{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/mintrec-a-new-dataset-for-multimodal-intent","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","arxiv_id":"2209.04355","date":"2022-09-09","proceeding":null,"authors":["Hanlei Zhang","Hua Xu","Xin Wang","Qianrui Zhou","Shaojie Zhao","Jiayan Teng"],"abstract":"Multimodal intent recognition is a significant task for understanding human language in real-world multimodal scenes. Most existing intent recognition methods have limitations in leveraging the multimodal information due to the restrictions of the benchmark datasets with only text information. This paper introduces a novel dataset for multimodal intent recognition (MIntRec) to address this issue. 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. Furthermore, we provide annotated bounding boxes of speakers in each video segment and achieve an automatic process for speaker annotation. MIntRec is helpful for researchers to mine relationships between different modalities to enhance the capability of intent recognition. We extract features from each modality and model cross-modal interactions by adapting three powerful multimodal fusion methods to build baselines. Extensive experiments show that employing the non-verbal modalities achieves substantial improvements compared with the text-only modality, demonstrating the effectiveness of using multimodal information for intent recognition. The gap between the best-performing methods and humans indicates the challenge and importance of this task for the community. The full dataset and codes are available for use at https://github.com/thuiar/MIntRec.","url_abs":"https://arxiv.org/abs/2209.04355v1","url_pdf":"https://arxiv.org/pdf/2209.04355v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mintrec-a-new-dataset-for-multimodal-intent","repo_url":"https://github.com/thuiar/mintrec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"intent-recognition","task_name":"Intent Recognition"},{"task_slug":"multimodal-intent-recognition","task_name":"Multimodal Intent Recognition"}],"methods":[],"datasets_introduced":[{"slug":"mintrec","name":"MIntRec","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/multimodal-intent-recognition-on-mintrec","task":"Multimodal Intent Recognition","dataset":"MIntRec","model":"Human","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy (20 classes)":"85.51","Accuracy (Binary)":"94.72"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-intent-recognition-on-mintrec","task":"Multimodal Intent Recognition","dataset":"MIntRec","model":"MAG-BERT (Text + Audio + Video)","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy (20 classes)":"72.65","Accuracy (Binary)":"89.24"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-intent-recognition-on-mintrec","task":"Multimodal Intent Recognition","dataset":"MIntRec","model":"MulT (Text + Audio + Video)","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy (20 classes)":"72.52","Accuracy (Binary)":"89.19"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-intent-recognition-on-mintrec","task":"Multimodal Intent Recognition","dataset":"MIntRec","model":"MISA (Text + Audio + Video)","rank_in_archive_order":6,"of":6,"metrics":{"Accuracy (20 classes)":"72.29","Accuracy (Binary)":"89.21"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.04355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.04355"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thuiar/mintrec","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8388af70b8314436","entry":"bb_intersection_over_union","repo":"thuiar/mintrec","repo_kind":"official","path":"TalkNet_ASD/calculate_score.py","file_url":"https://github.com/thuiar/mintrec/blob/HEAD/TalkNet_ASD/calculate_score.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8388af70b8314436"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}