{"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/multi-scale-spatial-temporal-graph","title":"Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition","arxiv_id":"2206.13028","date":"2022-06-27","proceeding":null,"authors":["Zhan Chen","Sicheng Li","Bing Yang","Qinghan Li","Hong Liu"],"abstract":"Graph convolutional networks have been widely used for skeleton-based action recognition due to their excellent modeling ability of non-Euclidean data. As the graph convolution is a local operation, it can only utilize the short-range joint dependencies and short-term trajectory but fails to directly model the distant joints relations and long-range temporal information that are vital to distinguishing various actions. To solve this problem, we present a multi-scale spatial graph convolution (MS-GC) module and a multi-scale temporal graph convolution (MT-GC) module to enrich the receptive field of the model in spatial and temporal dimensions. Concretely, the MS-GC and MT-GC modules decompose the corresponding local graph convolution into a set of sub-graph convolution, forming a hierarchical residual architecture. Without introducing additional parameters, the features will be processed with a series of sub-graph convolutions, and each node could complete multiple spatial and temporal aggregations with its neighborhoods. The final equivalent receptive field is accordingly enlarged, which is capable of capturing both short- and long-range dependencies in spatial and temporal domains. By coupling these two modules as a basic block, we further propose a multi-scale spatial temporal graph convolutional network (MST-GCN), which stacks multiple blocks to learn effective motion representations for action recognition. The proposed MST-GCN achieves remarkable performance on three challenging benchmark datasets, NTU RGB+D, NTU-120 RGB+D and Kinetics-Skeleton, for skeleton-based action recognition.","url_abs":"https://arxiv.org/abs/2206.13028v1","url_pdf":"https://arxiv.org/pdf/2206.13028v1.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":"multi-scale-spatial-temporal-graph","repo_url":"https://github.com/czhaneva/mst-gcn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-human-action-recognition","task_name":"3D Action Recognition"},{"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":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.13028","atlas_url":"https://app.syntology.ai/?focus=2206.13028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13028"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/czhaneva/mst-gcn","reach":null}],"summary":{"ran":19,"unverified":7},"by_repo_kind":{"official":{"samples":26,"ran":19,"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":"adf2726a0b3d58c7","entry":"Activations","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"adf2726a0b3d58c7"}},{"code_sha256_prefix":"b98c6db6e1002327","entry":"Basic_GCN_layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b98c6db6e1002327"}},{"code_sha256_prefix":"c796ca9dd59fa236","entry":"Basic_TCN_layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c796ca9dd59fa236"}},{"code_sha256_prefix":"48fe3fb98da81973","entry":"Channel_Att","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48fe3fb98da81973"}},{"code_sha256_prefix":"dbee7b6fa4f1ce15","entry":"Frame_Att","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dbee7b6fa4f1ce15"}},{"code_sha256_prefix":"30a4e5eac52b5024","entry":"HardSwish","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30a4e5eac52b5024"}},{"code_sha256_prefix":"c1df0458dc14ccc0","entry":"Joint_Att","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.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":"c1df0458dc14ccc0"}},{"code_sha256_prefix":"75741374fad8b7e5","entry":"MS_GCN_layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"75741374fad8b7e5"}},{"code_sha256_prefix":"bfbe1f03029f7ad2","entry":"MS_TCN_layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bfbe1f03029f7ad2"}},{"code_sha256_prefix":"d2414716f801d45c","entry":"MS_Temporal_Bottleneck_Layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d2414716f801d45c"}},{"code_sha256_prefix":"c5666841a031b400","entry":"Part_Att","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.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":"c5666841a031b400"}},{"code_sha256_prefix":"c00428bb1087d8c7","entry":"ST_Joint_Att","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c00428bb1087d8c7"}},{"code_sha256_prefix":"5af17e125ae250fa","entry":"SpatialGraphCov","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5af17e125ae250fa"}},{"code_sha256_prefix":"5080808855c5f5ab","entry":"Spatial_Bottleneck_Layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.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":"5080808855c5f5ab"}},{"code_sha256_prefix":"1287702d2c4a9cd2","entry":"Spatial_Sep_Layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.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":"1287702d2c4a9cd2"}},{"code_sha256_prefix":"f96addd2fbf1a9ff","entry":"Swish","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f96addd2fbf1a9ff"}},{"code_sha256_prefix":"50d877700bf66c6e","entry":"Temporal_Bottleneck_Layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50d877700bf66c6e"}},{"code_sha256_prefix":"ec58271211aef2f7","entry":"Temporal_Sep_Layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec58271211aef2f7"}},{"code_sha256_prefix":"3ab2a8a648baad65","entry":"Zero_Layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ab2a8a648baad65"}},{"code_sha256_prefix":"702b399cba4cde41","entry":"Attention_Layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.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":"702b399cba4cde41"}},{"code_sha256_prefix":"2793d688802c51f8","entry":"Basic_Layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.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":"2793d688802c51f8"}},{"code_sha256_prefix":"2a8639e74ce27e44","entry":"MST_GCN_block","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.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":"2a8639e74ce27e44"}},{"code_sha256_prefix":"45f3e4bb934a1064","entry":"MS_Spatial_Bottleneck_Layer","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.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":"45f3e4bb934a1064"}},{"code_sha256_prefix":"6734a97abcc87eb8","entry":"Model","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.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":"6734a97abcc87eb8"}},{"code_sha256_prefix":"20ef600dd57166cb","entry":"STC_Joint_Att","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.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":"20ef600dd57166cb"}},{"code_sha256_prefix":"a80e2c1116a03a17","entry":"conv_branch_init","repo":"czhaneva/mst-gcn","repo_kind":"official","path":"model/AEMST_GCN.py","file_url":"https://github.com/czhaneva/mst-gcn/blob/HEAD/model/AEMST_GCN.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":"a80e2c1116a03a17"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}