{"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-implicit-relation-reasoning-and","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","arxiv_id":"2303.12501","date":"2023-03-22","proceeding":"CVPR 2023 1","authors":["Ding Jiang","Mang Ye"],"abstract":"Text-to-image person retrieval aims to identify the target person based on a given textual description query. The primary challenge is to learn the mapping of visual and textual modalities into a common latent space. Prior works have attempted to address this challenge by leveraging separately pre-trained unimodal models to extract visual and textual features. However, these approaches lack the necessary underlying alignment capabilities required to match multimodal data effectively. Besides, these works use prior information to explore explicit part alignments, which may lead to the distortion of intra-modality information. To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision. Specifically, we first design an Implicit Relation Reasoning module in a masked language modeling paradigm. This achieves cross-modal interaction by integrating the visual cues into the textual tokens with a cross-modal multimodal interaction encoder. Secondly, to globally align the visual and textual embeddings, Similarity Distribution Matching is proposed to minimize the KL divergence between image-text similarity distributions and the normalized label matching distributions. The proposed method achieves new state-of-the-art results on all three public datasets, with a notable margin of about 3%-9% for Rank-1 accuracy compared to prior methods.","url_abs":"https://arxiv.org/abs/2303.12501v1","url_pdf":"https://arxiv.org/pdf/2303.12501v1.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-implicit-relation-reasoning-and","repo_url":"https://github.com/anosorae/irra","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":"person-retrieval","task_name":"Person Retrieval"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-matching","task_name":"Text Matching"},{"task_slug":"nlp-based-person-retrival","task_name":"Text based Person Retrieval"},{"task_slug":"text-based-person-retrieval","task_name":"Text-based Person Retrieval"},{"task_slug":"text-based-person-retrieval-with-noisy","task_name":"Text-based Person Retrieval with Noisy Correspondence"},{"task_slug":"multimodal-interaction","task_name":"multimodal interaction"},{"task_slug":"text-similarity","task_name":"text similarity"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-based-person-retrieval-on-icfg-pedes","task":"Text based Person Retrieval","dataset":"ICFG-PEDES","model":"IRRA","rank_in_archive_order":8,"of":12,"metrics":{"R@1":"63.46","R@10":"85.82","R@5":"80.25","mAP":"38.06","mINP":"7.93"},"uses_additional_data":true},{"leaderboard":"/sota/text-based-person-retrieval-on-rstpreid-1","task":"Text based Person Retrieval","dataset":"RSTPReid","model":"IRRA","rank_in_archive_order":7,"of":9,"metrics":{"R@1":"60.20","R@10":"81.30","R@5":"88.20"},"uses_additional_data":true},{"leaderboard":"/sota/text-based-person-retrieval-with-noisy","task":"Text-based Person Retrieval with Noisy Correspondence","dataset":"CUHK-PEDES","model":"IRRA","rank_in_archive_order":3,"of":6,"metrics":{"Rank 10":"92.20","Rank-1":"69.74","Rank-5":"87.09","mAP":"62.28","mINP":"45.84"},"uses_additional_data":true},{"leaderboard":"/sota/text-based-person-retrieval-with-noisy-1","task":"Text-based Person Retrieval with Noisy Correspondence","dataset":"ICFG-PEDES","model":"IRRA","rank_in_archive_order":3,"of":6,"metrics":{"Rank 1":"60.76","Rank-10":"84.01","Rank-5":"78.26","mAP":"35.87","mINP":"6.80"},"uses_additional_data":true},{"leaderboard":"/sota/text-based-person-retrieval-with-noisy-2","task":"Text-based Person Retrieval with Noisy Correspondence","dataset":"RSTPReid","model":"IRRA","rank_in_archive_order":3,"of":6,"metrics":{"Rank 1":"58.75","Rank 10":"88.25","Rank 5":"81.90","mAP":"46.38","mINP":"24.78"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.12501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12501"}},"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/anosorae/irra","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":9,"ran":5,"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":"03b49fee1c4ea883","entry":"AttentionPool2d","repo":"anosorae/irra","repo_kind":"official","path":"model/build.py","file_url":"https://github.com/anosorae/irra/blob/HEAD/model/build.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03b49fee1c4ea883"}},{"code_sha256_prefix":"88e333b1d22a6f6a","entry":"ModifiedResNet","repo":"anosorae/irra","repo_kind":"official","path":"model/build.py","file_url":"https://github.com/anosorae/irra/blob/HEAD/model/build.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88e333b1d22a6f6a"}},{"code_sha256_prefix":"8d1b78ed1b645333","entry":"VisionTransformer","repo":"anosorae/irra","repo_kind":"official","path":"model/build.py","file_url":"https://github.com/anosorae/irra/blob/HEAD/model/build.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d1b78ed1b645333"}},{"code_sha256_prefix":"571e8713488818e6","entry":"available_models","repo":"anosorae/irra","repo_kind":"official","path":"model/build.py","file_url":"https://github.com/anosorae/irra/blob/HEAD/model/build.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"571e8713488818e6"}},{"code_sha256_prefix":"46ab65070a560ea7","entry":"resize_pos_embed","repo":"anosorae/irra","repo_kind":"official","path":"model/build.py","file_url":"https://github.com/anosorae/irra/blob/HEAD/model/build.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46ab65070a560ea7"}},{"code_sha256_prefix":"36986ffbd858f742","entry":"CLIP","repo":"anosorae/irra","repo_kind":"official","path":"model/build.py","file_url":"https://github.com/anosorae/irra/blob/HEAD/model/build.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":"36986ffbd858f742"}},{"code_sha256_prefix":"a09d9efccb4269b5","entry":"IRRA","repo":"anosorae/irra","repo_kind":"official","path":"model/build.py","file_url":"https://github.com/anosorae/irra/blob/HEAD/model/build.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":"a09d9efccb4269b5"}},{"code_sha256_prefix":"c86fa5cb055d987d","entry":"_download","repo":"anosorae/irra","repo_kind":"official","path":"model/build.py","file_url":"https://github.com/anosorae/irra/blob/HEAD/model/build.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":"c86fa5cb055d987d"}},{"code_sha256_prefix":"2d184b2be5eb0d13","entry":"build_CLIP_from_openai_pretrained","repo":"anosorae/irra","repo_kind":"official","path":"model/build.py","file_url":"https://github.com/anosorae/irra/blob/HEAD/model/build.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":"2d184b2be5eb0d13"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}