{"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/unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","arxiv_id":"1909.11059","date":"2019-09-24","proceeding":null,"authors":["Luowei Zhou","Hamid Palangi","Lei Zhang","Houdong Hu","Jason J. Corso","Jianfeng Gao"],"abstract":"This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering) tasks, and (2) it uses a shared multi-layer transformer network for both encoding and decoding, which differs from many existing methods where the encoder and decoder are implemented using separate models. The unified VLP model is pre-trained on a large amount of image-text pairs using the unsupervised learning objectives of two tasks: bidirectional and sequence-to-sequence (seq2seq) masked vision-language prediction. The two tasks differ solely in what context the prediction conditions on. This is controlled by utilizing specific self-attention masks for the shared transformer network. To the best of our knowledge, VLP is the first reported model that achieves state-of-the-art results on both vision-language generation and understanding tasks, as disparate as image captioning and visual question answering, across three challenging benchmark datasets: COCO Captions, Flickr30k Captions, and VQA 2.0. The code and the pre-trained models are available at https://github.com/LuoweiZhou/VLP.","url_abs":"https://arxiv.org/abs/1909.11059v3","url_pdf":"https://arxiv.org/pdf/1909.11059v3.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":"unified-vision-language-pre-training-for","repo_url":"https://github.com/LuoweiZhou/VLP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"unified-vision-language-pre-training-for","repo_url":"https://github.com/WebQnA/WebQA_Baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unified-vision-language-pre-training-for","repo_url":"https://github.com/rmokady/clip_prefix_caption","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"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":"unified-vlp","method_name":"Unified VLP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-captioning-on-coco-captions-test","task":"Image Captioning","dataset":"COCO Captions test","model":"Unified VLP","rank_in_archive_order":2,"of":2,"metrics":{"BLEU-4":"36.5","CIDEr":"116.9","METEOR":"28.4","SPICE":"21.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-flickr30k-captions-test","task":"Image Captioning","dataset":"Flickr30k Captions test","model":"Unified VLP","rank_in_archive_order":1,"of":7,"metrics":{"BLEU-4":"30.1","CIDEr":"67.4","METEOR":"23","SPICE":"17"},"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":"Unified VLP","rank_in_archive_order":26,"of":38,"metrics":{"overall":"70.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.11059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11059"}},"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/WebQnA/WebQA_Baseline","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rmokady/clip_prefix_caption","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LuoweiZhou/VLP","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran":1,"ran_honours":1,"unverified":9},"by_repo_kind":{"official":{"samples":14,"ran":5,"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":13,"samples":[{"code_sha256_prefix":"0f786c407fb1ee4c","entry":"swish","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/pytorch_pretrained_bert/modeling.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"cab04f1e2101c79a","entry":"array_to_str","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"vlp/scst_utils.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/vlp/scst_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cab04f1e2101c79a"}},{"code_sha256_prefix":"633d1e424a09eb70","entry":"detokenize","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"vlp/decode_img2txt.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/vlp/decode_img2txt.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"633d1e424a09eb70"}},{"code_sha256_prefix":"40e9fee2e0b7e278","entry":"gelu","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/pytorch_pretrained_bert/modeling.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"code_sha256_prefix":"af64ec220e8bcdbc","entry":"url_to_filename","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"pytorch_pretrained_bert/file_utils.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/pytorch_pretrained_bert/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"af64ec220e8bcdbc"}},{"code_sha256_prefix":"7ff0d3834d30ddb5","entry":"batch_list_to_batch_tensors","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"vlp/loader_utils.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/vlp/loader_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"7ff0d3834d30ddb5"}},{"code_sha256_prefix":"349d780dd4a89a37","entry":"cached_path","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"pytorch_pretrained_bert/file_utils.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/pytorch_pretrained_bert/file_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"349d780dd4a89a37"}},{"code_sha256_prefix":"db0ac56aaf6e35e6","entry":"filename_to_url","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"pytorch_pretrained_bert/file_utils.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/pytorch_pretrained_bert/file_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"db0ac56aaf6e35e6"}},{"code_sha256_prefix":"0dc4252bed90db68","entry":"get_random_word","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"vlp/loader_utils.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/vlp/loader_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0dc4252bed90db68"}},{"code_sha256_prefix":"c681ae13f540b4a3","entry":"language_eval","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"vlp/lang_utils.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/vlp/lang_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c681ae13f540b4a3"}},{"code_sha256_prefix":"162a4118bd4b42b1","entry":"scatter_imbalance","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"misc/data_parallel.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/misc/data_parallel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"162a4118bd4b42b1"}},{"code_sha256_prefix":"1f83e9eb8603cd57","entry":"scatter_kwargs_imbalance","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"misc/data_parallel.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/misc/data_parallel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1f83e9eb8603cd57"}},{"code_sha256_prefix":"df768a32f36d7728","entry":"to_contiguous","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"vlp/scst_utils.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/vlp/scst_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"df768a32f36d7728"}},{"code_sha256_prefix":"900f8d4b7c3c4f40","entry":"truncate_tokens_pair","repo":"LuoweiZhou/VLP","repo_kind":"official","path":"vlp/seq2seq_loader.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/vlp/seq2seq_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"900f8d4b7c3c4f40"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}