{"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":"/method/interbert","slug":"interbert","name":"InterBERT","full_name":"InterBERT","full_name_withheld":false,"description_markdown":"InterBERT aims to model interaction between information flows pertaining to different modalities. This new architecture builds multi-modal interaction and preserves the independence of single modal representation. InterBERT is built with an image embedding layer, a text embedding layer, a single-stream interaction module, and a two stream extraction module. The model is pre-trained with three tasks: 1) masked segment modeling, 2) masked region modeling, and 3) image-text matching.","description_state":"present","introduced_year":null,"introduced_by":{"title":"InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining","paper":"/paper/interbert-vision-and-language-interaction-for","first_author":"Junyang Lin","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/interbert-vision-and-language-interaction-for"},"source":{"url":"https://arxiv.org/abs/2003.13198v4","title":"InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Vision and Language Pre-Trained Models","url":"/methods/category/vision-and-language-pre-trained-models","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/interbert-vision-and-language-interaction-for","slug":"interbert-vision-and-language-interaction-for","title":"InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining","date":"2020-03-30","arxiv_id":"2003.13198","n_code_links":0,"syntology":null}],"papers_shown":1,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":1,"with_a_code_link":0,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":1,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"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"},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/image-retrieval","name":"Image Retrieval","papers":1},{"task":"/task/image-text-matching","name":"Image-text matching","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/text-matching","name":"Text Matching","papers":1},{"task":"/task/visual-commonsense-reasoning","name":"Visual Commonsense Reasoning","papers":1}],"tasks_shown":5,"n_tasks":5,"usage_by_year":[{"year":"2020","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/interbert"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=InterBERT","read_at":"2026-10-05T00:58:03+00:00","query":"InterBERT","kind":"paper","have":"no_code","tier":"paper_only","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"arxiv_id":"2003.13198"},"resolution":"paper","resolved_name_differs":false,"absence_asserted":"for_this_paper_only","absence_unchecked":null,"no_code_is_about_this_method":true,"subject":"same_paper","archive_paper_arxiv_id":"2003.13198","repositories":{"listed":null,"in_graph":0,"list_truncated":null,"strongest_link":null},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2003.13198","citations":91},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'InterBERT'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2003.13198","page":"/paper/interbert-vision-and-language-interaction-for","syntology_url":"https://syntology.ai/paper/2003.13198","in_graph_layer":false,"samples":0},"line":"origin paper held, no code (paper_only). The lookup matched a paper by its title, arXiv:2003.13198, not a method entry. This answer is about arXiv:2003.13198, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"e795ddb8d424307e0183419780092fc299132fa61c86b0ab9f4b5c8b5247ff3f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}