{"id":"https://openalex.org/W2963699792","doi":"https://doi.org/10.1109/cvpr.2018.00710","title":"Attend and Interact: Higher-Order Object Interactions for Video Understanding","display_name":"Attend and Interact: Higher-Order Object Interactions for Video Understanding","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2963699792","doi":"https://doi.org/10.1109/cvpr.2018.00710","mag":"2963699792"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2018.00710","doi":"https://doi.org/10.1109/cvpr.2018.00710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00710","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1711.06330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057482975","display_name":"Chih\u2010Yao Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chih-Yao Ma","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016480160","display_name":"Asim Kadav","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asim Kadav","raw_affiliation_strings":["NEC Laboratories America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America","institution_ids":["https://openalex.org/I4210107353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058301235","display_name":"Iain Melvin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iain Melvin","raw_affiliation_strings":["NEC Laboratories America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America","institution_ids":["https://openalex.org/I4210107353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088892134","display_name":"Zsolt Kira","orcid":"https://orcid.org/0000-0002-2626-2004","observed_orcids":["https://orcid.org/0000-0002-2626-2004"]},"institutions":[{"id":"https://openalex.org/I4388482740","display_name":"Georgia Tech Research Institute","ror":"https://ror.org/04qfrh333","country_code":"US","type":"facility","lineage":["https://openalex.org/I130701444","https://openalex.org/I4388482740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zsolt Kira","raw_affiliation_strings":["Georgia Tech Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech Research Institute","institution_ids":["https://openalex.org/I4388482740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006145139","display_name":"Ghassan AlRegib","orcid":"https://orcid.org/0000-0001-6818-8001","observed_orcids":["https://orcid.org/0000-0001-6818-8001"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghassan AlRegib","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110182290","display_name":"Hans Peter Graf","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hans Peter Graf","raw_affiliation_strings":["NEC Laboratories America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America","institution_ids":["https://openalex.org/I4210107353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.9583,"has_fulltext":true,"cited_by_count":137,"citation_normalized_percentile":{"value":0.97426002,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6790","last_page":"6800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9932000041007996,"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":0.9932000041007996,"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":0.005900000222027302,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/visual-relationship-detection","display_name":"visual relationship detection","score":0.9739999771118164},{"id":"https://openalex.org/keywords/human-action-recognition","display_name":"human action recognition","score":0.8799999952316284},{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/sinet","display_name":"SINET","score":0.7770000100135803},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.5419999957084656},{"id":"https://openalex.org/keywords/low-frame-rate-video","display_name":"low frame rate video","score":0.4729999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8465682864189148},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.800013542175293},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7010047435760498},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6703168153762817},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6615790128707886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6279654502868652},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5295411348342896},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.509510338306427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43554019927978516},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4254192113876343},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4052094519138336},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3581410348415375},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20968139171600342},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08062079548835754},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr.2018.00710","doi":"https://doi.org/10.1109/cvpr.2018.00710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00710","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1711.06330","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.06330","pdf_url":"https://arxiv.org/pdf/1711.06330","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1711.06330","doi":"https://doi.org/10.48550/arxiv.1711.06330","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1711.06330","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1711.06330","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.06330","pdf_url":"https://arxiv.org/pdf/1711.06330","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6804925923","display_name":"NRI: Large-Scale Collaborative Semantic Mapping using 3D Structure from Motion","funder_award_id":"1426998","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963699792.pdf","grobid_xml":"https://content.openalex.org/works/W2963699792.