{"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/structural-rnn-deep-learning-on-spatio","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","arxiv_id":"1511.05298","date":"2015-11-17","proceeding":"CVPR 2016 6","authors":["Ashesh Jain","Amir R. Zamir","Silvio Savarese","Ashutosh Saxena"],"abstract":"Deep Recurrent Neural Network architectures, though remarkably capable at\nmodeling sequences, lack an intuitive high-level spatio-temporal structure.\nThat is while many problems in computer vision inherently have an underlying\nhigh-level structure and can benefit from it. Spatio-temporal graphs are a\npopular tool for imposing such high-level intuitions in the formulation of real\nworld problems. In this paper, we propose an approach for combining the power\nof high-level spatio-temporal graphs and sequence learning success of Recurrent\nNeural Networks~(RNNs). We develop a scalable method for casting an arbitrary\nspatio-temporal graph as a rich RNN mixture that is feedforward, fully\ndifferentiable, and jointly trainable. The proposed method is generic and\nprincipled as it can be used for transforming any spatio-temporal graph through\nemploying a certain set of well defined steps. The evaluations of the proposed\napproach on a diverse set of problems, ranging from modeling human motion to\nobject interactions, shows improvement over the state-of-the-art with a large\nmargin. We expect this method to empower new approaches to problem formulation\nthrough high-level spatio-temporal graphs and Recurrent Neural Networks.","url_abs":"http://arxiv.org/abs/1511.05298v3","url_pdf":"http://arxiv.org/pdf/1511.05298v3.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":"structural-rnn-deep-learning-on-spatio","repo_url":"https://github.com/asheshjain399/RNNexp","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"structural-rnn-deep-learning-on-spatio","repo_url":"https://github.com/zhaolongkzz/human_motion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"human-pose-forecasting","task_name":"Human Pose Forecasting"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-pose-forecasting-on-human36m","task":"Human Pose Forecasting","dataset":"Human3.6M","model":"SRNN","rank_in_archive_order":20,"of":33,"metrics":{"MAR, walking, 1,000ms":"2.13","MAR, walking, 400ms":"1.30"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-cad-120","task":"Skeleton Based Action Recognition","dataset":"CAD-120","model":"S-RNN (5-shot)","rank_in_archive_order":4,"of":8,"metrics":{"Accuracy":"85.4%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1511.05298","atlas_url":"https://app.syntology.ai/?focus=1511.05298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.05298"}},"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/asheshjain399/RNNexp","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhaolongkzz/human_motion","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"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":"e767841ab10a369a","entry":"readFile","repo":"zhaolongkzz/human_motion","repo_kind":"listed","path":"scripts/Animation/motionAnimation.py","file_url":"https://github.com/zhaolongkzz/human_motion/blob/HEAD/scripts/Animation/motionAnimation.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":"e767841ab10a369a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}