{"url":"/task/multi-modal-classification","name":"Multi-modal Classification","slug":"multi-modal-classification","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":31,"papers_with_code":12,"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":4,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/multi-modal-classification-on-vgg-sound","slug":"multi-modal-classification-on-vgg-sound","dataset":"VGG-Sound","dataset_url":"/dataset/vgg-sound","rows_in_archive":4,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"MMT","paper_title":"Multiscale Multimodal Transformer for Multimodal Action Recognition","paper_url":"/paper/multiscale-multimodal-transformer-for","paper_date":"2022-09-22","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/multi-modal-classification-on-audioset","slug":"multi-modal-classification-on-audioset","dataset":"AudioSet","dataset_url":"/dataset/audioset","rows_in_archive":2,"metrics":["Average mAP"],"first_row_in_archive_order":{"model":"CAV-MAE","paper_title":"Contrastive Audio-Visual Masked Autoencoder","paper_url":"/paper/contrastive-audio-visual-masked-autoencoder","paper_date":"2022-10-02","arxiv_id":"2210.07839","code_links":[{"title":"yuangongnd/cav-mae","url":"https://github.com/yuangongnd/cav-mae"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/audioset","name":"AudioSet","full_name":"","num_papers_in_archive":744},{"url":"/dataset/vgg-sound","name":"VGG-Sound","full_name":"","num_papers_in_archive":211},{"url":"/dataset/gaze-cifar-10","name":"Gaze-CIFAR-10","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mudestreda","name":"Mudestreda","full_name":"Mudestreda Multimodal Device State Recognition Dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/image-text-classification","name":"Image-text Classification"}],"parent_tasks":[{"url":"/task/classification-1","name":"Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":12,"of":12,"tagged_in_all":31,"items":[{"url":"/paper/what-makes-training-multi-modal-networks-hard","title":"What Makes Training Multi-Modal Classification Networks Hard?","date":"2019-05-29","arxiv_id":"1905.12681","repositories_listed":3,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/multimodal-learning-with-uncertainty","title":"Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion","date":"2024-12-23","arxiv_id":"2412.18024","repositories_listed":1,"syntology":null},{"url":"/paper/hateful-meme-detection-through-context","title":"Hateful Meme Detection through Context-Sensitive Prompting and Fine-Grained Labeling","date":"2024-11-13","arxiv_id":"2411.10480","repositories_listed":1,"syntology":null},{"url":"/paper/promptstyler-prompt-driven-style-generation","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","date":"2023-07-27","arxiv_id":"2307.15199","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/fame-vil-multi-tasking-vision-language-model","title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","date":"2023-03-04","arxiv_id":"2303.02483","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-audio-visual-masked-autoencoder","title":"Contrastive Audio-Visual Masked Autoencoder","date":"2022-10-02","arxiv_id":"2210.07839","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/uavm-a-unified-model-for-audio-visual","title":"UAVM: Towards Unifying Audio and Visual Models","date":"2022-07-29","arxiv_id":"2208.00061","repositories_listed":1,"syntology":{"n":14,"n_ran":6,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/on-modality-bias-recognition-and-reduction","title":"On Modality Bias Recognition and Reduction","date":"2022-02-25","arxiv_id":"2202.12690","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-dynamics-dynamical-fusion-for","title":"Multimodal Dynamics: Dynamical Fusion for Trustworthy Multimodal Classification","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-sarcasm-detection-and-humor","title":"Multi-modal Sarcasm Detection and Humor Classification in Code-mixed Conversations","date":"2021-05-20","arxiv_id":"2105.09984","repositories_listed":1,"syntology":null},{"url":"/paper/look-read-and-enrich-learning-from-scientific","title":"Look, Read and Enrich. Learning from Scientific Figures and their Captions","date":"2019-09-19","arxiv_id":"1909.09070","repositories_listed":1,"syntology":null},{"url":"/paper/image-and-encoded-text-fusion-for-multi-modal","title":"Image and Encoded Text Fusion for Multi-Modal Classification","date":"2018-10-03","arxiv_id":"1810.02001","repositories_listed":1,"syntology":null}],"syntology_records":4,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}