{"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/vilbert","slug":"vilbert","name":"ViLBERT","full_name":"Vision-and-Language BERT","full_name_withheld":false,"description_markdown":"**Vision-and-Language BERT** (**ViLBERT**) is a [BERT](https://paperswithcode.com/method/bert)-based model for learning task-agnostic joint representations of image content and natural language. ViLBERT extend the popular BERT architecture to a multi-modal two-stream model, processing both visual and textual inputs in separate streams that interact through co-attentional [transformer](https://paperswithcode.com/method/transformer) layers.","description_state":"present","introduced_year":null,"introduced_by":{"title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","paper":"/paper/vilbert-pretraining-task-agnostic","first_author":"Jiasen Lu","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/vilbert-pretraining-task-agnostic"},"source":{"url":"https://arxiv.org/abs/1908.02265v1","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","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":[]},{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]},{"area":"General","area_id":"general","collection":"Representation Learning","url":"/methods/category/representation-learning","pwc_aliases":[]}],"n_papers_tagged":30,"archive_num_papers":30,"papers_newest_first":[{"paper":null,"slug":"a-multimodal-fusion-network-for-student","title":"A Multimodal Fusion Network For Student Emotion Recognition Based on Transformer and Tensor Product","date":"2024-03-13","arxiv_id":"2403.08511","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-image-text-matching-verb-understanding","slug":"beyond-image-text-matching-verb-understanding","title":"Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking","date":"2024-01-29","arxiv_id":"2401.16575","n_code_links":1,"syntology":null},{"paper":"/paper/the-bla-benchmark-investigating-basic","slug":"the-bla-benchmark-investigating-basic","title":"The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models","date":"2023-10-23","arxiv_id":"2310.15061","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":6,"n_instrument":5,"unverified":1,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shin-ee-chen/bla"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-a-performance-analysis-on-pre-trained","slug":"towards-a-performance-analysis-on-pre-trained","title":"Towards a performance analysis on pre-trained Visual Question Answering models for autonomous driving","date":"2023-07-18","arxiv_id":"2307.09329","n_code_links":1,"syntology":null},{"paper":null,"slug":"switch-bert-learning-to-model-multimodal","title":"Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input","date":"2023-06-25","arxiv_id":"2306.14182","n_code_links":0,"syntology":null},{"paper":null,"slug":"weakly-supervised-visual-question-answer","title":"Weakly Supervised Visual Question Answer Generation","date":"2023-06-11","arxiv_id":"2306.06622","n_code_links":0,"syntology":null},{"paper":"/paper/unified-multimodal-model-with-unlikelihood","slug":"unified-multimodal-model-with-unlikelihood","title":"Unified Multimodal Model with Unlikelihood Training for Visual Dialog","date":"2022-11-23","arxiv_id":"2211.13235","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-knowledge-enhanced-multimodal","title":"A survey on knowledge-enhanced multimodal learning","date":"2022-11-19","arxiv_id":"2211.12328","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-cross-modal-semantics-alignment","title":"Probing Cross-modal Semantics Alignment Capability from the Textual Perspective","date":"2022-10-18","arxiv_id":"2210.09550","n_code_links":0,"syntology":null},{"paper":"/paper/image-retrieval-from-contextual-descriptions-1","slug":"image-retrieval-from-contextual-descriptions-1","title":"Image Retrieval from Contextual Descriptions","date":"2022-03-29","arxiv_id":"2203.15867","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mcgill-nlp/imagecode"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/tribert-human-centric-audio-visual","slug":"tribert-human-centric-audio-visual","title":"TriBERT: Human-centric Audio-visual Representation Learning","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"image-retrieval-from-contextual-descriptions","title":"Image Retrieval from Contextual Descriptions","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-learning-are-captions-all-you-need","title":"Multimodal Learning: Are Captions All You Need?","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/tribert-full-body-human-centric-audio-visual","slug":"tribert-full-body-human-centric-audio-visual","title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation","date":"2021-10-26","arxiv_id":"2110.13412","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["ubc-vision/tribert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/broaden-the-vision-geo-diverse-visual","slug":"broaden-the-vision-geo-diverse-visual","title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","date":"2021-09-14","arxiv_id":"2109.06860","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["wadeyin9712/gd-vcr"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhance-multimodal-model-performance-with","slug":"enhance-multimodal-model-performance-with","title":"Enhance Multimodal Model Performance with Data Augmentation: Facebook Hateful Meme Challenge Solution","date":"2021-05-25","arxiv_id":"2105.13132","n_code_links":1,"syntology":null},{"paper":null,"slug":"chop-chop-bert-visual-question-answering-by","title":"Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads","date":"2021-04-30","arxiv_id":"2104.14741","n_code_links":0,"syntology":null},{"paper":null,"slug":"playing-lottery-tickets-with-vision-and","title":"Playing Lottery Tickets with Vision and Language","date":"2021-04-23","arxiv_id":"2104.11832","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-role-of-images-for-analyzing-claims-in","slug":"on-the-role-of-images-for-analyzing-claims-in","title":"On the Role of Images for Analyzing Claims in Social