{"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/single-shot-temporal-action-detection","title":"Single Shot Temporal Action Detection","arxiv_id":"1710.06236","date":"2017-10-17","proceeding":null,"authors":["Tianwei Lin","Xu Zhao","Zheng Shou"],"abstract":"Temporal action detection is a very important yet challenging problem, since\nvideos in real applications are usually long, untrimmed and contain multiple\naction instances. This problem requires not only recognizing action categories\nbut also detecting start time and end time of each action instance. Many\nstate-of-the-art methods adopt the \"detection by classification\" framework:\nfirst do proposal, and then classify proposals. The main drawback of this\nframework is that the boundaries of action instance proposals have been fixed\nduring the classification step. To address this issue, we propose a novel\nSingle Shot Action Detector (SSAD) network based on 1D temporal convolutional\nlayers to skip the proposal generation step via directly detecting action\ninstances in untrimmed video. On pursuit of designing a particular SSAD network\nthat can work effectively for temporal action detection, we empirically search\nfor the best network architecture of SSAD due to lacking existing models that\ncan be directly adopted. Moreover, we investigate into input feature types and\nfusion strategies to further improve detection accuracy. We conduct extensive\nexperiments on two challenging datasets: THUMOS 2014 and MEXaction2. When\nsetting Intersection-over-Union threshold to 0.5 during evaluation, SSAD\nsignificantly outperforms other state-of-the-art systems by increasing mAP from\n19.0% to 24.6% on THUMOS 2014 and from 7.4% to 11.0% on MEXaction2.","url_abs":"http://arxiv.org/abs/1710.06236v1","url_pdf":"http://arxiv.org/pdf/1710.06236v1.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":"single-shot-temporal-action-detection","repo_url":"https://github.com/blowing-wind/SSAD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"single-shot-temporal-action-detection","repo_url":"https://github.com/hypjudy/Decouple-SSAD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1710.06236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.06236"}},"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/blowing-wind/SSAD","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hypjudy/Decouple-SSAD","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"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":"2b03cca413bf1fb0","entry":"test_operation","repo":"hypjudy/Decouple-SSAD","repo_kind":"listed","path":"decouple_ssad.py","file_url":"https://github.com/hypjudy/Decouple-SSAD/blob/HEAD/decouple_ssad.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":"2b03cca413bf1fb0"}},{"code_sha256_prefix":"1e8c188cdb611c6c","entry":"test_operation","repo":"hypjudy/Decouple-SSAD","repo_kind":"listed","path":"main_stream.py","file_url":"https://github.com/hypjudy/Decouple-SSAD/blob/HEAD/main_stream.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":"1e8c188cdb611c6c"}},{"code_sha256_prefix":"1ca99ca1146596e0","entry":"train_operation","repo":"hypjudy/Decouple-SSAD","repo_kind":"listed","path":"decouple_ssad.py","file_url":"https://github.com/hypjudy/Decouple-SSAD/blob/HEAD/decouple_ssad.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":"1ca99ca1146596e0"}},{"code_sha256_prefix":"d2a08950061d6d08","entry":"train_operation","repo":"hypjudy/Decouple-SSAD","repo_kind":"listed","path":"main_stream.py","file_url":"https://github.com/hypjudy/Decouple-SSAD/blob/HEAD/main_stream.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":"d2a08950061d6d08"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}