{"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/versatile-multi-modal-pre-training-for-human","title":"Versatile Multi-Modal Pre-Training for Human-Centric Perception","arxiv_id":"2203.13815","date":"2022-03-25","proceeding":"CVPR 2022 1","authors":["Fangzhou Hong","Liang Pan","Zhongang Cai","Ziwei Liu"],"abstract":"Human-centric perception plays a vital role in vision and graphics. But their data annotations are prohibitively expensive. Therefore, it is desirable to have a versatile pre-train model that serves as a foundation for data-efficient downstream tasks transfer. To this end, we propose the Human-Centric Multi-Modal Contrastive Learning framework HCMoCo that leverages the multi-modal nature of human data (e.g. RGB, depth, 2D keypoints) for effective representation learning. The objective comes with two main challenges: dense pre-train for multi-modality data, efficient usage of sparse human priors. To tackle the challenges, we design the novel Dense Intra-sample Contrastive Learning and Sparse Structure-aware Contrastive Learning targets by hierarchically learning a modal-invariant latent space featured with continuous and ordinal feature distribution and structure-aware semantic consistency. HCMoCo provides pre-train for different modalities by combining heterogeneous datasets, which allows efficient usage of existing task-specific human data. Extensive experiments on four downstream tasks of different modalities demonstrate the effectiveness of HCMoCo, especially under data-efficient settings (7.16% and 12% improvement on DensePose Estimation and Human Parsing). Moreover, we demonstrate the versatility of HCMoCo by exploring cross-modality supervision and missing-modality inference, validating its strong ability in cross-modal association and reasoning.","url_abs":"https://arxiv.org/abs/2203.13815v1","url_pdf":"https://arxiv.org/pdf/2203.13815v1.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":"versatile-multi-modal-pre-training-for-human","repo_url":"https://github.com/hongfz16/hcmoco","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"human-parsing","task_name":"Human Parsing"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.13815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13815"}},"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/hongfz16/hcmoco","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":9},"by_repo_kind":{"official":{"samples":11,"ran":2,"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":"d9def42110729a85","entry":"conv1x1","repo":"hongfz16/hcmoco","repo_kind":"official","path":"A2J/resnet.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/A2J/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"hongfz16/hcmoco","repo_kind":"official","path":"A2J/hrnet/official_hrnet.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/A2J/hrnet/official_hrnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"b2d53cc48ea1cb28","entry":"build_linear","repo":"hongfz16/hcmoco","repo_kind":"official","path":"pycontrast/networks/build_linear.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/pycontrast/networks/build_linear.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":"b2d53cc48ea1cb28"}},{"code_sha256_prefix":"fe0aa3d3b690e0dc","entry":"build_model","repo":"hongfz16/hcmoco","repo_kind":"official","path":"pycontrast/networks/build_backbone.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/pycontrast/networks/build_backbone.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":"fe0aa3d3b690e0dc"}},{"code_sha256_prefix":"25300fd4c866b19b","entry":"build_segmentor","repo":"hongfz16/hcmoco","repo_kind":"official","path":"pycontrast/networks/build_linear.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/pycontrast/networks/build_linear.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":"25300fd4c866b19b"}},{"code_sha256_prefix":"25d0e9bb83f15fe8","entry":"conv3x3","repo":"hongfz16/hcmoco","repo_kind":"official","path":"A2J/resnet.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/A2J/resnet.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":"25d0e9bb83f15fe8"}},{"code_sha256_prefix":"90f11ad439eb9eac","entry":"generate_anchors","repo":"hongfz16/hcmoco","repo_kind":"official","path":"A2J/anchor.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/A2J/anchor.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":"90f11ad439eb9eac"}},{"code_sha256_prefix":"2064af1371b9ba93","entry":"get_hrnet_w48_backbone","repo":"hongfz16/hcmoco","repo_kind":"official","path":"A2J/hrnet/official_hrnet.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/A2J/hrnet/official_hrnet.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":"2064af1371b9ba93"}},{"code_sha256_prefix":"226ea34fe84b3e48","entry":"get_seg_model","repo":"hongfz16/hcmoco","repo_kind":"official","path":"A2J/hrnet/official_hrnet.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/A2J/hrnet/official_hrnet.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":"226ea34fe84b3e48"}},{"code_sha256_prefix":"190a23da3ae32160","entry":"resnet18","repo":"hongfz16/hcmoco","repo_kind":"official","path":"A2J/resnet.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/A2J/resnet.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":"190a23da3ae32160"}},{"code_sha256_prefix":"8308f24a0a9426f4","entry":"shift","repo":"hongfz16/hcmoco","repo_kind":"official","path":"A2J/anchor.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/A2J/anchor.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":"8308f24a0a9426f4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}