{"url":"/dataset/cmu-mosi","name":"CMU-MOSI","full_name":"Multimodal Corpus of Sentiment Intensity","description_markdown":"The Multimodal Corpus of Sentiment Intensity (CMU-MOSI) dataset is a collection of 2199 opinion video clips. Each opinion video is annotated with sentiment in the range [-3,3]. The dataset is rigorously annotated with labels for subjectivity, sentiment intensity, per-frame and per-opinion annotated visual features, and per-milliseconds annotated audio features.","description_withheld":null,"homepage":"http://multicomp.cs.cmu.edu/resources/cmu-mosi-dataset/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Emotion Recognition in Conversation","url":"/task/emotion-recognition-in-conversation","datasets_with_task":"/datasets/task/emotion-recognition-in-conversation"},{"name":"Multimodal Sentiment Analysis","url":"/task/multimodal-sentiment-analysis","datasets_with_task":"/datasets/task/multimodal-sentiment-analysis"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CMU-MOSI"],"data_loaders":[{"repo":"https://github.com/ravikumarsharma23/Multimodal-Sentiment-Analysis-with-cross-modal-interaction","url":"https://github.com/ravikumarsharma23/Multimodal-Sentiment-Analysis-with-cross-modal-interaction","frameworks":["tf","pytorch"]}],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multimodal-sentiment-analysis-on-cmu-mosi","task":"Multimodal Sentiment Analysis","dataset_variant":"CMU-MOSI","rows":12,"metrics":["F1","Acc-7","Acc-2","Corr","MAE","F1-score (Weighted)","Acc-5"],"first_row_in_archive_order":{"model":"MMML","paper":"/paper/multi-modality-multi-loss-fusion-network","metrics":{"Acc-2":"90.35","Acc-5":"60.01","Acc-7":"52.72","Corr":"0.8824","F1":"90.35","MAE":"0.5573"},"code_links":[{"title":"zehuiwu/MMML","url":"https://github.com/zehuiwu/MMML"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-cmu","task":"Emotion Recognition in Conversation","dataset_variant":"CMU-MOSI","rows":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"Audio + Text (Stage III)","paper":"/paper/hcam-hierarchical-cross-attention-model-for","metrics":{"F1 score":"0.858"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/learning-language-guided-adaptive-hyper","title":"Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis","date":"2023-10-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modality-multi-loss-fusion-network","title":"Multimodal Multi-loss Fusion Network for Sentiment Analysis","date":"2023-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hcam-hierarchical-cross-attention-model-for","title":"HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition","date":"2023-04-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/meltr-meta-loss-transformer-for-learning-to","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","date":"2023-03-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unimse-towards-unified-multimodal-sentiment","title":"UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition","date":"2022-11-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adversarial-multimodal-domain-transfer-for","title":"Adversarial Multimodal Domain Transfer for Video-Level Sentiment Analysis","date":"2022-05-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/teasel-a-transformer-based-speech-prefixed","title":"TEASEL: A Transformer-Based Speech-Prefixed Language Model","date":"2021-09-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-multimodal-fusion-with-hierarchical","title":"Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis","date":"2021-09-01","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":4,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transmodality-an-end2end-fusion-method-with","title":"TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis","date":"2020-09-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/10000-times-accelerated-robust-subset","title":"10,000+ Times Accelerated Robust Subset Selection (ARSS)","date":"2014-09-12","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":12,"samples_ran":5,"samples_unverified":7,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}