{"id":"https://openalex.org/W4388579521","doi":"https://doi.org/10.1109/tpami.2023.3331738","title":"FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection","display_name":"FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388579521","doi":"https://doi.org/10.1109/tpami.2023.3331738","pmid":"https://pubmed.ncbi.nlm.nih.gov/37948147"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3331738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3331738","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088158236","display_name":"Shuailei Ma","orcid":"https://orcid.org/0009-0005-1134-8787"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuailei Ma","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602341","display_name":"Yuefeng Wang","orcid":"https://orcid.org/0009-0005-7133-5830"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuefeng Wang","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074944266","display_name":"Shanze Wang","orcid":"https://orcid.org/0009-0006-5771-8891"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210111795","display_name":"Hisense (China)","ror":"https://ror.org/0276vcd78","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210111795"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanze Wang","raw_affiliation_strings":["Changsha Hisense Intelligent System Research Institute Company, Ltd., Information Technology R&D Innovation Center of Peking University, Shaoxing, China"],"affiliations":[{"raw_affiliation_string":"Changsha Hisense Intelligent System Research Institute Company, Ltd., Information Technology R&D Innovation Center of Peking University, Shaoxing, China","institution_ids":["https://openalex.org/I4210111795","https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024330462","display_name":"Ying Wei","orcid":"https://orcid.org/0000-0003-0915-5378"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wei","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088158236"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":5.777,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.9730005,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"46","issue":"4","first_page":"2415","last_page":"2429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9944999814033508,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.832489013671875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.616617739200592},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5880274176597595},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5475422739982605},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4588371813297272},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45088210701942444},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42570433020591736},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3950708210468292},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2427055537700653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832489013671875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.616617739200592},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5880274176597595},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5475422739982605},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4588371813297272},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45088210701942444},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42570433020591736},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3950708210468292},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2427055537700653},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3331738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3331738","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37948147","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37948147","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2229564580","display_name":null,"funder_award_id":"61370152","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6060645268","display_name":null,"funder_award_id":"61871106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W2102605133","https://openalex.org/W2110798204","https://openalex.org/W2116341502","https://openalex.org/W2136922672","https://openalex.org/W2194775991","https://openalex.org/W2214124602","https://openalex.org/W2307770531","https://openalex.org/W2798453399","https://openalex.org/W2888096830","https://openalex.org/W2962844592","https://openalex.org/W2963037989","https://openalex.org/W2963097937","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2964016027","https://openalex.org/W2964225075","https://openalex.org/W2982232158","https://openalex.org/W2990599624","https://openalex.org/W2997150218","https://openalex.org/W3009811369","https://openalex.org/W3012573144","https://openalex.org/W3034934229","https://openalex.org/W3034951775","https://openalex.org/W3035047011","https://openalex.org