{"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/plip-language-image-pre-training-for-person","title":"PLIP: Language-Image Pre-training for Person Representation Learning","arxiv_id":"2305.08386","date":"2023-05-15","proceeding":null,"authors":["Jialong Zuo","Jiahao Hong","Feng Zhang","Changqian Yu","Hanyu Zhou","Changxin Gao","Nong Sang","Jingdong Wang"],"abstract":"Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory performance. The reason is that they neglect critical person-related characteristics, i.e., fine-grained attributes and identities. To address this issue, we propose a novel language-image pre-training framework for person representation learning, termed PLIP. Specifically, we elaborately design three pretext tasks: 1) Text-guided Image Colorization, aims to establish the correspondence between the person-related image regions and the fine-grained color-part textual phrases. 2) Image-guided Attributes Prediction, aims to mine fine-grained attribute information of the person body in the image; and 3) Identity-based Vision-Language Contrast, aims to correlate the cross-modal representations at the identity level rather than the instance level. Moreover, to implement our pre-train framework, we construct a large-scale person dataset with image-text pairs named SYNTH-PEDES by automatically generating textual annotations. We pre-train PLIP on SYNTH-PEDES and evaluate our models by spanning downstream person-centric tasks. PLIP not only significantly improves existing methods on all these tasks, but also shows great ability in the zero-shot and domain generalization settings. The code, dataset and weights will be released at~\\url{https://github.com/Zplusdragon/PLIP}","url_abs":"https://arxiv.org/abs/2305.08386v2","url_pdf":"https://arxiv.org/pdf/2305.08386v2.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":"plip-language-image-pre-training-for-person","repo_url":"https://github.com/zplusdragon/plip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"pedestrian-attribute-recognition","task_name":"Pedestrian Attribute Recognition"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"nlp-based-person-retrival","task_name":"Text based Person Retrieval"},{"task_slug":"text-based-person-retrieval","task_name":"Text-based Person Retrieval"}],"methods":[{"method_slug":"plip","method_name":"PLIP"}],"datasets_introduced":[{"slug":"synth-pedes","name":"SYNTH-PEDES","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"PLIP-RN50-MGN","rank_in_archive_order":35,"of":94,"metrics":{"mAP":"81.7"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"PLIP-RN50-ABDNet","rank_in_archive_order":127,"of":135,"metrics":{"mAP":"91.2"},"uses_additional_data":false},{"leaderboard":"/sota/text-based-person-retrieval-on-icfg-pedes","task":"Text based Person Retrieval","dataset":"ICFG-PEDES","model":"PLIP-RN50","rank_in_archive_order":7,"of":12,"metrics":{"R@1":"64.25","R@10":"86.32","R@5":"80.88"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.08386","atlas_url":"https://app.syntology.ai/?focus=2305.08386","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.08386"}},"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/zplusdragon/plip","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"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":"0d7629fa4e046920","entry":"Create_model","repo":"zplusdragon/plip","repo_kind":"official","path":"Downstreams/CMPM-C/model.py","file_url":"https://github.com/zplusdragon/plip/blob/HEAD/Downstreams/CMPM-C/model.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":"0d7629fa4e046920"}},{"code_sha256_prefix":"4ccd7de6989659c6","entry":"compute_topk","repo":"zplusdragon/plip","repo_kind":"official","path":"Downstreams/CMPM-C/utils.py","file_url":"https://github.com/zplusdragon/plip/blob/HEAD/Downstreams/CMPM-C/utils.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":"4ccd7de6989659c6"}},{"code_sha256_prefix":"57ae9f6a6a29d5b3","entry":"create_optimizer","repo":"zplusdragon/plip","repo_kind":"official","path":"Downstreams/CMPM-C/optimizer.py","file_url":"https://github.com/zplusdragon/plip/blob/HEAD/Downstreams/CMPM-C/optimizer.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":"57ae9f6a6a29d5b3"}},{"code_sha256_prefix":"b4ebb1de75f2cf57","entry":"get_loader_test","repo":"zplusdragon/plip","repo_kind":"official","path":"Downstreams/CMPM-C/dataloader.py","file_url":"https://github.com/zplusdragon/plip/blob/HEAD/Downstreams/CMPM-C/dataloader.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":"b4ebb1de75f2cf57"}},{"code_sha256_prefix":"37854be4ad8fe76e","entry":"gradual_warmup","repo":"zplusdragon/plip","repo_kind":"official","path":"Downstreams/CMPM-C/utils.py","file_url":"https://github.com/zplusdragon/plip/blob/HEAD/Downstreams/CMPM-C/utils.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":"37854be4ad8fe76e"}},{"code_sha256_prefix":"87c0152a55e9d1aa","entry":"image_to_patch","repo":"zplusdragon/plip","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zplusdragon/plip/blob/HEAD/utils.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":"87c0152a55e9d1aa"}},{"code_sha256_prefix":"a31fc96a7b978b35","entry":"lr_scheduler","repo":"zplusdragon/plip","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zplusdragon/plip/blob/HEAD/utils.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":"a31fc96a7b978b35"}},{"code_sha256_prefix":"7e5735c288ba3ced","entry":"mask_ratio_scheduler","repo":"zplusdragon/plip","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zplusdragon/plip/blob/HEAD/utils.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":"7e5735c288ba3ced"}},{"code_sha256_prefix":"2b71a5dd46418465","entry":"test","repo":"zplusdragon/plip","repo_kind":"official","path":"zs_infer.py","file_url":"https://github.com/zplusdragon/plip/blob/HEAD/zs_infer.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":"2b71a5dd46418465"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}