{"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/cross-modal-retrieval-for-knowledge-based","title":"Cross-modal Retrieval for Knowledge-based Visual Question Answering","arxiv_id":"2401.05736","date":"2024-01-11","proceeding":null,"authors":["Paul Lerner","Olivier Ferret","Camille Guinaudeau"],"abstract":"Knowledge-based Visual Question Answering about Named Entities is a challenging task that requires retrieving information from a multimodal Knowledge Base. Named entities have diverse visual representations and are therefore difficult to recognize. We argue that cross-modal retrieval may help bridge the semantic gap between an entity and its depictions, and is foremost complementary with mono-modal retrieval. We provide empirical evidence through experiments with a multimodal dual encoder, namely CLIP, on the recent ViQuAE, InfoSeek, and Encyclopedic-VQA datasets. Additionally, we study three different strategies to fine-tune such a model: mono-modal, cross-modal, or joint training. Our method, which combines mono-and cross-modal retrieval, is competitive with billion-parameter models on the three datasets, while being conceptually simpler and computationally cheaper.","url_abs":"https://arxiv.org/abs/2401.05736v1","url_pdf":"https://arxiv.org/pdf/2401.05736v1.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":"cross-modal-retrieval-for-knowledge-based","repo_url":"https://github.com/paullerner/viquae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"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":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.05736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05736"}},"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/paullerner/viquae","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":4,"unverified":7},"by_repo_kind":{"official":{"samples":11,"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":11,"samples":[{"code_sha256_prefix":"8a5bbb57c7e37a1b","entry":"get_best_spans","repo":"paullerner/viquae","repo_kind":"official","path":"meerqat/models/qa.py","file_url":"https://github.com/paullerner/viquae/blob/HEAD/meerqat/models/qa.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8a5bbb57c7e37a1b"}},{"code_sha256_prefix":"f9ac9b65a5d2c881","entry":"get_encoder","repo":"paullerner/viquae","repo_kind":"official","path":"meerqat/image/embedding.py","file_url":"https://github.com/paullerner/viquae/blob/HEAD/meerqat/image/embedding.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f9ac9b65a5d2c881"}},{"code_sha256_prefix":"1c217b274340313b","entry":"overwrite_bert_config","repo":"paullerner/viquae","repo_kind":"official","path":"meerqat/models/mm.py","file_url":"https://github.com/paullerner/viquae/blob/HEAD/meerqat/models/mm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1c217b274340313b"}},{"code_sha256_prefix":"5f326428e6fbad60","entry":"prepare_inputs","repo":"paullerner/viquae","repo_kind":"official","path":"meerqat/models/utils.py","file_url":"https://github.com/paullerner/viquae/blob/HEAD/meerqat/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5f326428e6fbad60"}},{"code_sha256_prefix":"1d2c69ba4291ccfc","entry":"dataset_detect_face","repo":"paullerner/viquae","repo_kind":"official","path":"meerqat/image/face_detection.py","file_url":"https://github.com/paullerner/viquae/blob/HEAD/meerqat/image/face_detection.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1d2c69ba4291ccfc"}},{"code_sha256_prefix":"33c02545052fa630","entry":"dataset_detect_faces","repo":"paullerner/viquae","repo_kind":"official","path":"meerqat/image/face_detection.py","file_url":"https://github.com/paullerner/viquae/blob/HEAD/meerqat/image/face_detection.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"33c02545052fa630"}},{"code_sha256_prefix":"803711dbc2585ec9","entry":"detect_face","repo":"paullerner/viquae","repo_kind":"official","path":"meerqat/image/face_detection.py","file_url":"https://github.com/paullerner/viquae/blob/HEAD/meerqat/image/face_detection.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"803711dbc2585ec9"}},{"code_sha256_prefix":"9955e310f84fd923","entry":"from_pretrained","repo":"paullerner/viquae","repo_kind":"official","path":"meerqat/image/embedding.py","file_url":"https://github.com/paullerner/viquae/blob/HEAD/meerqat/image/embedding.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9955e310f84fd923"}},{"code_sha256_prefix":"e0c8e4c513b000b4","entry":"get_nn_module","repo":"paullerner/viquae","repo_kind":"official","path":"meerqat/image/embedding.py","file_url":"https://github.com/paullerner/viquae/blob/HEAD/meerqat/image/embedding.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e0c8e4c513b000b4"}},{"code_sha256_prefix":"092bade66d8c1956","entry":"map_if_not_None","repo":"paullerner/viquae","repo_kind":"official","path":"meerqat/models/utils.py","file_url":"https://github.com/paullerner/viquae/blob/HEAD/meerqat/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"092bade66d8c1956"}},{"code_sha256_prefix":"dbe6a522b61fa983","entry":"scale_box","repo":"paullerner/viquae","repo_kind":"official","path":"meerqat/image/face_box.py","file_url":"https://github.com/paullerner/viquae/blob/HEAD/meerqat/image/face_box.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"dbe6a522b61fa983"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}