{"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/aggpose-deep-aggregation-vision-transformer","title":"AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation","arxiv_id":"2205.05277","date":"2022-05-11","proceeding":null,"authors":["Xu Cao","Xiaoye Li","Liya Ma","Yi Huang","Xuan Feng","Zening Chen","Hongwu Zeng","Jianguo Cao"],"abstract":"Movement and pose assessment of newborns lets experienced pediatricians predict neurodevelopmental disorders, allowing early intervention for related diseases. However, most of the newest AI approaches for human pose estimation methods focus on adults, lacking publicly benchmark for infant pose estimation. In this paper, we fill this gap by proposing infant pose dataset and Deep Aggregation Vision Transformer for human pose estimation, which introduces a fast trained full transformer framework without using convolution operations to extract features in the early stages. It generalizes Transformer + MLP to high-resolution deep layer aggregation within feature maps, thus enabling information fusion between different vision levels. We pre-train AggPose on COCO pose dataset and apply it on our newly released large-scale infant pose estimation dataset. The results show that AggPose could effectively learn the multi-scale features among different resolutions and significantly improve the performance of infant pose estimation. We show that AggPose outperforms hybrid model HRFormer and TokenPose in the infant pose estimation dataset. Moreover, our AggPose outperforms HRFormer by 0.8 AP on COCO val pose estimation on average. Our code is available at github.com/SZAR-LAB/AggPose.","url_abs":"https://arxiv.org/abs/2205.05277v2","url_pdf":"https://arxiv.org/pdf/2205.05277v2.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":"aggpose-deep-aggregation-vision-transformer","repo_url":"https://github.com/szar-lab/aggpose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"tasks":[{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keypoint-detection-on-coco","task":"Keypoint Detection","dataset":"COCO (Common Objects in Context)","model":"AggPose(256x192)","rank_in_archive_order":7,"of":24,"metrics":{"Test AP":"75.7","Validation AP":"76.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.05277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05277"}},"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/szar-lab/aggpose","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/SZAR-LAB/AggPose","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"58193b289e41db55","entry":"Attention","repo":"SZAR-LAB/AggPose","repo_kind":"official","path":"lib/models/pose_aggpose.py","file_url":"https://github.com/SZAR-LAB/AggPose/blob/HEAD/lib/models/pose_aggpose.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"58193b289e41db55"}},{"code_sha256_prefix":"e68b276a44902fe9","entry":"DWConv","repo":"SZAR-LAB/AggPose","repo_kind":"official","path":"lib/models/pose_aggpose.py","file_url":"https://github.com/SZAR-LAB/AggPose/blob/HEAD/lib/models/pose_aggpose.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e68b276a44902fe9"}},{"code_sha256_prefix":"150e9a8b4f87d226","entry":"Mlp","repo":"SZAR-LAB/AggPose","repo_kind":"official","path":"lib/models/pose_aggpose.py","file_url":"https://github.com/SZAR-LAB/AggPose/blob/HEAD/lib/models/pose_aggpose.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"150e9a8b4f87d226"}},{"code_sha256_prefix":"48c4de8068ed4f7a","entry":"MlpUpsample","repo":"SZAR-LAB/AggPose","repo_kind":"official","path":"lib/models/pose_aggpose.py","file_url":"https://github.com/SZAR-LAB/AggPose/blob/HEAD/lib/models/pose_aggpose.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"48c4de8068ed4f7a"}},{"code_sha256_prefix":"c319db933db9b552","entry":"OverlapPatchEmbed","repo":"SZAR-LAB/AggPose","repo_kind":"official","path":"lib/models/pose_aggpose.py","file_url":"https://github.com/SZAR-LAB/AggPose/blob/HEAD/lib/models/pose_aggpose.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c319db933db9b552"}},{"code_sha256_prefix":"599ead8c797aad19","entry":"AggPose","repo":"SZAR-LAB/AggPose","repo_kind":"official","path":"lib/models/pose_aggpose.py","file_url":"https://github.com/SZAR-LAB/AggPose/blob/HEAD/lib/models/pose_aggpose.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"599ead8c797aad19"}},{"code_sha256_prefix":"f5274e90d3e2d72b","entry":"Block","repo":"SZAR-LAB/AggPose","repo_kind":"official","path":"lib/models/pose_aggpose.py","file_url":"https://github.com/SZAR-LAB/AggPose/blob/HEAD/lib/models/pose_aggpose.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f5274e90d3e2d72b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}