{"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/memory-attention-networks-for-skeleton-based","title":"Memory Attention Networks for Skeleton-based Action Recognition","arxiv_id":"1804.08254","date":"2018-04-23","proceeding":null,"authors":["Chunyu Xie","Ce Li","Baochang Zhang","Chen Chen","Jungong Han","Changqing Zou","Jianzhuang Liu"],"abstract":"Skeleton-based action recognition task is entangled with complex\nspatio-temporal variations of skeleton joints, and remains challenging for\nRecurrent Neural Networks (RNNs). In this work, we propose a\ntemporal-then-spatial recalibration scheme to alleviate such complex\nvariations, resulting in an end-to-end Memory Attention Networks (MANs) which\nconsist of a Temporal Attention Recalibration Module (TARM) and a\nSpatio-Temporal Convolution Module (STCM). Specifically, the TARM is deployed\nin a residual learning module that employs a novel attention learning network\nto recalibrate the temporal attention of frames in a skeleton sequence. The\nSTCM treats the attention calibrated skeleton joint sequences as images and\nleverages the Convolution Neural Networks (CNNs) to further model the spatial\nand temporal information of skeleton data. These two modules (TARM and STCM)\nseamlessly form a single network architecture that can be trained in an\nend-to-end fashion. MANs significantly boost the performance of skeleton-based\naction recognition and achieve the best results on four challenging benchmark\ndatasets: NTU RGB+D, HDM05, SYSU-3D and UT-Kinect.","url_abs":"http://arxiv.org/abs/1804.08254v2","url_pdf":"http://arxiv.org/pdf/1804.08254v2.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":"memory-attention-networks-for-skeleton-based","repo_url":"https://github.com/memory-attention-networks/MANs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"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":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"MANs (DenseNet-161)","rank_in_archive_order":105,"of":135,"metrics":{"Accuracy (CS)":"82.67","Accuracy (CV)":"93.22"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.08254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.08254"}},"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/memory-attention-networks/MANs","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"23feefdb6bb6fb19","entry":"data_generator","repo":"memory-attention-networks/MANs","repo_kind":"listed","path":"train_MANs.py","file_url":"https://github.com/memory-attention-networks/MANs/blob/HEAD/train_MANs.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"23feefdb6bb6fb19"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}