{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/constructing-stronger-and-faster-baselines","title":"Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition","arxiv_id":"2106.15125","date":"2021-06-29","proceeding":null,"authors":["Yi-Fan Song","Zhang Zhang","Caifeng Shan","Liang Wang"],"abstract":"One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the recent State-Of-The-Art (SOTA) models for this task tends to be exceedingly sophisticated and over-parameterized. The low efficiency in model training and inference has increased the validation costs of model architectures in large-scale datasets. To address the above issue, recent advanced separable convolutional layers are embedded into an early fused Multiple Input Branches (MIB) network, constructing an efficient Graph Convolutional Network (GCN) baseline for skeleton-based action recognition. In addition, based on such the baseline, we design a compound scaling strategy to expand the model's width and depth synchronously, and eventually obtain a family of efficient GCN baselines with high accuracies and small amounts of trainable parameters, termed EfficientGCN-Bx, where \"x\" denotes the scaling coefficient. On two large-scale datasets, i.e., NTU RGB+D 60 and 120, the proposed EfficientGCN-B4 baseline outperforms other SOTA methods, e.g., achieving 91.7% accuracy on the cross-subject benchmark of NTU 60 dataset, while being 3.15x smaller and 3.21x faster than MS-G3D, which is one of the best SOTA methods. The source code in PyTorch version and the pretrained models are available at https://github.com/yfsong0709/EfficientGCNv1.","url_abs":"https://arxiv.org/abs/2106.15125v2","url_pdf":"https://arxiv.org/pdf/2106.15125v2.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":"constructing-stronger-and-faster-baselines","repo_url":"https://github.com/yfsong0709/EfficientGCNv1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"constructing-stronger-and-faster-baselines","repo_url":"https://github.com/yfsong0709/ResGCNv1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"constructing-stronger-and-faster-baselines","repo_url":"https://github.com/Wuxiao85/paddle_EfficientGCNv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"constructing-stronger-and-faster-baselines","repo_url":"https://github.com/small-whirlwind/EfficientGCN_paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok"}}],"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":"gcn","method_name":"GCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"EfficientGCN-B4","rank_in_archive_order":34,"of":135,"metrics":{"Accuracy (CS)":"92.1","Accuracy (CV)":"96.1"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"EfficientGCN-B2","rank_in_archive_order":45,"of":135,"metrics":{"Accuracy (CS)":"90.9","Accuracy (CV)":"95.5"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"EfficientGCN-B0","rank_in_archive_order":57,"of":135,"metrics":{"Accuracy (CS)":"89.9","Accuracy (CV)":"94.7"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd-1","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D 120","model":"EfficientGCN-B4","rank_in_archive_order":27,"of":83,"metrics":{"Accuracy (Cross-Setup)":"89.1","Accuracy (Cross-Subject)":"88.7"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd-1","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D 120","model":"EfficientGCN-B2","rank_in_archive_order":31,"of":83,"metrics":{"Accuracy (Cross-Setup)":"88.0","Accuracy (Cross-Subject)":"87.9"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd-1","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D 120","model":"EfficientGCN-B0","rank_in_archive_order":43,"of":83,"metrics":{"Accuracy (Cross-Setup)":"84.3","Accuracy (Cross-Subject)":"85.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.15125","atlas_url":"https://app.syntology.ai/?focus=2106.15125","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2106.15125"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2106.15125\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2106.15125"},"call":"get_concepts_for_paper(arxiv_id=\"2106.15125\")"}],"by_repo":[{"repo":"yfsong0709/EfficientGCNv1","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yfsong0709/ResGCNv1","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Wuxiao85/paddle_EfficientGCNv","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"small-whirlwind/EfficientGCN_paddle","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c49389d8f563e996446d6134c87b16a03bbc00115037ee947340831f38ba6362","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}