{"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/temporal-action-detection-with-structured","title":"Temporal Action Detection with Structured Segment Networks","arxiv_id":"1704.06228","date":"2017-04-20","proceeding":"ICCV 2017 10","authors":["Yue Zhao","Yuanjun Xiong","Li-Min Wang","Zhirong Wu","Xiaoou Tang","Dahua Lin"],"abstract":"Detecting actions in untrimmed videos is an important yet challenging task.\nIn this paper, we present the structured segment network (SSN), a novel\nframework which models the temporal structure of each action instance via a\nstructured temporal pyramid. On top of the pyramid, we further introduce a\ndecomposed discriminative model comprising two classifiers, respectively for\nclassifying actions and determining completeness. This allows the framework to\neffectively distinguish positive proposals from background or incomplete ones,\nthus leading to both accurate recognition and localization. These components\nare integrated into a unified network that can be efficiently trained in an\nend-to-end fashion. Additionally, a simple yet effective temporal action\nproposal scheme, dubbed temporal actionness grouping (TAG) is devised to\ngenerate high quality action proposals. On two challenging benchmarks, THUMOS14\nand ActivityNet, our method remarkably outperforms previous state-of-the-art\nmethods, demonstrating superior accuracy and strong adaptivity in handling\nactions with various temporal structures.","url_abs":"http://arxiv.org/abs/1704.06228v2","url_pdf":"http://arxiv.org/pdf/1704.06228v2.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":"temporal-action-detection-with-structured","repo_url":"https://github.com/open-mmlab/mmaction","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"temporal-action-detection-with-structured","repo_url":"https://github.com/Lechatelia/SSN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"temporal-action-detection-with-structured","repo_url":"https://github.com/happygds/two_level","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"temporal-action-detection-with-structured","repo_url":"https://github.com/yjxiong/action-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"temporal-action-detection-with-structured","repo_url":"https://github.com/Mind23-2/MindCode-87","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"temporal-action-detection-with-structured","repo_url":"https://github.com/open-mmlab/mmaction2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-in-videos-on-thumos14","task":"Action Recognition","dataset":"THUMOS’14","model":"SSN","rank_in_archive_order":6,"of":10,"metrics":{"mAP@0.1":"66.0","mAP@0.2":"59.4","mAP@0.3":"51.9","mAP@0.4":"41.0","mAP@0.5":"29.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.06228","atlas_url":"https://app.syntology.ai/?focus=1704.06228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.06228"}},"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/yjxiong/action-detection","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Lechatelia/SSN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/happygds/two_level","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmaction","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-87","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmaction2","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"40f06c92da7aaa45","entry":"convert_categorical","repo":"happygds/two_level","repo_kind":"listed","path":"binary_train.py","file_url":"https://github.com/happygds/two_level/blob/HEAD/binary_train.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"40f06c92da7aaa45"}},{"code_sha256_prefix":"c3bb5aeb6a0f7d6e","entry":"accuracy","repo":"happygds/two_level","repo_kind":"listed","path":"binary_train.py","file_url":"https://github.com/happygds/two_level/blob/HEAD/binary_train.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c3bb5aeb6a0f7d6e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}