{"url":"/dataset/mintrec","name":"MIntRec","full_name":null,"description_markdown":"**MIntRec** is a novel dataset for multimodal intent recognition. It formulates coarse-grained and fine-grained intent taxonomies based on the data collected from the TV series *Superstore*. The dataset consists of 2,224 high-quality samples with text, video, and audio modalities and has multimodal annotations among twenty intent categories.","description_withheld":null,"homepage":"https://github.com/thuiar/MIntRec","introduced_date":"2022-09-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/mintrec-a-new-dataset-for-multimodal-intent","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","first_author":"Hanlei Zhang","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Multimodal Intent Recognition","url":"/task/multimodal-intent-recognition","datasets_with_task":"/datasets/task/multimodal-intent-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MIntRec"],"data_loaders":[],"num_papers_in_archive":14,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multimodal-intent-recognition-on-mintrec","task":"Multimodal Intent Recognition","dataset_variant":"MIntRec","rows":6,"metrics":["Accuracy (20 classes)","Accuracy (Binary)"],"first_row_in_archive_order":{"model":"Human","paper":"/paper/mintrec-a-new-dataset-for-multimodal-intent","metrics":{"Accuracy (20 classes)":"85.51","Accuracy (Binary)":"94.72"},"code_links":[{"title":"thuiar/mintrec","url":"https://github.com/thuiar/mintrec"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/token-level-contrastive-learning-with","title":"Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition","date":"2023-12-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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/mintrec-a-new-dataset-for-multimodal-intent","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","date":"2022-09-09","rows_on_this_dataset":4,"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."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":9,"samples_ran":6,"samples_unverified":3,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"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."}