{"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/visualbert-a-simple-and-performant-baseline","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","arxiv_id":"1908.03557","date":"2019-08-09","proceeding":null,"authors":["Liunian Harold Li","Mark Yatskar","Da Yin","Cho-Jui Hsieh","Kai-Wei Chang"],"abstract":"We propose VisualBERT, a simple and flexible framework for modeling a broad range of vision-and-language tasks. VisualBERT consists of a stack of Transformer layers that implicitly align elements of an input text and regions in an associated input image with self-attention. We further propose two visually-grounded language model objectives for pre-training VisualBERT on image caption data. Experiments on four vision-and-language tasks including VQA, VCR, NLVR2, and Flickr30K show that VisualBERT outperforms or rivals with state-of-the-art models while being significantly simpler. Further analysis demonstrates that VisualBERT can ground elements of language to image regions without any explicit supervision and is even sensitive to syntactic relationships, tracking, for example, associations between verbs and image regions corresponding to their arguments.","url_abs":"https://arxiv.org/abs/1908.03557v1","url_pdf":"https://arxiv.org/pdf/1908.03557v1.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":"visualbert-a-simple-and-performant-baseline","repo_url":"https://github.com/chenkangyang/paddle_visual_bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":null},{"paper_slug":"visualbert-a-simple-and-performant-baseline","repo_url":"https://github.com/gchhablani/multilingual-vqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"visualbert-a-simple-and-performant-baseline","repo_url":"https://github.com/lalithjets/surgical_vqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visualbert-a-simple-and-performant-baseline","repo_url":"https://github.com/longbai1006/surgical-vqla","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"visualbert-a-simple-and-performant-baseline","repo_url":"https://github.com/social-ai-studio/matk","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"visualbert-a-simple-and-performant-baseline","repo_url":"https://github.com/uclanlp/visualbert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visualbert-a-simple-and-performant-baseline","repo_url":"https://github.com/MindCode-4/code-1/tree/main/visual_bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"visualbert-a-simple-and-performant-baseline","repo_url":"https://github.com/MindCode-4/code-5/tree/main/visual_bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"visualbert-a-simple-and-performant-baseline","repo_url":"https://github.com/YIKUAN8/Transformers-VQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"visualbert-a-simple-and-performant-baseline","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/5/visual_bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"visualbert","method_name":"VisualBERT"}],"datasets_introduced":[],"methods_introduced":[{"slug":"visualbert","name":"VisualBERT","full_name":"VisualBERT"}],"results":[{"leaderboard":"/sota/phrase-grounding-on-flickr30k-entities-dev","task":"Phrase Grounding","dataset":"Flickr30k Entities Dev","model":"VisualBERT","rank_in_archive_order":3,"of":3,"metrics":{"R@1":"70.4","R@10":"86.31","R@5":"84.49"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-grounding-on-flickr30k-entities-test","task":"Phrase Grounding","dataset":"Flickr30k Entities Test","model":"VisualBERT","rank_in_archive_order":10,"of":18,"metrics":{"R@1":"71.33","R@10":"86.51","R@5":"84.98"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vcr-q-a-dev","task":"Visual Question Answering (VQA)","dataset":"VCR (Q-A) dev","model":"VisualBERT","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"70.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vcr-q-a-test","task":"Visual Question Answering (VQA)","dataset":"VCR (Q-A) test","model":"VisualBERT","rank_in_archive_order":9,"of":11,"metrics":{"Accuracy":"71.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vcr-q-ar-dev","task":"Visual Question Answering (VQA)","dataset":"VCR (Q-AR) dev","model":"VisualBERT","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"52.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vcr-q-ar-test","task":"Visual Question Answering (VQA)","dataset":"VCR (Q-AR) test","model":"VisualBERT","rank_in_archive_order":7,"of":7,"metrics":{"Accuracy":"52.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vcr-qa-r-dev","task":"Visual Question Answering (VQA)","dataset":"VCR (QA-R) dev","model":"VisualBERT","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"73.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vcr-qa-r-test","task":"Visual Question Answering (VQA)","dataset":"VCR (QA-R) test","model":"VisualBERT","rank_in_archive_order":8,"of":8,"metrics":{"Accuracy":"73.