{"id":"https://openalex.org/W4387969909","doi":"https://doi.org/10.1145/3581783.3611945","title":"Foreground/Background-Masked Interaction Learning for Spatio-temporal Action Detection","display_name":"Foreground/Background-Masked Interaction Learning for Spatio-temporal Action Detection","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969909","doi":"https://doi.org/10.1145/3581783.3611945"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611945","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611945","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611945","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611945","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103104903","display_name":"Keke Chen","orcid":"https://orcid.org/0009-0006-2985-8918"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keke Chen","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-2985-8918","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040437528","display_name":"Xiangbo Shu","orcid":"https://orcid.org/0000-0003-4902-4663"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangbo Shu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4902-4663","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084688255","display_name":"Guo-Sen Xie","orcid":"https://orcid.org/0000-0002-5487-9845"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo-Sen Xie","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5487-9845","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716371","display_name":"Rui Yan","orcid":"https://orcid.org/0000-0002-0694-9458"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yan","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0694-9458","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035112538","display_name":"Jinhui Tang","orcid":"https://orcid.org/0000-0001-9008-222X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Tang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9008-222X","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2381","last_page":"2390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7997469902038574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6254537105560303},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5763144493103027},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5729292631149292},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5491958260536194},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5069044232368469},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4978370666503906},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4643898904323578},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4250989258289337},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.329541951417923},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07357251644134521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997469902038574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6254537105560303},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5763144493103027},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5729292631149292},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5491958260536194},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5069044232368469},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4978370666503906},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4643898904323578},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4250989258289337},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.329541951417923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07357251644134521},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611945","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611945","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611945","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3611945","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611945","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611945","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G2268872017","display_name":null,"funder_award_id":"2023M731596","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3938807848","display_name":null,"funder_award_id":"62276134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5512729199","display_name":null,"funder_award_id":"62222207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5558408212","display_name":"\u9762\u5411\u590d\u6742\u573a\u666f\u7684\u7fa4\u4f53\u6d3b\u52a8\u591a\u7c92\u5ea6\u89e3\u6790\u7814\u7a76","funder_award_id":"62072245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5950360714","display_name":null,"funder_award_id":"BK20211520","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G6329772822","display_name":null,"funder_award_id":"61925204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6714998264","display_name":null,"funder_award_id":"62222207,61925204,62072245,62276134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8273014382","display_name":null,"funder_award_id":"2018AAA0102001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969909.pdf","grobid_xml":"https://content.openalex.org/works/W4387969909.