{"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/towards-zero-shot-cross-lingual-image-1","title":"Towards Zero-shot Cross-lingual Image Retrieval and Tagging","arxiv_id":"2109.07622","date":"2021-09-15","proceeding":null,"authors":["Pranav Aggarwal","Ritiz Tambi","Ajinkya Kale"],"abstract":"There has been a recent spike in interest in multi-modal Language and Vision problems. On the language side, most of these models primarily focus on English since most multi-modal datasets are monolingual. We try to bridge this gap with a zero-shot approach for learning multi-modal representations using cross-lingual pre-training on the text side. We present a simple yet practical approach for building a cross-lingual image retrieval model which trains on a monolingual training dataset but can be used in a zero-shot cross-lingual fashion during inference. We also introduce a new objective function which tightens the text embedding clusters by pushing dissimilar texts away from each other. For evaluation, we introduce a new 1K multi-lingual MSCOCO2014 caption test dataset (XTD10) in 7 languages that we collected using a crowdsourcing platform. We use this as the test set for zero-shot model performance across languages. We also demonstrate how a cross-lingual model can be used for downstream tasks like multi-lingual image tagging in a zero shot manner. XTD10 dataset is made publicly available here: https://github.com/adobe-research/Cross-lingual-Test-Dataset-XTD10.","url_abs":"https://arxiv.org/abs/2109.07622v1","url_pdf":"https://arxiv.org/pdf/2109.07622v1.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":"towards-zero-shot-cross-lingual-image-1","repo_url":"https://github.com/adobe-research/Cross-lingual-Test-Dataset-XTD10","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"towards-zero-shot-cross-lingual-image-1","repo_url":"https://github.com/FreddeFrallan/Multilingual-CLIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"xtd10","name":"XTD10","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.07622","atlas_url":"https://app.syntology.ai/?focus=2109.07622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07622"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FreddeFrallan/Multilingual-CLIP","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adobe-research/Cross-lingual-Test-Dataset-XTD10","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"listed":{"samples":8,"ran":6,"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":"3fb74a0679cf6044","entry":"createDataset","repo":"FreddeFrallan/Multilingual-CLIP","repo_kind":"listed","path":"multilingual_clip/TeacherLearning/Dataset.py","file_url":"https://github.com/FreddeFrallan/Multilingual-CLIP/blob/HEAD/multilingual_clip/TeacherLearning/Dataset.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":"3fb74a0679cf6044"}},{"code_sha256_prefix":"0388a1f07bdd8902","entry":"createTrainingAndValidationDataset","repo":"FreddeFrallan/Multilingual-CLIP","repo_kind":"listed","path":"multilingual_clip/TeacherLearning/Dataset.py","file_url":"https://github.com/FreddeFrallan/Multilingual-CLIP/blob/HEAD/multilingual_clip/TeacherLearning/Dataset.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":"0388a1f07bdd8902"}},{"code_sha256_prefix":"cb1ad92bf1aa4cce","entry":"custom_collate_fn","repo":"FreddeFrallan/Multilingual-CLIP","repo_kind":"listed","path":"translation/02_translate_multilingual.py","file_url":"https://github.com/FreddeFrallan/Multilingual-CLIP/blob/HEAD/translation/02_translate_multilingual.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":"cb1ad92bf1aa4cce"}},{"code_sha256_prefix":"fa54a724efeb2987","entry":"loadTargetEmbeddings","repo":"FreddeFrallan/Multilingual-CLIP","repo_kind":"listed","path":"multilingual_clip/TeacherLearning/Training.py","file_url":"https://github.com/FreddeFrallan/Multilingual-CLIP/blob/HEAD/multilingual_clip/TeacherLearning/Training.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":"fa54a724efeb2987"}},{"code_sha256_prefix":"d55e6ea8e1bff0dd","entry":"splitIntoValueChunks","repo":"FreddeFrallan/Multilingual-CLIP","repo_kind":"listed","path":"multilingual_clip/TeacherLearning/Utils.py","file_url":"https://github.com/FreddeFrallan/Multilingual-CLIP/blob/HEAD/multilingual_clip/TeacherLearning/Utils.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":"d55e6ea8e1bff0dd"}},{"code_sha256_prefix":"7c8aa0fb63b4ea23","entry":"splitListIntoChunks","repo":"FreddeFrallan/Multilingual-CLIP","repo_kind":"listed","path":"multilingual_clip/TeacherLearning/Utils.py","file_url":"https://github.com/FreddeFrallan/Multilingual-CLIP/blob/HEAD/multilingual_clip/TeacherLearning/Utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c8aa0fb63b4ea23"}},{"code_sha256_prefix":"8ff441d03da0ffed","entry":"loadTokenizer","repo":"FreddeFrallan/Multilingual-CLIP","repo_kind":"listed","path":"multilingual_clip/TeacherLearning/Utils.py","file_url":"https://github.com/FreddeFrallan/Multilingual-CLIP/blob/HEAD/multilingual_clip/TeacherLearning/Utils.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":"8ff441d03da0ffed"}},{"code_sha256_prefix":"325e7d8398013efd","entry":"load_model","repo":"FreddeFrallan/Multilingual-CLIP","repo_kind":"listed","path":"multilingual_clip/legacy_multilingual_clip.py","file_url":"https://github.com/FreddeFrallan/Multilingual-CLIP/blob/HEAD/multilingual_clip/legacy_multilingual_clip.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":"325e7d8398013efd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}