{"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/vd-bert-a-unified-vision-and-dialog","title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT","arxiv_id":"2004.13278","date":"2020-04-28","proceeding":"EMNLP 2020 11","authors":["Yue Wang","Shafiq Joty","Michael R. Lyu","Irwin King","Caiming Xiong","Steven C. H. Hoi"],"abstract":"Visual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior work has mostly focused on various attention mechanisms to model such intricate interactions. By contrast, in this work, we propose VD-BERT, a simple yet effective framework of unified vision-dialog Transformer that leverages the pretrained BERT language models for Visual Dialog tasks. The model is unified in that (1) it captures all the interactions between the image and the multi-turn dialog using a single-stream Transformer encoder, and (2) it supports both answer ranking and answer generation seamlessly through the same architecture. More crucially, we adapt BERT for the effective fusion of vision and dialog contents via visually grounded training. Without the need of pretraining on external vision-language data, our model yields new state of the art, achieving the top position in both single-model and ensemble settings (74.54 and 75.35 NDCG scores) on the visual dialog leaderboard. Our code and pretrained models are released at https://github.com/salesforce/VD-BERT.","url_abs":"https://arxiv.org/abs/2004.13278v3","url_pdf":"https://arxiv.org/pdf/2004.13278v3.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":"vd-bert-a-unified-vision-and-dialog","repo_url":"https://github.com/salesforce/VD-BERT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"answer-generation","task_name":"Answer Generation"},{"task_slug":"visual-dialogue","task_name":"Visual Dialog"}],"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":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"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":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"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":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.13278","atlas_url":"https://app.syntology.ai/?focus=2004.13278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13278"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/salesforce/VD-BERT","reach":null}],"summary":{"ran":2,"unverified":9},"by_repo_kind":{"official":{"samples":11,"ran":2,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"270c717db63a62be","entry":"BertConfig","repo":"salesforce/VD-BERT","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"270c717db63a62be"}},{"code_sha256_prefix":"39133fc31b6e7ba0","entry":"BertSelfAttention","repo":"salesforce/VD-BERT","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"39133fc31b6e7ba0"}},{"code_sha256_prefix":"a37aa2973e8e5c9f","entry":"BertAttention","repo":"salesforce/VD-BERT","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"a37aa2973e8e5c9f"}},{"code_sha256_prefix":"d128e762e565e2bb","entry":"BertEmbeddings","repo":"salesforce/VD-BERT","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"d128e762e565e2bb"}},{"code_sha256_prefix":"3001206d0b79eb22","entry":"BertEncoder","repo":"salesforce/VD-BERT","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"3001206d0b79eb22"}},{"code_sha256_prefix":"9f308c4ca55ba13a","entry":"BertLayer","repo":"salesforce/VD-BERT","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"9f308c4ca55ba13a"}},{"code_sha256_prefix":"b76586b7d7a5e61f","entry":"BertModel","repo":"salesforce/VD-BERT","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"b76586b7d7a5e61f"}},{"code_sha256_prefix":"4339e883ae5cd42b","entry":"BertModelIncr","repo":"salesforce/VD-BERT","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"4339e883ae5cd42b"}},{"code_sha256_prefix":"4a7f9dbc40aaed5d","entry":"BertOutput","repo":"salesforce/VD-BERT","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"4a7f9dbc40aaed5d"}},{"code_sha256_prefix":"3b0ae0e2b34fdf2e","entry":"BertSelfOutput","repo":"salesforce/VD-BERT","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"3b0ae0e2b34fdf2e"}},{"code_sha256_prefix":"6d0e6e5f9872487f","entry":"PreTrainedBertModel","repo":"salesforce/VD-BERT","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"6d0e6e5f9872487f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}