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"VisualBERT","rank_in_archive_order":28,"of":56,"metrics":{"Accuracy":"70.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-std","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-std","model":"VisualBERT","rank_in_archive_order":24,"of":38,"metrics":{"overall":"71"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-nlvr","task":"Visual Reasoning","dataset":"NLVR","model":"VisualBERT","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (Dev)":"67.4%","Accuracy (Test-P)":"67%","Accuracy (Test-U)":"67.3%"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-dev","task":"Visual Reasoning","dataset":"NLVR2 Dev","model":"VisualBERT","rank_in_archive_order":15,"of":15,"metrics":{"Accuracy":"66.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.03557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03557"}},"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/social-ai-studio/matk","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/longbai1006/surgical-vqla","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenkangyang/paddle_visual_bert","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lalithjets/surgical_vqa","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YIKUAN8/Transformers-VQA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uclanlp/visualbert","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/5/visual_bert","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gchhablani/multilingual-vqa","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-1/tree/main/visual_bert","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-5/tree/main/visual_bert","reach":null}],"summary":{"ran":4,"unverified":5},"by_repo_kind":{"listed":{"samples":9,"ran":4,"repositories":3}},"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":6,"samples":[{"code_sha256_prefix":"74b2fcf39fdad75a","entry":"CLIPVisionBertConfig","repo":"gchhablani/multilingual-vqa","repo_kind":"listed","path":"models/flax_clip_vision_bert/modeling_clip_vision_bert.py","file_url":"https://github.com/gchhablani/multilingual-vqa/blob/HEAD/models/flax_clip_vision_bert/modeling_clip_vision_bert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74b2fcf39fdad75a"}},{"code_sha256_prefix":"eed1fcab3a96812d","entry":"FlaxCLIPVisionBertModule","repo":"gchhablani/multilingual-vqa","repo_kind":"listed","path":"models/flax_clip_vision_bert/modeling_clip_vision_bert.py","file_url":"https://github.com/gchhablani/multilingual-vqa/blob/HEAD/models/flax_clip_vision_bert/modeling_clip_vision_bert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eed1fcab3a96812d"}},{"code_sha256_prefix":"cd39cffdc7b1f9c3","entry":"perform_truncate","repo":"chenkangyang/paddle_visual_bert","repo_kind":"listed","path":"run_pretrain.py","file_url":"https://github.com/chenkangyang/paddle_visual_bert/blob/HEAD/run_pretrain.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd39cffdc7b1f9c3"}},{"code_sha256_prefix":"1d3d00a8a5932be0","entry":"random_word","repo":"chenkangyang/paddle_visual_bert","repo_kind":"listed","path":"run_pretrain.py","file_url":"https://github.com/chenkangyang/paddle_visual_bert/blob/HEAD/run_pretrain.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d3d00a8a5932be0"}},{"code_sha256_prefix":"59f36be33253afad","entry":"BertEncoder","repo":"YIKUAN8/Transformers-VQA","repo_kind":"listed","path":"src/modeling.py","file_url":"https://github.com/YIKUAN8/Transformers-VQA/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"59f36be33253afad"}},{"code_sha256_prefix":"bc82bcf6d781550f","entry":"FlaxCLIPVisionBertEmbeddings","repo":"gchhablani/multilingual-vqa","repo_kind":"listed","path":"models/flax_clip_vision_bert/modeling_clip_vision_bert.py","file_url":"https://github.com/gchhablani/multilingual-vqa/blob/HEAD/models/flax_clip_vision_bert/modeling_clip_vision_bert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc82bcf6d781550f"}},{"code_sha256_prefix":"2e705a7d909038d1","entry":"VBBertModel","repo":"YIKUAN8/Transformers-VQA","repo_kind":"listed","path":"src/modeling.py","file_url":"https://github.com/YIKUAN8/Transformers-VQA/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e705a7d909038d1"}},{"code_sha256_prefix":"7c7933295057c6b3","entry":"VisualBertEmbeddings","repo":"YIKUAN8/Transformers-VQA","repo_kind":"listed","path":"src/modeling.py","file_url":"https://github.com/YIKUAN8/Transformers-VQA/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7c7933295057c6b3"}},{"code_sha256_prefix":"49436f86e6503e90","entry":"prepare_train_features_single","repo":"chenkangyang/paddle_visual_bert","repo_kind":"listed","path":"run_pretrain.py","file_url":"https://github.com/chenkangyang/paddle_visual_bert/blob/HEAD/run_pretrain.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"49436f86e6503e90"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}