{"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/ctap-complementary-temporal-action-proposal","title":"CTAP: Complementary Temporal Action Proposal Generation","arxiv_id":"1807.04821","date":"2018-07-12","proceeding":"ECCV 2018 9","authors":["Jiyang Gao","Kan Chen","Ram Nevatia"],"abstract":"Temporal action proposal generation is an important task, akin to object\nproposals, temporal action proposals are intended to capture \"clips\" or\ntemporal intervals in videos that are likely to contain an action. Previous\nmethods can be divided to two groups: sliding window ranking and actionness\nscore grouping. Sliding windows uniformly cover all segments in videos, but the\ntemporal boundaries are imprecise; grouping based method may have more precise\nboundaries but it may omit some proposals when the quality of actionness score\nis low. Based on the complementary characteristics of these two methods, we\npropose a novel Complementary Temporal Action Proposal (CTAP) generator.\nSpecifically, we apply a Proposal-level Actionness Trustworthiness Estimator\n(PATE) on the sliding windows proposals to generate the probabilities\nindicating whether the actions can be correctly detected by actionness scores,\nthe windows with high scores are collected. The collected sliding windows and\nactionness proposals are then processed by a temporal convolutional neural\nnetwork for proposal ranking and boundary adjustment. CTAP outperforms\nstate-of-the-art methods on average recall (AR) by a large margin on THUMOS-14\nand ActivityNet 1.3 datasets. We further apply CTAP as a proposal generation\nmethod in an existing action detector, and show consistent significant\nimprovements.","url_abs":"http://arxiv.org/abs/1807.04821v2","url_pdf":"http://arxiv.org/pdf/1807.04821v2.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":"ctap-complementary-temporal-action-proposal","repo_url":"https://github.com/jiyanggao/CTAP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"temporal-action-proposal-generation","task_name":"Temporal Action Proposal Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/temporal-action-proposal-generation-on","task":"Temporal Action Proposal Generation","dataset":"ActivityNet-1.3","model":"CTAP","rank_in_archive_order":10,"of":11,"metrics":{"AR@100":"73.17","AUC (val)":"65.72"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.04821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.04821"}},"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/jiyanggao/CTAP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"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":"0ea2d9908d139760","entry":"compute_prob_dist","repo":"jiyanggao/CTAP","repo_kind":"official","path":"PATE/test_results/post_processing.py","file_url":"https://github.com/jiyanggao/CTAP/blob/HEAD/PATE/test_results/post_processing.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":"0ea2d9908d139760"}},{"code_sha256_prefix":"6b43f0d2273d2ffa","entry":"compute_prob_dist","repo":"jiyanggao/CTAP","repo_kind":"official","path":"TAR/test_results/post_processing.py","file_url":"https://github.com/jiyanggao/CTAP/blob/HEAD/TAR/test_results/post_processing.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":"6b43f0d2273d2ffa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}