{"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/universal-multi-modality-retrieval-with-one","title":"Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval","arxiv_id":"2209.00179","date":"2022-09-01","proceeding":null,"authors":["Zhenghao Liu","Chenyan Xiong","Yuanhuiyi Lv","Zhiyuan Liu","Ge Yu"],"abstract":"This paper presents Universal Vision-Language Dense Retrieval (UniVL-DR), which builds a unified model for multi-modal retrieval. UniVL-DR encodes queries and multi-modality resources in an embedding space for searching candidates from different modalities. To learn a unified embedding space for multi-modal retrieval, UniVL-DR proposes two techniques: 1) Universal embedding optimization strategy, which contrastively optimizes the embedding space using the modality-balanced hard negatives; 2) Image verbalization method, which bridges the modality gap between images and texts in the raw data space. UniVL-DR achieves the state-of-the-art on the multi-modal open-domain question answering benchmark, WebQA, and outperforms all retrieval models on the two subtasks, text-text retrieval and text-image retrieval. It demonstrates that universal multi-modal search is feasible to replace the divide-and-conquer pipeline with a united model and also benefits single/cross modality tasks. All source codes of this work are available at https://github.com/OpenMatch/UniVL-DR.","url_abs":"https://arxiv.org/abs/2209.00179v2","url_pdf":"https://arxiv.org/pdf/2209.00179v2.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":"universal-multi-modality-retrieval-with-one","repo_url":"https://github.com/openmatch/univl-dr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.00179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.00179"}},"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/openmatch/univl-dr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":9},"by_repo_kind":{"official":{"samples":13,"ran":4,"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":"5f50bc569621e9e0","entry":"convert_to_string_id","repo":"openmatch/univl-dr","repo_kind":"official","path":"UniVL-DR/retrieval.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/retrieval.py","link_basis":"harvester_set","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":"5f50bc569621e9e0"}},{"code_sha256_prefix":"44dabd5275dfdd74","entry":"load_candidate_from_stream","repo":"openmatch/univl-dr","repo_kind":"official","path":"UniVL-DR/msmarco_eval.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/msmarco_eval.py","link_basis":"harvester_set","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":"44dabd5275dfdd74"}},{"code_sha256_prefix":"73a28fd25464e18b","entry":"load_reference","repo":"openmatch/univl-dr","repo_kind":"official","path":"UniVL-DR/msmarco_eval.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/msmarco_eval.py","link_basis":"harvester_set","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":"73a28fd25464e18b"}},{"code_sha256_prefix":"3bb6407c68aabca4","entry":"load_reference_from_stream","repo":"openmatch/univl-dr","repo_kind":"official","path":"UniVL-DR/msmarco_eval.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/msmarco_eval.py","link_basis":"harvester_set","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":"3bb6407c68aabca4"}},{"code_sha256_prefix":"932d44bbf8bd0e3f","entry":"cosine_lr","repo":"openmatch/univl-dr","repo_kind":"official","path":"UniVL-DR/gen_embeddings.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/gen_embeddings.py","link_basis":"harvester_set","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":"932d44bbf8bd0e3f"}},{"code_sha256_prefix":"bdeeac353609fba9","entry":"load_caps","repo":"openmatch/univl-dr","repo_kind":"official","path":"UniVL-DR/data.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/data.py","link_basis":"harvester_set","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":"bdeeac353609fba9"}},{"code_sha256_prefix":"ba3ccdb2b1dd91b9","entry":"load_docs","repo":"openmatch/univl-dr","repo_kind":"official","path":"UniVL-DR/data.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/data.py","link_basis":"harvester_set","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":"ba3ccdb2b1dd91b9"}},{"code_sha256_prefix":"c332382577bfa765","entry":"load_docs","repo":"openmatch/univl-dr","repo_kind":"official","path":"UniVL-DR/gen_embeddings.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/gen_embeddings.py","link_basis":"harvester_set","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":"c332382577bfa765"}},{"code_sha256_prefix":"657a1b13e0907d5f","entry":"load_file","repo":"openmatch/univl-dr","repo_kind":"official","path":"UniVL-DR/data.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/data.py","link_basis":"harvester_set","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":"657a1b13e0907d5f"}},{"code_sha256_prefix":"ab52e35a4aeb0fdd","entry":"load_file","repo":"openmatch/univl-dr","repo_kind":"official","path":"UniVL-DR/retrieval.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/retrieval.py","link_basis":"harvester_set","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":"ab52e35a4aeb0fdd"}},{"code_sha256_prefix":"03524f1126e7841f","entry":"load_file","repo":"openmatch/univl-dr","repo_kind":"official","path":"CLIP-DPR/data.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/CLIP-DPR/data.py","link_basis":"harvester_set","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":"03524f1126e7841f"}},{"code_sha256_prefix":"10874e9329daa92e","entry":"load_file","repo":"openmatch/univl-dr","repo_kind":"official","path":"CLIP-DPR/get_hard_negs.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/CLIP-DPR/get_hard_negs.py","link_basis":"harvester_set","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":"10874e9329daa92e"}},{"code_sha256_prefix":"d6a43c1609102421","entry":"load_queries","repo":"openmatch/univl-dr","repo_kind":"official","path":"UniVL-DR/gen_embeddings.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/gen_embeddings.py","link_basis":"harvester_set","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":"d6a43c1609102421"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}