/W3035598501","https://openalex.org/W3047999543","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3106121867","https://openalex.org/W3109754877","https://openalex.org/W3138516171","https://openalex.org/W3151099711","https://openalex.org/W3168488421","https://openalex.org/W3171169846","https://openalex.org/W3171660447","https://openalex.org/W3174164794","https://openalex.org/W3174480456","https://openalex.org/W3181762391","https://openalex.org/W3199093552","https://openalex.org/W4214493665","https://openalex.org/W4221138453","https://openalex.org/W4312960790","https://openalex.org/W4313007769","https://openalex.org/W4385245566","https://openalex.org/W4386072519","https://openalex.org/W6632100814","https://openalex.org/W6632922691","https://openalex.org/W6633802082","https://openalex.org/W6746776673","https://openalex.org/W6748370023","https://openalex.org/W6754152559","https://openalex.org/W6757817989","https://openalex.org/W6768920361","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6796526935","https://openalex.org/W6798016242","https://openalex.org/W6799822930","https://openalex.org/W6802996638","https://openalex.org/W6811230874","https://openalex.org/W6841090899"],"related_works":["https://openalex.org/W4234886518","https://openalex.org/W2389591058","https://openalex.org/W2382112581","https://openalex.org/W3124036233","https://openalex.org/W4229787472","https://openalex.org/W2732813147","https://openalex.org/W2143460112","https://openalex.org/W2042906257","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Human-Object":[0,247,255],"Interaction":[1],"(HOI),":[2],"as":[3],"an":[4,102],"important":[5],"problem":[6],"in":[7,29,186,193,246],"computer":[8],"vision,":[9],"requires":[10],"locating":[11],"the":[12,17,35,49,62,76,84,94,110,134,180,187,196,209,228,240,274,280,284],"human-object":[13],"pair":[14],"and":[15,32,113,150,161,174,178,183,190,233,249,269,279],"identifying":[16],"interactive":[18],"relationships":[19],"between":[20],"them.":[21],"The":[22],"HOI":[23,55,79,168,231,258,276],"instance":[24],"has":[25,83],"a":[26,118,124,198,234],"greater":[27],"span":[28],"spatial,":[30],"scale,":[31],"task":[33,191],"than":[34],"individual":[36],"object":[37],"instance,":[38],"making":[39],"its":[40],"detection":[41,77,232,277],"more":[42],"susceptible":[43],"to":[44,60,66,74,89,107,132,207,226],"noisy":[45,52,165],"backgrounds.":[46],"To":[47],"alleviate":[48,133],"disturbance":[50],"of":[51,78,158,170,230,254,257,286],"backgrounds":[53,166],"on":[54,264],"detection,":[56],"it":[57,82],"is":[58,100,116,130,205],"necessary":[59],"consider":[61],"input":[63],"image":[64],"information":[65,99],"generate":[67],"fine-grained":[68],"anchors":[69],"which":[70],"are":[71,262],"then":[72],"leveraged":[73],"guide":[75],"instances.":[80],"However,":[81],"following":[85],"challenges.":[86],"i)":[87],"how":[88,106],"extract":[90],"pivotal":[91],"features":[92,112,157,182],"from":[93,164],"images":[95],"with":[96],"complex":[97,215],"background":[98],"still":[101],"open":[103],"question.":[104],"ii)":[105],"semantically":[108,176],"align":[109,177],"extracted":[111,181],"query":[114,184],"embeddings":[115,185],"also":[117],"difficult":[119],"issue.":[120],"In":[121,195,220],"this":[122],"paper,":[123],"novel":[125,199,235],"end-to-end":[126],"transformer-based":[127],"framework":[128],"(FGAHOI)":[129],"proposed":[131,288],"above":[135],"problems.":[136],"FGAHOI":[137],"comprises":[138],"three":[139,265],"dedicated":[140],"components":[141],"namely,":[142],"multi-scale":[143],"sampling":[144],"(MSS),":[145],"hierarchical":[146,188],"spatial-aware":[147],"merging":[148,152],"(HSAM)":[149],"task-aware":[151],"mechanism":[153],"(TAM).":[154],"MSS":[155],"extracts":[156],"humans,":[159],"objects":[160],"interaction":[162],"areas":[163],"for":[167,239],"instances":[169,259],"various":[171],"scales.":[172],"HSAM":[173],"TAM":[175],"merge":[179],"spatial":[189],"perspectives":[192],"turn.":[194],"meanwhile,":[197],"training":[200,210],"strategy":[201],"Stage-wise":[202],"Training":[203],"Strategy":[204],"designed":[206],"reduce":[208],"pressure":[211],"caused":[212],"by":[213,218],"overly":[214],"tasks":[216],"done":[217],"FGAHOI.":[219],"addition,":[221],"we":[222],"propose":[223],"two":[224,241],"ways":[225],"measure":[227],"difficulty":[229],"dataset,":[236],"i.e.,":[237],"HOI-SDC":[238,268],"challenges":[242],"(Uneven":[243],"Distributed":[244],"Area":[245],"Pairs":[248],"Long":[250],"Distance":[251],"Visual":[252],"Modeling":[253],"Pairs)":[256],"detection.":[260],"Experiments":[261],"conducted":[263],"benchmarks:":[266],"HICO-DET,":[267],"V-COCO.":[270],"Our":[271],"model":[272],"outperforms":[273],"state-of-the-art":[275],"methods,":[278],"extensive":[281],"ablations":[282],"reveal":[283],"merits":[285],"our":[287],"contribution.":[289]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}