{"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/sr-lstm-state-refinement-for-lstm-towards","title":"SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction","arxiv_id":"1903.02793","date":"2019-03-07","proceeding":"CVPR 2019 6","authors":["Pu Zhang","Wanli Ouyang","Pengfei Zhang","Jianru Xue","Nanning Zheng"],"abstract":"In crowd scenarios, reliable trajectory prediction of pedestrians requires\ninsightful understanding of their social behaviors. These behaviors have been\nwell investigated by plenty of studies, while it is hard to be fully expressed\nby hand-craft rules. Recent studies based on LSTM networks have shown great\nability to learn social behaviors. However, many of these methods rely on\nprevious neighboring hidden states but ignore the important current intention\nof the neighbors. In order to address this issue, we propose a data-driven\nstate refinement module for LSTM network (SR-LSTM), which activates the\nutilization of the current intention of neighbors, and jointly and iteratively\nrefines the current states of all participants in the crowd through a message\npassing mechanism. To effectively extract the social effect of neighbors, we\nfurther introduce a social-aware information selection mechanism consisting of\nan element-wise motion gate and a pedestrian-wise attention to select useful\nmessage from neighboring pedestrians. Experimental results on two public\ndatasets, i.e. ETH and UCY, demonstrate the effectiveness of our proposed\nSR-LSTM and we achieves state-of-the-art results.","url_abs":"http://arxiv.org/abs/1903.02793v1","url_pdf":"http://arxiv.org/pdf/1903.02793v1.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":"sr-lstm-state-refinement-for-lstm-towards","repo_url":"https://github.com/zhangpur/SR-LSTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"pedestrian-trajectory-prediction","task_name":"Pedestrian Trajectory Prediction"},{"task_slug":"trajectory-prediction","task_name":"Trajectory Prediction"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.02793","atlas_url":"https://app.syntology.ai/?focus=1903.02793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.02793"}},"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/zhangpur/SR-LSTM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"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":"9414a91b8e91375a","entry":"L2forTest_nl","repo":"zhangpur/SR-LSTM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/zhangpur/SR-LSTM/blob/HEAD/utils.py","link_basis":"harvester_set","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":"9414a91b8e91375a"}},{"code_sha256_prefix":"78bed37adf746764","entry":"getLossMask","repo":"zhangpur/SR-LSTM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/zhangpur/SR-LSTM/blob/HEAD/utils.py","link_basis":"harvester_set","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":"78bed37adf746764"}},{"code_sha256_prefix":"3f5f02c4eea03dfc","entry":"L2forTest","repo":"zhangpur/SR-LSTM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/zhangpur/SR-LSTM/blob/HEAD/utils.py","link_basis":"harvester_set","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":"3f5f02c4eea03dfc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}