Media","date":"2021-03-17","arxiv_id":"2103.09602","n_code_links":1,"syntology":null},{"paper":"/paper/seeing-past-words-testing-the-cross-modal","slug":"seeing-past-words-testing-the-cross-modal","title":"Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks","date":"2020-12-22","arxiv_id":"2012.12352","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-closer-look-at-the-robustness-of-vision-and","title":"A Closer Look at the Robustness of Vision-and-Language Pre-trained Models","date":"2020-12-15","arxiv_id":"2012.08673","n_code_links":0,"syntology":null},{"paper":"/paper/a-multi-modal-method-for-satire-detection","slug":"a-multi-modal-method-for-satire-detection","title":"A Multi-Modal Method for Satire Detection using Textual and Visual Cues","date":"2020-10-13","arxiv_id":"2010.06671","n_code_links":1,"syntology":null},{"paper":"/paper/x-lxmert-paint-caption-and-answer-questions","slug":"x-lxmert-paint-caption-and-answer-questions","title":"X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers","date":"2020-09-23","arxiv_id":"2009.11278","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["allenai/x-lxmert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"contrastive-visual-linguistic-pretraining","title":"Contrastive Visual-Linguistic Pretraining","date":"2020-07-26","arxiv_id":"2007.13135","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-does-bert-with-vision-look-at","title":"What Does BERT with Vision Look At?","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"behind-the-scene-revealing-the-secrets-of-pre","title":"Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models","date":"2020-05-15","arxiv_id":"2005.07310","n_code_links":0,"syntology":null},{"paper":"/paper/words-aren-t-enough-their-order-matters-on","slug":"words-aren-t-enough-their-order-matters-on","title":"Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring Expressions","date":"2020-05-04","arxiv_id":"2005.01655","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-rationales-in-visual-question","title":"Generating Rationales in Visual Question Answering","date":"2020-04-04","arxiv_id":"2004.02032","n_code_links":0,"syntology":null},{"paper":"/paper/large-scale-pretraining-for-visual-dialog-a","slug":"large-scale-pretraining-for-visual-dialog-a","title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline","date":"2019-12-05","arxiv_id":"1912.02379","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["vmurahari3/visdial-bert"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/vilbert-pretraining-task-agnostic","slug":"vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","arxiv_id":"1908.02265","n_code_links":11,"syntology":{"ran":10,"of":34,"n_ran_checked":8,"n_instrument":2,"unverified":24,"pointer_only":34,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 24 unverified","official":null}}],"papers_shown":30,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":30,"with_a_code_link":15,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":30,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":2,"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":7,"papers_where_code_ran_first_page":"/method/vilbert/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/vilbert/papers/ran/1","json":"/method/vilbert/papers/ran/1.json","rows":7}],"tasks":[{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":9},{"task":"/task/visual-question-answering-1","name":"Visual Question Answering","papers":8},{"task":"/task/question-answering","name":"Question Answering","papers":7},{"task":"/task/retrieval","name":"Retrieval","papers":7},{"task":"/task/representation-learning","name":"Representation Learning","papers":6},{"task":"/task/image-captioning","name":"Image Captioning","papers":4},{"task":"/task/visual-commonsense-reasoning","name":"Visual Commonsense Reasoning","papers":4},{"task":"/task/image-retrieval","name":"Image Retrieval","papers":3},{"task":"/task/language-modelling","name":"Language Modelling","papers":3},{"task":"/task/referring-expression","name":"Referring Expression","papers":3},{"task":"/task/referring-expression-comprehension","name":"Referring Expression Comprehension","papers":3},{"task":"/task/visual-dialogue","name":"Visual Dialog","papers":3},{"task":"/task/visual-grounding","name":"Visual Grounding","papers":3},{"task":"/task/visual-reasoning","name":"Visual Reasoning","papers":3},{"task":"/task/answer-generation","name":"Answer Generation","papers":2},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":2},{"task":"/task/image-text-retrieval","name":"Image-text Retrieval","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":2},{"task":"/task/pose-retrieval","name":"Pose Retrieval","papers":2}],"tasks_shown":20,"n_tasks":64,"usage_by_year":[{"year":"2019","papers":2},{"year":"2020","papers":9},{"year":"2021","papers":9},{"year":"2022","papers":4},{"year":"2023","papers":4},{"year":"2024","papers":2}],"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/vilbert"},"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=ViLBERT","read_at":"2026-10-05T01:03:39+00:00","query":"ViLBERT","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"ViLBERT","origin_arxiv_id":"1908.02265"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"1908.02265","repositories":{"listed":5,"in_graph":11,"list_truncated":true,"strongest_link":"mentioned_in_github"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"1908.02265","citations":4660},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'ViLBERT'. 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":"1908.02265","page":"/paper/vilbert-pretraining-task-agnostic","syntology_url":"https://syntology.ai/paper/1908.02265","in_graph_layer":true,"samples":34,"ran":10,"n_ran_checked":8,"n_instrument":2,"unverified":24,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 24 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 11 in the graph, strongest link: mentioned on GitHub). This answer is about arXiv:1908.02265, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"7e002942008a7fc8a12bc842145a910a935700d6416f7c4e409a3d6856839c80","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}