{"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":"/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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/contrastive-audio-visual-masked-autoencoder#ran","syntology_url":"https://syntology.ai/paper/2210.07839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07839"}},"official":{"repos":["yuangongnd/cav-mae"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}}],"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":31,"of":31,"of_with_code":12,"tagged_in_all":31,"counts":{"archive_papers_tagged":31,"with_a_code_link":12,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":31,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":1,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/what-makes-training-multi-modal-networks-hard","slug":"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":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/what-makes-training-multi-modal-networks-hard#ran","syntology_url":"https://syntology.ai/paper/1905.12681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12681"}},"official":null}},{"url":"/paper/multimodal-learning-with-uncertainty","slug":"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","slug":"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","slug":"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":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/promptstyler-prompt-driven-style-generation#ran","syntology_url":"https://syntology.ai/paper/2307.15199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15199"}},"official":null}},{"url":"/paper/fame-vil-multi-tasking-vision-language-model","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/contrastive-audio-visual-masked-autoencoder#ran","syntology_url":"https://syntology.ai/paper/2210.07839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07839"}},"official":{"repos":["yuangongnd/cav-mae"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/uavm-a-unified-model-for-audio-visual","slug":"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":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/uavm-a-unified-model-for-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2208.00061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.00061"}},"official":{"repos":["YuanGongND/uavm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/on-modality-bias-recognition-and-reduction","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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},{"url":null,"slug":"lightweight-joint-audio-visual-deepfake","title":"Lightweight Joint Audio-Visual Deepfake Detection via Single-Stream Multi-Modal Learning Framework","date":"2025-06-09","arxiv_id":"2506.07358","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-training-free-open-vocabulary","title":"A Survey on Training-free Open-Vocabulary Semantic Segmentation","date":"2025-05-28","arxiv_id":"2505.22209","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-human-activity","title":"A Comparative Study of Human Activity Recognition: Motion, Tactile, and multi-modal Approaches","date":"2025-05-13","arxiv_id":"2505.08657","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-classification-of-forest","title":"Multi-modal classification of forest biodiversity potential from 2D orthophotos and 3D airborne laser scanning point clouds","date":"2025-01-03","arxiv_id":"2501.01728","repositories_listed":0,"syntology":null},{"url":null,"slug":"turbo-your-multi-modal-classification-with","title":"Turbo your multi-modal classification with contrastive learning","date":"2024-09-14","arxiv_id":"2409.09282","repositories_listed":0,"syntology":null},{"url":null,"slug":"fungitastic-a-multi-modal-dataset-and","title":"FungiTastic: A multi-modal dataset and benchmark for image categorization","date":"2024-08-24","arxiv_id":"2408.13632","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-augmentation-in-clip-for-improved","title":"Language Augmentation in CLIP for Improved Anatomy Detection on Multi-modal Medical Images","date":"2024-05-31","arxiv_id":"2405.20735","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-individual-fusion-structure-with-fusion","title":"Joint-Individual Fusion Structure with Fusion Attention Module for Multi-Modal Skin Cancer Classification","date":"2023-12-07","arxiv_id":"2312.04189","repositories_listed":0,"syntology":null},{"url":"/paper/avt-audio-video-transformer-for-multimodal","slug":"avt-audio-video-transformer-for-multimodal","title":"AVT: Audio-Video Transformer for Multimodal Action Recognition","date":"2022-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/multiscale-multimodal-transformer-for","slug":"multiscale-multimodal-transformer-for","title":"Multiscale Multimodal Transformer for Multimodal Action Recognition","date":"2022-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-hypergraph-diffusion-network-with","title":"Multi-Modal Hypergraph Diffusion Network with Dual Prior for Alzheimer Classification","date":"2022-04-04","arxiv_id":"2204.02399","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-based-framework-for","title":"Multi Task Learning based Framework for Multimodal Classification","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-retrieval-augmentation-for-multi-1","title":"Cross-Modal Retrieval Augmentation for Multi-Modal Classification","date":"2021-04-16","arxiv_id":"2104.08108","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multi-modal-nonlinear-embeddings","title":"Learning Multi-Modal Nonlinear Embeddings: Performance Bounds and an Algorithm","date":"2020-06-03","arxiv_id":"2006.02330","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-post-deletion-in-sina-weibo-multi","title":"Assessing Post Deletion in Sina Weibo: Multi-modal Classification of Hot Topics","date":"2019-06-26","arxiv_id":"1906.10861","repositories_listed":0,"syntology":null},{"url":null,"slug":"cuisinenet-food-attributes-classification","title":"CuisineNet: Food Attributes Classification using Multi-scale Convolution Network","date":"2018-05-30","arxiv_id":"1805.12081","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-large-scale-multi-modal","title":"Efficient Large-Scale Multi-Modal Classification","date":"2018-02-06","arxiv_id":"1802.02892","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-multi-modal-classification-of","title":"Deep Multi-Modal Classification of Intraductal Papillary Mucinous Neoplasms (IPMN) with Canonical Correlation Analysis","date":"2017-10-26","arxiv_id":"1710.09779","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-fusion-for-diabetes-mellitus-and","title":"Multi-modal Fusion for Diabetes Mellitus and Impaired Glucose Regulation Detection","date":"2016-04-12","arxiv_id":"1604.03443","repositories_listed":0,"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"},"key_notes":{"n_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'","n_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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/task/multi-modal-classification/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/multi-modal-classification/papers/ran/1","json":"/task/multi-modal-classification/papers/ran/1.json","rows":3}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"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"},"record_sha256":"1a97785d8200e58393327b7be3e632ab16e2c48a94d31a345ab54e818ddbd44b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}