{"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/uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","arxiv_id":"1909.11740","date":"2019-09-25","proceeding":"ECCV 2020 8","authors":["Yen-Chun Chen","Linjie Li","Licheng Yu","Ahmed El Kholy","Faisal Ahmed","Zhe Gan","Yu Cheng","Jingjing Liu"],"abstract":"Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal Image-TExt Representation, learned through large-scale pre-training over four image-text datasets (COCO, Visual Genome, Conceptual Captions, and SBU Captions), which can power heterogeneous downstream V+L tasks with joint multimodal embeddings. We design four pre-training tasks: Masked Language Modeling (MLM), Masked Region Modeling (MRM, with three variants), Image-Text Matching (ITM), and Word-Region Alignment (WRA). Different from previous work that applies joint random masking to both modalities, we use conditional masking on pre-training tasks (i.e., masked language/region modeling is conditioned on full observation of image/text). In addition to ITM for global image-text alignment, we also propose WRA via the use of Optimal Transport (OT) to explicitly encourage fine-grained alignment between words and image regions during pre-training. Comprehensive analysis shows that both conditional masking and OT-based WRA contribute to better pre-training. We also conduct a thorough ablation study to find an optimal combination of pre-training tasks. Extensive experiments show that UNITER achieves new state of the art across six V+L tasks (over nine datasets), including Visual Question Answering, Image-Text Retrieval, Referring Expression Comprehension, Visual Commonsense Reasoning, Visual Entailment, and NLVR$^2$. Code is available at https://github.com/ChenRocks/UNITER.","url_abs":"https://arxiv.org/abs/1909.11740v3","url_pdf":"https://arxiv.org/pdf/1909.11740v3.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":"uniter-learning-universal-image-text-1","repo_url":"https://github.com/ChenRocks/UNITER","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"uniter-learning-universal-image-text-1","repo_url":"https://github.com/SDLZY/VCR_Align","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"uniter-learning-universal-image-text-1","repo_url":"https://github.com/lichengunc/pretrain-vl-data","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"uniter-learning-universal-image-text-1","repo_url":"https://github.com/necla-ml/SNLI-VE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"uniter-learning-universal-image-text-1","repo_url":"https://github.com/vladsandulescu/hatefulmemes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"uniter-learning-universal-image-text-1","repo_url":"https://github.com/xiaomin418/cfsum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"uniter-learning-universal-image-text-1","repo_url":"https://github.com/YIKUAN8/Transformers-VQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"image-text-matching","task_name":"Image-text matching"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-matching","task_name":"Text Matching"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"visual-commonsense-reasoning","task_name":"Visual Commonsense Reasoning"},{"task_slug":"visual-entailment","task_name":"Visual Entailment"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":"zero-shot-cross-modal-retrieval","task_name":"Zero-Shot Cross-Modal Retrieval"}],"methods":[{"method_slug":"uniter","method_name":"UNITER"}],"datasets_introduced":[],"methods_introduced":[{"slug":"uniter","name":"UNITER","full_name":"UNiversal Image-TExt Representation Learning"}],"results":[{"leaderboard":"/sota/visual-entailment-on-snli-ve-test","task":"Visual Entailment","dataset":"SNLI-VE test","model":"UNITER (Large)","rank_in_archive_order":7,"of":8,"metrics":{"Accuracy":"78.98"},"uses_additional_data":false},{"leaderboard":"/sota/visual-entailment-on-snli-ve-val","task":"Visual Entailment","dataset":"SNLI-VE val","model":"UNITER","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"78.98"},"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":"UNITER-large (10 ensemble)","rank_in_archive_order":3,"of":11,"metrics":{"Accuracy":"79.8"},"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":"UNITER (Large)","rank_in_archive_order":5,"of":11,"metrics":{"Accuracy":"77.3"},"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":"UNITER (Large)","rank_in_archive_order":3,"of":7,"metrics":{"Accuracy":"62.8"},"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":"UNITER-large (ensemble of 10 models)","rank_in_archive_order":3,"of":8,"metrics":{"Accuracy":"83.4"},"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":"UNITER (Large)","rank_in_archive_order":4,"of":8,"metrics":{"Accuracy":"80.8"},"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":"UNITER (Large)","rank_in_archive_order":21,"of":56,"metrics":{"Accuracy":"73.24"},"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":"UNITER (Large)","rank_in_archive_order":19,"of":38,"metrics":{"overall":"73.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-test","task":"Visual Reasoning","dataset":"NLVR2 Test","model":"UNITER (Large)","rank_in_archive_order":11,"of":14,"metrics":{"Accuracy":"79.5"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-flickr30k","task":"Zero-Shot Cross-Modal Retrieval","dataset":"Flickr30k","model":"UNITER","rank_in_archive_order":18,"of":22,"metrics":{"Image-to-text R@1":"80.7","Image-to-text R@10":"98.0","Image-to-text R@5":"95.7","Text-to-image R@1":"66.2","Text-to-image R@10":"92.9","Text-to-image R@5":"88.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}},"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/necla-ml/SNLI-VE","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SDLZY/VCR_Align","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vladsandulescu/hatefulmemes","reach":{"status":"unanswered"}},{"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/lichengunc/pretrain-vl-data","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ChenRocks/UNITER","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiaomin418/cfsum","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":2}},"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":2,"samples":[{"code_sha256_prefix":"347953d8bd5d46e8","entry":"evaluate","repo":"SDLZY/VCR_Align","repo_kind":"listed","path":"inf_nlvr2.py","file_url":"https://github.com/SDLZY/VCR_Align/blob/HEAD/inf_nlvr2.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"347953d8bd5d46e8"}},{"code_sha256_prefix":"32ec2df257af200f","entry":"merge_sub_word","repo":"xiaomin418/cfsum","repo_kind":"listed","path":"src/inference.py","file_url":"https://github.com/xiaomin418/cfsum/blob/HEAD/src/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32ec2df257af200f"}},{"code_sha256_prefix":"9bd01ccf1581d378","entry":"merge_sub_word2score","repo":"xiaomin418/cfsum","repo_kind":"listed","path":"src/inference.py","file_url":"https://github.com/xiaomin418/cfsum/blob/HEAD/src/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9bd01ccf1581d378"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}