{"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/part-aware-unified-representation-of-language-1","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","arxiv_id":"2406.13327","date":"2024-06-19","proceeding":"CVPR 2024 1","authors":["Anqi Zhu","Qiuhong Ke","Mingming Gong","James Bailey"],"abstract":"While remarkable progress has been made on supervised skeleton-based action recognition, the challenge of zero-shot recognition remains relatively unexplored. In this paper, we argue that relying solely on aligning label-level semantics and global skeleton features is insufficient to effectively transfer locally consistent visual knowledge from seen to unseen classes. To address this limitation, we introduce Part-aware Unified Representation between Language and Skeleton (PURLS) to explore visual-semantic alignment at both local and global scales. PURLS introduces a new prompting module and a novel partitioning module to generate aligned textual and visual representations across different levels. The former leverages a pre-trained GPT-3 to infer refined descriptions of the global and local (body-part-based and temporal-interval-based) movements from the original action labels. The latter employs an adaptive sampling strategy to group visual features from all body joint movements that are semantically relevant to a given description. Our approach is evaluated on various skeleton/language backbones and three large-scale datasets, i.e., NTU-RGB+D 60, NTU-RGB+D 120, and a newly curated dataset Kinetics-skeleton 200. The results showcase the universality and superior performance of PURLS, surpassing prior skeleton-based solutions and standard baselines from other domains. The source codes can be accessed at https://github.com/azzh1/PURLS.","url_abs":"https://arxiv.org/abs/2406.13327v1","url_pdf":"https://arxiv.org/pdf/2406.13327v1.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":"part-aware-unified-representation-of-language-1","repo_url":"https://github.com/azzh1/purls","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"},{"task_slug":"zero-shot-skeletal-action-recognition","task_name":"Zero Shot Skeletal Action Recognition"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-skeletal-action-recognition-on-ntu","task":"Zero Shot Skeletal Action Recognition","dataset":"NTU RGB+D","model":"PURLS","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy (12 unseen classes)":"40.99","Accuracy (5 unseen classes)":"79.23"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-skeletal-action-recognition-on-ntu-1","task":"Zero Shot Skeletal Action Recognition","dataset":"NTU RGB+D 120","model":"PURLS","rank_in_archive_order":3,"of":9,"metrics":{"Accuracy (10 unseen classes)":"71.95","Accuracy (24 unseen classes)":"52.01"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.13327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13327"}},"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":"deterministic:regex_extraction","url":"https://github.com/azzh1/PURLS","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran":2,"ran_violates":1},"by_repo_kind":{"official":{"samples":3,"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":"0aa492f73682c30c","entry":"accuracy","repo":"azzh1/PURLS","repo_kind":"official","path":"model/utils/losses.py","file_url":"https://github.com/azzh1/PURLS/blob/HEAD/model/utils/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0aa492f73682c30c"}},{"code_sha256_prefix":"29ad04a5f041d9d1","entry":"contrastive_loss","repo":"azzh1/PURLS","repo_kind":"official","path":"model/utils/losses.py","file_url":"https://github.com/azzh1/PURLS/blob/HEAD/model/utils/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"29ad04a5f041d9d1"}},{"code_sha256_prefix":"f017532fc389cbfe","entry":"str2bool","repo":"azzh1/PURLS","repo_kind":"official","path":"utils.py","file_url":"https://github.com/azzh1/PURLS/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f017532fc389cbfe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}