{"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/mixste-seq2seq-mixed-spatio-temporal-encoder","title":"MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video","arxiv_id":"2203.00859","date":"2022-03-02","proceeding":"CVPR 2022 1","authors":["Jinlu Zhang","Zhigang Tu","Jianyu Yang","Yujin Chen","Junsong Yuan"],"abstract":"Recent transformer-based solutions have been introduced to estimate 3D human pose from 2D keypoint sequence by considering body joints among all frames globally to learn spatio-temporal correlation. We observe that the motions of different joints differ significantly. However, the previous methods cannot efficiently model the solid inter-frame correspondence of each joint, leading to insufficient learning of spatial-temporal correlation. We propose MixSTE (Mixed Spatio-Temporal Encoder), which has a temporal transformer block to separately model the temporal motion of each joint and a spatial transformer block to learn inter-joint spatial correlation. These two blocks are utilized alternately to obtain better spatio-temporal feature encoding. In addition, the network output is extended from the central frame to entire frames of the input video, thereby improving the coherence between the input and output sequences. Extensive experiments are conducted on three benchmarks (Human3.6M, MPI-INF-3DHP, and HumanEva). The results show that our model outperforms the state-of-the-art approach by 10.9% P-MPJPE and 7.6% MPJPE. The code is available at https://github.com/JinluZhang1126/MixSTE.","url_abs":"https://arxiv.org/abs/2203.00859v4","url_pdf":"https://arxiv.org/pdf/2203.00859v4.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":"mixste-seq2seq-mixed-spatio-temporal-encoder","repo_url":"https://github.com/JinluZhang1126/MixSTE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"monocular-3d-human-pose-estimation","task_name":"Monocular 3D Human Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"spatial-transformer","method_name":"Spatial Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-human36m","task":"3D Human Pose Estimation","dataset":"Human3.6M","model":"MixSTE (HRNet, T=243)","rank_in_archive_order":17,"of":88,"metrics":{"Average MPJPE (mm)":"39.8","Multi-View or Monocular":"Monocular","Using 2D ground-truth joints":"No"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-human36m","task":"3D Human Pose Estimation","dataset":"Human3.6M","model":"MixSTE (CPN, T=243)","rank_in_archive_order":21,"of":88,"metrics":{"Average MPJPE (mm)":"40.9","Multi-View or Monocular":"Monocular","Using 2D ground-truth joints":"No"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-human36m","task":"3D Human Pose Estimation","dataset":"Human3.6M","model":"MixSTE (CPN, T=81)","rank_in_archive_order":24,"of":88,"metrics":{"Average MPJPE (mm)":"42.4","Multi-View or Monocular":"Monocular","Using 2D ground-truth joints":"No"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-humaneva-i","task":"3D Human Pose Estimation","dataset":"HumanEva-I","model":"MixSTE (T=43, FT)","rank_in_archive_order":7,"of":31,"metrics":{"Mean Reconstruction Error (mm)":"16.1"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-mpi-inf-3dhp","task":"3D Human Pose Estimation","dataset":"MPI-INF-3DHP","model":"MixSTE (T=27)","rank_in_archive_order":22,"of":108,"metrics":{"AUC":"66.5","MPJPE":"54.9","PCK":"94.4"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-mpi-inf-3dhp","task":"3D Human Pose Estimation","dataset":"MPI-INF-3DHP","model":"MixSTE (T=1)","rank_in_archive_order":24,"of":108,"metrics":{"AUC":"63.8","MPJPE":"57.9","PCK":"94.2"},"uses_additional_data":false},{"leaderboard":"/sota/classification-on-full-body-parkinsons","task":"Classification","dataset":"Full-body Parkinson’s disease dataset","model":"Mixste","rank_in_archive_order":7,"of":7,"metrics":{"F1-score (weighted)":"0.41"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-3d-human-pose-estimation-on-human3","task":"Monocular 3D Human Pose Estimation","dataset":"Human3.6M","model":"MixSTE (HRNet, T=243)","rank_in_archive_order":7,"of":52,"metrics":{"2D detector":"HRNet","Average MPJPE (mm)":"39.8","Frames Needed":"243","Need Ground Truth 2D Pose":"No","Use Video Sequence":"Yes"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.00859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.00859"}},"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/JinluZhang1126/MixSTE","reach":null}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"a54bb4e29b966532","entry":"Attention","repo":"JinluZhang1126/MixSTE","repo_kind":"official","path":"common/model_cross.py","file_url":"https://github.com/JinluZhang1126/MixSTE/blob/HEAD/common/model_cross.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a54bb4e29b966532"}},{"code_sha256_prefix":"361cb029385178dc","entry":"Block","repo":"JinluZhang1126/MixSTE","repo_kind":"official","path":"common/model_cross.py","file_url":"https://github.com/JinluZhang1126/MixSTE/blob/HEAD/common/model_cross.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"361cb029385178dc"}},{"code_sha256_prefix":"bff35ee778555423","entry":"MixSTE2","repo":"JinluZhang1126/MixSTE","repo_kind":"official","path":"common/model_cross.py","file_url":"https://github.com/JinluZhang1126/MixSTE/blob/HEAD/common/model_cross.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bff35ee778555423"}},{"code_sha256_prefix":"d1243176e8bb4111","entry":"Mlp","repo":"JinluZhang1126/MixSTE","repo_kind":"official","path":"common/model_cross.py","file_url":"https://github.com/JinluZhang1126/MixSTE/blob/HEAD/common/model_cross.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d1243176e8bb4111"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}