{"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/spatio-temporal-tuples-transformer-for","title":"Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition","arxiv_id":"2201.02849","date":"2022-01-08","proceeding":null,"authors":["Helei Qiu","Biao Hou","Bo Ren","Xiaohua Zhang"],"abstract":"Capturing the dependencies between joints is critical in skeleton-based action recognition task. Transformer shows great potential to model the correlation of important joints. However, the existing Transformer-based methods cannot capture the correlation of different joints between frames, which the correlation is very useful since different body parts (such as the arms and legs in \"long jump\") between adjacent frames move together. Focus on this problem, A novel spatio-temporal tuples Transformer (STTFormer) method is proposed. The skeleton sequence is divided into several parts, and several consecutive frames contained in each part are encoded. And then a spatio-temporal tuples self-attention module is proposed to capture the relationship of different joints in consecutive frames. In addition, a feature aggregation module is introduced between non-adjacent frames to enhance the ability to distinguish similar actions. Compared with the state-of-the-art methods, our method achieves better performance on two large-scale datasets.","url_abs":"https://arxiv.org/abs/2201.02849v1","url_pdf":"https://arxiv.org/pdf/2201.02849v1.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":"spatio-temporal-tuples-transformer-for","repo_url":"https://github.com/heleiqiu/sttformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"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":"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2201.02849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.02849"}},"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/heleiqiu/sttformer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":2,"unverified":8},"by_repo_kind":{"official":{"samples":11,"ran":3,"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":"d63c7bd0fe3e1881","entry":"denoising_by_length","repo":"heleiqiu/sttformer","repo_kind":"official","path":"gendata/ntu/get_raw_denoised_data.py","file_url":"https://github.com/heleiqiu/sttformer/blob/HEAD/gendata/ntu/get_raw_denoised_data.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":"d63c7bd0fe3e1881"}},{"code_sha256_prefix":"8b14974e8aa7320f","entry":"downsample","repo":"heleiqiu/sttformer","repo_kind":"official","path":"feeders/tools.py","file_url":"https://github.com/heleiqiu/sttformer/blob/HEAD/feeders/tools.py","link_basis":"harvester_set","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":"8b14974e8aa7320f"}},{"code_sha256_prefix":"37939bae213ecfd4","entry":"valid_crop_resize","repo":"heleiqiu/sttformer","repo_kind":"official","path":"feeders/tools.py","file_url":"https://github.com/heleiqiu/sttformer/blob/HEAD/feeders/tools.py","link_basis":"harvester_set","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":"37939bae213ecfd4"}},{"code_sha256_prefix":"d3358705b52bccbe","entry":"denoising_by_spread","repo":"heleiqiu/sttformer","repo_kind":"official","path":"gendata/ntu/get_raw_denoised_data.py","file_url":"https://github.com/heleiqiu/sttformer/blob/HEAD/gendata/ntu/get_raw_denoised_data.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":"d3358705b52bccbe"}},{"code_sha256_prefix":"5ccb28010b540cbf","entry":"frame_translation","repo":"heleiqiu/sttformer","repo_kind":"official","path":"gendata/ntu/seq_transformation.py","file_url":"https://github.com/heleiqiu/sttformer/blob/HEAD/gendata/ntu/seq_transformation.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":"5ccb28010b540cbf"}},{"code_sha256_prefix":"5b01cb771784850f","entry":"get_raw_bodies_data","repo":"heleiqiu/sttformer","repo_kind":"official","path":"gendata/ntu/get_raw_skes_data.py","file_url":"https://github.com/heleiqiu/sttformer/blob/HEAD/gendata/ntu/get_raw_skes_data.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":"5b01cb771784850f"}},{"code_sha256_prefix":"a77a4bd849c26036","entry":"get_raw_bodies_data","repo":"heleiqiu/sttformer","repo_kind":"official","path":"gendata/ntu120/get_raw_skes_data.py","file_url":"https://github.com/heleiqiu/sttformer/blob/HEAD/gendata/ntu120/get_raw_skes_data.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":"a77a4bd849c26036"}},{"code_sha256_prefix":"785086bb1a2ced64","entry":"get_valid_frames_by_spread","repo":"heleiqiu/sttformer","repo_kind":"official","path":"gendata/ntu/get_raw_denoised_data.py","file_url":"https://github.com/heleiqiu/sttformer/blob/HEAD/gendata/ntu/get_raw_denoised_data.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":"785086bb1a2ced64"}},{"code_sha256_prefix":"1cc3adc4a2068ead","entry":"remove_nan_frames","repo":"heleiqiu/sttformer","repo_kind":"official","path":"gendata/ntu/seq_transformation.py","file_url":"https://github.com/heleiqiu/sttformer/blob/HEAD/gendata/ntu/seq_transformation.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":"1cc3adc4a2068ead"}},{"code_sha256_prefix":"477b711e99221772","entry":"seq_translation","repo":"heleiqiu/sttformer","repo_kind":"official","path":"gendata/ntu/seq_transformation.py","file_url":"https://github.com/heleiqiu/sttformer/blob/HEAD/gendata/ntu/seq_transformation.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":"477b711e99221772"}},{"code_sha256_prefix":"2f7f389f0584c97e","entry":"temporal_slice","repo":"heleiqiu/sttformer","repo_kind":"official","path":"feeders/tools.py","file_url":"https://github.com/heleiqiu/sttformer/blob/HEAD/feeders/tools.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":"2f7f389f0584c97e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}