mechanism-for-attention-based","slug":"gated-mechanism-for-attention-based","title":"Gated Mechanism for Attention Based Multimodal Sentiment Analysis","date":"2020-02-21","arxiv_id":"2003.01043","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multilogue-net-a-context-aware-rnn-for-multi","slug":"multilogue-net-a-context-aware-rnn-for-multi","title":"Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation","date":"2020-02-19","arxiv_id":"2002.08267","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["amanshenoy/multilogue-net"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multilogue-net-a-context-aware-rnn-for-multi#ran","syntology_url":"https://syntology.ai/paper/2002.08267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.08267"}}}},{"paper":"/paper/multimodal-language-analysis-in-the-wild-cmu","slug":"multimodal-language-analysis-in-the-wild-cmu","title":"Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph","date":"2018-07-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/multi-task-multi-modal-self-supervised","slug":"multi-task-multi-modal-self-supervised","title":"Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition","date":"2024-04-16","arxiv_id":"2404.10904","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multi-label-emotion-analysis-in-conversation","slug":"multi-label-emotion-analysis-in-conversation","title":"Multi-label Emotion Analysis in Conversation via Multimodal Knowledge Distillation","date":"2023-10-27","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-language-guided-adaptive-hyper","slug":"learning-language-guided-adaptive-hyper","title":"Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis","date":"2023-10-09","arxiv_id":"2310.05804","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modality-multi-loss-fusion-network","slug":"multi-modality-multi-loss-fusion-network","title":"Multimodal Multi-loss Fusion Network for Sentiment Analysis","date":"2023-08-01","arxiv_id":"2308.00264","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/speech-text-dialog-pre-training-for-spoken","slug":"speech-text-dialog-pre-training-for-spoken","title":"Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment","date":"2023-05-19","arxiv_id":"2305.11579","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unimse-towards-unified-multimodal-sentiment","slug":"unimse-towards-unified-multimodal-sentiment","title":"UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition","date":"2022-11-21","arxiv_id":"2211.11256","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/marlin-masked-autoencoder-for-facial-video","slug":"marlin-masked-autoencoder-for-facial-video","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","date":"2022-11-12","arxiv_id":"2211.06627","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/mmlatch-bottom-up-top-down-fusion-for","slug":"mmlatch-bottom-up-top-down-fusion-for","title":"MMLatch: Bottom-up Top-down Fusion for Multimodal Sentiment Analysis","date":"2022-01-24","arxiv_id":"2201.09828","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-multimodal-language","slug":"unsupervised-multimodal-language","title":"Unsupervised Multimodal Language Representations using Convolutional Autoencoders","date":"2021-10-06","arxiv_id":"2110.03007","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/modulated-fusion-using-transformer-for","slug":"modulated-fusion-using-transformer-for","title":"Modulated Fusion using Transformer for Linguistic-Acoustic Emotion Recognition","date":"2020-10-05","arxiv_id":"2010.02057","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-transformer-based-joint-encoding-for-1","slug":"a-transformer-based-joint-encoding-for-1","title":"A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis","date":"2020-06-29","arxiv_id":"2006.15955","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-transformer-based-joint-encoding-for-1#ran","syntology_url":"https://syntology.ai/paper/2006.15955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15955"}}}},{"paper":"/paper/gated-mechanism-for-attention-based","slug":"gated-mechanism-for-attention-based","title":"Gated Mechanism for Attention Based Multimodal Sentiment Analysis","date":"2020-02-21","arxiv_id":"2003.01043","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multilogue-net-a-context-aware-rnn-for-multi","slug":"multilogue-net-a-context-aware-rnn-for-multi","title":"Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation","date":"2020-02-19","arxiv_id":"2002.08267","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["amanshenoy/multilogue-net"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multilogue-net-a-context-aware-rnn-for-multi#ran","syntology_url":"https://syntology.ai/paper/2002.08267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.08267"}}}},{"paper":"/paper/multimodal-language-analysis-in-the-wild-cmu","slug":"multimodal-language-analysis-in-the-wild-cmu","title":"Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph","date":"2018-07-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/cmu-mosei/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/cmu-mosei/papers/ran/1","json":"/dataset/cmu-mosei/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":2,"samples_harvested":8,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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":3,"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/multimodal-sentiment-analysis-on-cmu-mosei-1","since_archive":"/sota/multimodal-sentiment-analysis-on-cmu-mosei-1#since-judged","papers_judged":3,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"8d5526cfc12a77d2ff1817d675136f3f92e655afe7a640cd35489f0b96cd6213","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}