{"id":"https://openalex.org/W4285600359","doi":"https://doi.org/10.24963/ijcai.2022/148","title":"Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement","display_name":"Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285600359","doi":"https://doi.org/10.24963/ijcai.2022/148"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/148","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/148","pdf_url":"https://www.ijcai.org/proceedings/2022/0148.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0148.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109346446","display_name":"Bing Li","orcid":"https://orcid.org/0000-0002-5888-6735"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Li","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China","State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360559","display_name":"Jiaxin Chen","orcid":"https://orcid.org/0000-0003-2035-6242"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632765","display_name":"Dongming Zhang","orcid":"https://orcid.org/0000-0002-1237-7177"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongming Zhang","raw_affiliation_strings":["National Computer Network Emergency Response Technical Team, Coordination Center of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Computer Network Emergency Response Technical Team, Coordination Center of China, Beijing, China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109674238","display_name":"Xiuguo Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuguo Bao","raw_affiliation_strings":["National Computer Network Emergency Response Technical Team, Coordination Center of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Computer Network Emergency Response Technical Team, Coordination Center of China, Beijing, China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056972984","display_name":"Di Huang","orcid":"https://orcid.org/0000-0002-2412-9330"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China","State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"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":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1060","last_page":"1066"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.998199999332428,"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":0.998199999332428,"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/T11227","display_name":"Diabetic Foot Ulcer Assessment and Management","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.973800003528595,"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":0.7524544596672058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7385597229003906},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6921660900115967},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6230624318122864},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5856122374534607},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5696756839752197},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5646135807037354},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5012435913085938},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4951864778995514},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.45181140303611755},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4151570200920105},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41420263051986694},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11551591753959656},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09377852082252502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524544596672058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7385597229003906},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6921660900115967},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6230624318122864},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5856122374534607},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5696756839752197},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5646135807037354},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5012435913085938},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4951864778995514},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.45181140303611755},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4151570200920105},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41420263051986694},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11551591753959656},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09377852082252502},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/148","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/148","pdf_url":"https://www.ijcai.org/proceedings/2022/0148.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/148","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/148","pdf_url":"https://www.ijcai.org/proceedings/2022/0148.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5048885466","display_name":null,"funder_award_id":"62022011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6767081752","display_name":null,"funder_award_id":"SKLSDE-2021ZX-04","funder_id":"https://openalex.org/F4320326978","funder_display_name":"State Key Laboratory of Software Development Environment"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326978","display_name":"State Key Laboratory of Software Development Environment","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285600359.pdf","grobid_xml":"https://content.openalex.org/works/W4285600359.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1923404803","https://openalex.org/W1971603957","https://openalex.org/W2105101328","https://openalex.org/W2156303437","https://openalex.org/W2342776425","https://openalex.org/W2507009361","https://openalex.org/W2782776028","https://openalex.org/W2963155035","https://openalex.org/W2963370182","https://openalex.org/W2963524571","https://openalex.org/W2963645879","https://openalex.org/W2963782415","https://openalex.org/W2963901365","https://openalex.org/W2964491122","https://openalex.org/W2970282336","https://openalex.org/W2978412477","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2996295497","https://openalex.org/W3035303837","https://openalex.org/W3092651603","https://openalex.org/W3175528717","https://openalex.org/W4288021822"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W2361654993","https://openalex.org/W2392886218"],"abstract_inverted_index":{"Compressed":[0],"video":[1],"action":[2],"recognition":[3],"has":[4],"recently":[5],"drawn":[6],"growing":[7],"attention,":[8],"since":[9],"it":[10],"remarkably":[11],"reduces":[12],"the":[13,42,48,52,60,81,87,91,94,98,117,125,138,151,161,168],"storage":[14],"and":[15,27,34,44,47,55,90,130,147,164,170],"computational":[16],"cost":[17],"via":[18],"replacing":[19],"raw":[20],"videos":[21],"by":[22,123],"sparsely":[23],"sampled":[24],"RGB":[25,54,88,139],"frames":[26],"compressed":[28],"motion":[29,32,56,95,99,145],"cues":[30],"(e.g.,":[31],"vectors":[33],"residuals).":[35],"However,":[36],"this":[37,64],"task":[38],"severely":[39],"suffers":[40],"from":[41],"coarse":[43],"noisy":[45],"dynamics":[46],"insufficient":[49],"fusion":[50],"of":[51,172],"heterogeneous":[53],"modalities.":[57],"To":[58],"address":[59],"two":[61,118,152],"issues":[62],"above,":[63],"paper":[65],"proposes":[66],"a":[67,102,107],"novel":[68],"framework,":[69],"namely":[70],"Attentive":[71],"Cross-modal":[72],"Interaction":[73],"Network":[74],"with":[75,106,141,154],"Motion":[76,127],"Enhancement":[77],"(MEACI-Net).":[78],"It":[79],"follows":[80],"two-stream":[82],"architecture,":[83],"i.e.":[84],"one":[85],"for":[86,93],"modality":[89,140],"other":[92],"modality.":[96],"Particularly,":[97],"stream":[100],"employs":[101],"multi-scale":[103],"block":[104],"embedded":[105],"denoising":[108],"module":[109],"to":[110],"enhance":[111],"representation":[112],"learning.":[113],"The":[114],"interaction":[115],"between":[116],"streams":[119],"is":[120],"then":[121],"strengthened":[122],"introducing":[124],"Selective":[126],"Complement":[128],"(SMC)":[129],"Cross-Modality":[131],"Augment":[132],"(CMA)":[133],"modules,":[134],"where":[135],"SMC":[136],"complements":[137],"spatio-temporally":[142],"attentive":[143],"local":[144],"features":[146],"CMA":[148],"further":[149],"combines":[150],"modalities":[153],"selective":[155],"feature":[156],"augmentation.":[157],"Extensive":[158],"experiments":[159],"on":[160],"UCF-101,":[162],"HMDB-51":[163],"Kinetics-400":[165],"benchmarks":[166],"demonstrate":[167],"effectiveness":[169],"efficiency":[171],"MEACI-Net.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}