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W874179280","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1927052826","https://openalex.org/W1956340063","https://openalex.org/W2016053056","https://openalex.org/W2029928277","https://openalex.org/W2077069816","https://openalex.org/W2101105183","https://openalex.org/W2122476475","https://openalex.org/W2123301721","https://openalex.org/W2126579184","https://openalex.org/W2136036867","https://openalex.org/W2139501017","https://openalex.org/W2154652894","https://openalex.org/W2156303437","https://openalex.org/W2194775991","https://openalex.org/W2308045930","https://openalex.org/W2336403884","https://openalex.org/W2337252826","https://openalex.org/W2342662179","https://openalex.org/W2462631560","https://openalex.org/W2491875666","https://openalex.org/W2507009361","https://openalex.org/W2518918709","https://openalex.org/W2519080876","https://openalex.org/W2524365899","https://openalex.org/W2538640453","https://openalex.org/W2549139847","https://openalex.org/W2556388456","https://openalex.org/W2558535589","https://openalex.org/W2558834163","https://openalex.org/W2563296158","https://openalex.org/W2565656701","https://openalex.org/W2575842049","https://openalex.org/W2579549467","https://openalex.org/W2583815496","https://openalex.org/W2591644541","https://openalex.org/W2601564443","https://openalex.org/W2607119937","https://openalex.org/W2607855566","https://openalex.org/W2608988379","https://openalex.org/W2610163825","https://openalex.org/W2619082050","https://openalex.org/W2619947201","https://openalex.org/W2621571501","https://openalex.org/W2624614404","https://openalex.org/W2626778328","https://openalex.org/W2706729717","https://openalex.org/W2745461083","https://openalex.org/W2747804831","https://openalex.org/W2754191212","https://openalex.org/W2765277449","https://openalex.org/W2799261915","https://openalex.org/W2949190893","https://openalex.org/W2949650786","https://openalex.org/W2950019618","https://openalex.org/W2950209802","https://openalex.org/W2950307714","https://openalex.org/W2952574180","https://openalex.org/W2952686080","https://openalex.org/W2953084276","https://openalex.org/W2963097937","https://openalex.org/W2963166524","https://openalex.org/W2963576560","https://openalex.org/W2963649796","https://openalex.org/W2963650529","https://openalex.org/W2963820951","https://openalex.org/W2964225075","https://openalex.org/W6600983433","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2770368992","https://openalex.org/W2951702519","https://openalex.org/W3125857240","https://openalex.org/W4377009942","https://openalex.org/W2953048415","https://openalex.org/W4210650681","https://openalex.org/W7172118599","https://openalex.org/W3152380984","https://openalex.org/W4402715892","https://openalex.org/W2904023314"],"abstract_inverted_index":{"Human":[0],"actions":[1],"often":[2,24],"involve":[3],"complex":[4],"interactions":[5,36,71,86,156,169],"across":[6,37],"several":[7],"inter-related":[8],"objects":[9,39,76],"in":[10,40],"the":[11,102,133,144,151,172],"scene.":[12],"However,":[13],"existing":[14],"approaches":[15],"to":[16,59,67],"fine-grained":[17,78],"video":[18,45,79,95,161],"understanding":[19],"or":[20,30],"visual":[21],"relationship":[22],"detection":[23],"rely":[25],"on":[26,113,128,157],"single":[27],"object":[28,32,85,155,168],"representation":[29],"pairwise":[31,106],"relationships.":[33,107],"Furthermore,":[34],"learning":[35],"multiple":[38],"hundreds":[41],"of":[42,75,140,146],"frames":[43],"for":[44,77,90],"is":[46,111,150],"computationally":[47],"infeasible":[48],"and":[49,94,118,123,163],"performance":[50,173],"may":[51],"suffer":[52],"since":[53],"a":[54,138],"large":[55],"combinatorial":[56],"space":[57],"has":[58],"be":[60],"modeled.":[61],"In":[62],"this":[63,149],"paper,":[64],"we":[65,164],"propose":[66],"efficiently":[68],"learn":[69],"higher-order":[70,167],"between":[72],"arbitrary":[73],"subgroups":[74],"understanding.":[80],"We":[81],"demonstrate":[82],"that":[83],"modeling":[84,154],"significantly":[87],"improves":[88,171],"accuracy":[89],"both":[91,129],"action":[92],"recognition":[93],"captioning,":[96],"while":[97],"saving":[98],"more":[99],"than":[100],"3-times":[101],"computation":[103],"over":[104],"traditional":[105],"The":[108],"proposed":[109],"method":[110],"validated":[112],"two":[114],"large-scale":[115,160],"datasets:":[116],"Kinetics":[117],"ActivityNet":[119],"Captions.":[120],"Our":[121],"SINet":[122],"SINet-Caption":[124],"achieve":[125],"state-of-the-art":[126],"performances":[127],"datasets":[130],"even":[131],"though":[132],"videos":[134],"are":[135],"sampled":[136],"at":[137],"maximum":[139],"1":[141],"FPS.":[142],"To":[143],"best":[145],"our":[147],"knowledge,":[148],"first":[152],"work":[153],"open":[158],"domain":[159],"datasets,":[162],"additionally":[165],"model":[166],"which":[170],"with":[174],"low":[175],"computational":[176],"costs.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":12}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-07-30T00:00:00"}