{"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/vista-visualized-text-embedding-for-universal","title":"VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval","arxiv_id":"2406.04292","date":"2024-06-06","proceeding":null,"authors":["Junjie Zhou","Zheng Liu","Shitao Xiao","Bo Zhao","Yongping Xiong"],"abstract":"Multi-modal retrieval becomes increasingly popular in practice. However, the existing retrievers are mostly text-oriented, which lack the capability to process visual information. Despite the presence of vision-language models like CLIP, the current methods are severely limited in representing the text-only and image-only data. In this work, we present a new embedding model VISTA for universal multi-modal retrieval. Our work brings forth threefold technical contributions. Firstly, we introduce a flexible architecture which extends a powerful text encoder with the image understanding capability by introducing visual token embeddings. Secondly, we develop two data generation strategies, which bring high-quality composed image-text to facilitate the training of the embedding model. Thirdly, we introduce a multi-stage training algorithm, which first aligns the visual token embedding with the text encoder using massive weakly labeled data, and then develops multi-modal representation capability using the generated composed image-text data. In our experiments, VISTA achieves superior performances across a variety of multi-modal retrieval tasks in both zero-shot and supervised settings. Our model, data, and source code are available at https://github.com/FlagOpen/FlagEmbedding.","url_abs":"https://arxiv.org/abs/2406.04292v1","url_pdf":"https://arxiv.org/pdf/2406.04292v1.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":"vista-visualized-text-embedding-for-universal","repo_url":"https://github.com/flagopen/flagembedding","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-cirr","task":"Image Retrieval","dataset":"CIRR","model":"VISTA (base)","rank_in_archive_order":9,"of":17,"metrics":{"(Recall@5+Recall_subset@1)/2":"75.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.04292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04292"}},"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/flagopen/flagembedding","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/FlagOpen/FlagEmbedding","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":"f28b605454debf69","entry":"BGEM3Model","repo":"FlagOpen/FlagEmbedding","repo_kind":"official","path":"research/BGE_M3/modeling.py","file_url":"https://github.com/FlagOpen/FlagEmbedding/blob/HEAD/research/BGE_M3/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":"f28b605454debf69"}},{"code_sha256_prefix":"34b44d6cb35d6dec","entry":"EncoderOutput","repo":"FlagOpen/FlagEmbedding","repo_kind":"official","path":"research/BGE_M3/modeling.py","file_url":"https://github.com/FlagOpen/FlagEmbedding/blob/HEAD/research/BGE_M3/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":"34b44d6cb35d6dec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}