{"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/identifying-visible-actions-in-lifestyle","title":"Identifying Visible Actions in Lifestyle Vlogs","arxiv_id":"1906.04236","date":"2019-06-10","proceeding":"ACL 2019 7","authors":["Oana Ignat","Laura Burdick","Jia Deng","Rada Mihalcea"],"abstract":"We consider the task of identifying human actions visible in online videos. We focus on the widely spread genre of lifestyle vlogs, which consist of videos of people performing actions while verbally describing them. Our goal is to identify if actions mentioned in the speech description of a video are visually present. We construct a dataset with crowdsourced manual annotations of visible actions, and introduce a multimodal algorithm that leverages information derived from visual and linguistic clues to automatically infer which actions are visible in a video. We demonstrate that our multimodal algorithm outperforms algorithms based only on one modality at a time.","url_abs":"https://arxiv.org/abs/1906.04236v1","url_pdf":"https://arxiv.org/pdf/1906.04236v1.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":"identifying-visible-actions-in-lifestyle","repo_url":"https://github.com/MichiganNLP/vlog_action_recognition","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"}],"methods":[],"datasets_introduced":[{"slug":"vlogs","name":"IfAct","full_name":"Identifying Human Actions Visible in Online Vlogs"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.04236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04236"}},"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/MichiganNLP/vlog_action_recognition","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"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":"add9845de22feb70","entry":"agreement_total","repo":"MichiganNLP/vlog_action_recognition","repo_kind":"official","path":"amt/compute_agreement.py","file_url":"https://github.com/MichiganNLP/vlog_action_recognition/blob/HEAD/amt/compute_agreement.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":"add9845de22feb70"}},{"code_sha256_prefix":"f634d81b68c16596","entry":"build_dense_model","repo":"MichiganNLP/vlog_action_recognition","repo_kind":"official","path":"classify/main_model.py","file_url":"https://github.com/MichiganNLP/vlog_action_recognition/blob/HEAD/classify/main_model.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":"f634d81b68c16596"}},{"code_sha256_prefix":"3015fc5f426cd562","entry":"compare_with_GT","repo":"MichiganNLP/vlog_action_recognition","repo_kind":"official","path":"amt/detect_spam.py","file_url":"https://github.com/MichiganNLP/vlog_action_recognition/blob/HEAD/amt/detect_spam.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":"3015fc5f426cd562"}},{"code_sha256_prefix":"633a98e67cf8f4f7","entry":"compute_agreement","repo":"MichiganNLP/vlog_action_recognition","repo_kind":"official","path":"amt/read_csv_results.py","file_url":"https://github.com/MichiganNLP/vlog_action_recognition/blob/HEAD/amt/read_csv_results.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":"633a98e67cf8f4f7"}},{"code_sha256_prefix":"ef2f2d82063b646a","entry":"compute_ratings","repo":"MichiganNLP/vlog_action_recognition","repo_kind":"official","path":"amt/compute_agreement.py","file_url":"https://github.com/MichiganNLP/vlog_action_recognition/blob/HEAD/amt/compute_agreement.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":"ef2f2d82063b646a"}},{"code_sha256_prefix":"1a9424d013afe82b","entry":"create_model_concat","repo":"MichiganNLP/vlog_action_recognition","repo_kind":"official","path":"classify/main_model.py","file_url":"https://github.com/MichiganNLP/vlog_action_recognition/blob/HEAD/classify/main_model.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":"1a9424d013afe82b"}},{"code_sha256_prefix":"69de3cbbda85c060","entry":"fleiss_kappa","repo":"MichiganNLP/vlog_action_recognition","repo_kind":"official","path":"amt/compute_agreement.py","file_url":"https://github.com/MichiganNLP/vlog_action_recognition/blob/HEAD/amt/compute_agreement.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":"69de3cbbda85c060"}},{"code_sha256_prefix":"8538771bd1dd8a7d","entry":"getLength","repo":"MichiganNLP/vlog_action_recognition","repo_kind":"official","path":"amt/read_csv_results.py","file_url":"https://github.com/MichiganNLP/vlog_action_recognition/blob/HEAD/amt/read_csv_results.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":"8538771bd1dd8a7d"}},{"code_sha256_prefix":"8aec1885fd917bd9","entry":"get_compromised_hits","repo":"MichiganNLP/vlog_action_recognition","repo_kind":"official","path":"amt/detect_spam.py","file_url":"https://github.com/MichiganNLP/vlog_action_recognition/blob/HEAD/amt/detect_spam.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":"8aec1885fd917bd9"}},{"code_sha256_prefix":"dad39214a8dcfe23","entry":"read_results_from_AMT","repo":"MichiganNLP/vlog_action_recognition","repo_kind":"official","path":"amt/read_csv_results.py","file_url":"https://github.com/MichiganNLP/vlog_action_recognition/blob/HEAD/amt/read_csv_results.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":"dad39214a8dcfe23"}},{"code_sha256_prefix":"872bab173b6ed8cc","entry":"read_results_from_amt","repo":"MichiganNLP/vlog_action_recognition","repo_kind":"official","path":"amt/read_AMT.py","file_url":"https://github.com/MichiganNLP/vlog_action_recognition/blob/HEAD/amt/read_AMT.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":"872bab173b6ed8cc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}