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W410625161","https://openalex.org/W569478347","https://openalex.org/W1861492603","https://openalex.org/W1923332106","https://openalex.org/W1983364832","https://openalex.org/W2097342496","https://openalex.org/W2117539524","https://openalex.org/W2549139847","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2611596598","https://openalex.org/W2618799552","https://openalex.org/W2770804203","https://openalex.org/W2788945907","https://openalex.org/W2806331055","https://openalex.org/W2883275382","https://openalex.org/W2941818575","https://openalex.org/W2955874753","https://openalex.org/W2962688385","https://openalex.org/W2962722947","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963524571","https://openalex.org/W2963529931","https://openalex.org/W2963563276","https://openalex.org/W2963616706","https://openalex.org/W2963699792","https://openalex.org/W2964087927","https://openalex.org/W2964207322","https://openalex.org/W2974686944","https://openalex.org/W2976669726","https://openalex.org/W2990503944","https://openalex.org/W3014545861","https://openalex.org/W3028797339","https://openalex.org/W3034257141","https://openalex.org/W3034572008","https://openalex.org/W3034679267","https://openalex.org/W3093195700","https://openalex.org/W3096609285","https://openalex.org/W3096719817","https://openalex.org/W3096824106","https://openalex.org/W3108226879","https://openalex.org/W3109142545","https://openalex.org/W3109173645","https://openalex.org/W3111172959","https://openalex.org/W3121052081","https://openalex.org/W3173407577","https://openalex.org/W3197341423","https://openalex.org/W3203086442","https://openalex.org/W3204116406","https://openalex.org/W4214614183","https://openalex.org/W4289550868","https://openalex.org/W4304086659","https://openalex.org/W4312509322","https://openalex.org/W4312815172","https://openalex.org/W4313169234","https://openalex.org/W4360993849","https://openalex.org/W6600310816"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W1976205134","https://openalex.org/W2381570729","https://openalex.org/W4248336175","https://openalex.org/W2905271011","https://openalex.org/W3164948662","https://openalex.org/W4289536128","https://openalex.org/W3153597579","https://openalex.org/W1872833176"],"abstract_inverted_index":{"Spatio-temporal":[0],"Action":[1],"Detection":[2],"(SAD)":[3],"aims":[4],"to":[5,57,70,92,123,168],"recognize":[6],"the":[7,22,36,72,77,94,101,120,125,129,152,187,194],"multi-class":[8],"actions,":[9],"and":[10,35,104,131,147,181],"meanwhile":[11],"locate":[12],"their":[13],"spatio-temporal":[14],"occurrence":[15],"in":[16],"untrimmed":[17],"videos.":[18],"Besides":[19],"relying":[20],"on":[21,176],"inherent":[23],"inter-actor":[24],"interactions,":[25],"most":[26],"previous":[27],"SAD":[28],"approaches":[29,46],"model":[30],"actor":[31,149],"interactions":[32],"between":[33,128],"multi-actors":[34],"whole":[37],"frames":[38],"or":[39,62],"special":[40,73],"parts":[41],"(e.g.,":[42],"objects/hands).":[43],"However,":[44],"such":[45],"are":[47,174],"relatively":[48],"graceless":[49],"by":[50,63,97],"1)":[51],"roughly":[52],"treating":[53],"all":[54],"various":[55],"actors":[56,130],"equivalently":[58],"interact":[59],"with":[60,100,151],"frames/parts":[61],"2)":[64],"sumptuously":[65],"borrowing":[66],"multiple":[67],"costly":[68],"detectors":[69],"acquire":[71],"parts.":[74],"To":[75],"solve":[76],"above":[78],"dilemma,":[79],"we":[80,108,135,157],"propose":[81],"a":[82,111,137,159],"novel":[83],"Foreground/Background-masked":[84],"Interaction":[85],"Learning":[86,192],"(dubbed":[87],"as":[88],"FBI":[89,191],"Learning)":[90],"framework":[91],"learn":[93],"multi-actor":[95],"features":[96,150],"attentively":[98],"interacting":[99],"hands-down":[102],"foreground":[103],"background":[105],"frames.":[106],"Specifically,":[107],"first":[109],"design":[110],"new":[112,138],"Mask-guided":[113],"Cross":[114],"Attention":[115],"(MCA)":[116],"mechanism":[117],"that":[118,144,163],"calculates":[119],"masked":[121],"cross-attentions":[122],"capture":[124],"compact":[126],"relations":[127],"foreground/background":[132],"regions.":[133],"Next,":[134],"present":[136],"Actor-guided":[139],"Feature":[140],"Aggregation":[141],"(AFA)":[142],"scheme":[143],"integrates":[145],"foreground-":[146],"background-interacted":[148],"learnable":[153],"actor-based":[154],"weights.":[155],"Finally,":[156],"construct":[158],"long-term":[160],"feature":[161],"bank":[162],"associates":[164],"temporal":[165],"context":[166],"information":[167],"facilitate":[169],"action":[170],"classification.":[171],"Extensive":[172],"experiments":[173],"conducted":[175],"commonly":[177],"available":[178],"UCF101-24,":[179],"MultiSports,":[180],"AVA":[182],"v2.1/v2.2":[183],"datasets,":[184],"which":[185],"illustrate":[186],"competitive":[188],"performance":[189],"of":[190],"against":[193],"state-of-the-art":[195],"methods.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}