{"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/humanbench-towards-general-human-centric","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","arxiv_id":"2303.05675","date":"2023-03-10","proceeding":"CVPR 2023 1","authors":["Shixiang Tang","Cheng Chen","Qingsong Xie","Meilin Chen","Yizhou Wang","Yuanzheng Ci","Lei Bai","Feng Zhu","Haiyang Yang","Li Yi","Rui Zhao","Wanli Ouyang"],"abstract":"Human-centric perceptions include a variety of vision tasks, which have widespread industrial applications, including surveillance, autonomous driving, and the metaverse. It is desirable to have a general pretrain model for versatile human-centric downstream tasks. This paper forges ahead along this path from the aspects of both benchmark and pretraining methods. Specifically, we propose a \\textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting. To learn both coarse-grained and fine-grained knowledge in human bodies, we further propose a \\textbf{P}rojector \\textbf{A}ssis\\textbf{T}ed \\textbf{H}ierarchical pretraining method (\\textbf{PATH}) to learn diverse knowledge at different granularity levels. Comprehensive evaluations on HumanBench show that our PATH achieves new state-of-the-art results on 17 downstream datasets and on-par results on the other 2 datasets. The code will be publicly at \\href{https://github.com/OpenGVLab/HumanBench}{https://github.com/OpenGVLab/HumanBench}.","url_abs":"https://arxiv.org/abs/2303.05675v1","url_pdf":"https://arxiv.org/pdf/2303.05675v1.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":"humanbench-towards-general-human-centric","repo_url":"https://github.com/opengvlab/humanbench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"crowd-counting","task_name":"Crowd Counting"},{"task_slug":"human-parsing","task_name":"Human Parsing"},{"task_slug":"pedestrian-attribute-recognition","task_name":"Pedestrian Attribute Recognition"},{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pedestrian-attribute-recognition-on-pa-100k","task":"Pedestrian Attribute Recognition","dataset":"PA-100K","model":"PATH (Partial FT)","rank_in_archive_order":1,"of":13,"metrics":{"Accuracy":"90.8"},"uses_additional_data":true},{"leaderboard":"/sota/pose-estimation-on-coco","task":"Pose Estimation","dataset":"COCO (Common Objects in Context)","model":"PATH (Partial FT)","rank_in_archive_order":7,"of":10,"metrics":{"AP":"77.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.05675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05675"}},"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/opengvlab/humanbench","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/OpenGVLab/HumanBench","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9,"ran_draft_wrong":4,"ran_honours":1,"ran_fixture":1,"unverified":10},"by_repo_kind":{"official":{"samples":25,"ran":15,"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":"39af89396152713c","entry":"NestedTensor","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"39af89396152713c"}},{"code_sha256_prefix":"9af8e85813684a76","entry":"PatchEmbed","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"9af8e85813684a76"}},{"code_sha256_prefix":"69b9d45d322d1680","entry":"autocast","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"69b9d45d322d1680"}},{"code_sha256_prefix":"68e7a844f6a217c9","entry":"enable_checkpointing","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","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":"68e7a844f6a217c9"}},{"code_sha256_prefix":"d32957ea95e1f955","entry":"enable_recomputing","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","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":"d32957ea95e1f955"}},{"code_sha256_prefix":"0973dbf09d2066c7","entry":"get_2d_sincos_pos_embed","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0973dbf09d2066c7"}},{"code_sha256_prefix":"8dc7dc2bedef1191","entry":"get_abs_pos","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8dc7dc2bedef1191"}},{"code_sha256_prefix":"a88ee7f6d338ad8d","entry":"is_autocast_enabled","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","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":"a88ee7f6d338ad8d"}},{"code_sha256_prefix":"dfb3581e62456ff2","entry":"is_checkpointing","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","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":"dfb3581e62456ff2"}},{"code_sha256_prefix":"60a3f862716c1212","entry":"is_recomputing","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","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":"60a3f862716c1212"}},{"code_sha256_prefix":"87cadb13cda1c63e","entry":"pack_kwargs","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","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":"87cadb13cda1c63e"}},{"code_sha256_prefix":"37dc7bc4f8eea14d","entry":"patch_batchnorm","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37dc7bc4f8eea14d"}},{"code_sha256_prefix":"c0b365b386a2ce5a","entry":"split_non_tensors","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0b365b386a2ce5a"}},{"code_sha256_prefix":"c577116b3b35c1c3","entry":"unpack_kwargs","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c577116b3b35c1c3"}},{"code_sha256_prefix":"e9cfd29d0d37ed43","entry":"unpack_non_tensors","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","link_basis":"first_harvest_node","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":"e9cfd29d0d37ed43"}},{"code_sha256_prefix":"d2b8be1e94eca236","entry":"Attention","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"d2b8be1e94eca236"}},{"code_sha256_prefix":"344d0eb15f2cb514","entry":"Block","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"344d0eb15f2cb514"}},{"code_sha256_prefix":"8e99c11a4e7efdd5","entry":"CheckpointFunction","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"8e99c11a4e7efdd5"}},{"code_sha256_prefix":"c8bcf97bcffa2bfd","entry":"ViT","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"c8bcf97bcffa2bfd"}},{"code_sha256_prefix":"fc286c766c71de79","entry":"WindowAttention","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"fc286c766c71de79"}},{"code_sha256_prefix":"839f42723dc179f9","entry":"_checkpointed_forward","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"839f42723dc179f9"}},{"code_sha256_prefix":"37c5cac4e0bae684","entry":"calc_rel_pos_spatial","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"37c5cac4e0bae684"}},{"code_sha256_prefix":"5de1a5737d6af117","entry":"checkpoint_wrapper","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"5de1a5737d6af117"}},{"code_sha256_prefix":"f6675e1e59cce43a","entry":"get_rng_state","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"f6675e1e59cce43a"}},{"code_sha256_prefix":"9deeaa92c6fb18e5","entry":"set_rng_state","repo":"OpenGVLab/HumanBench","repo_kind":"official","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.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":"9deeaa92c6fb18e5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}