{"id":"https://openalex.org/W4407606881","doi":"https://doi.org/10.1007/s11263-025-02369-8","title":"Diagnosing Human-Object Interaction Detectors","display_name":"Diagnosing Human-Object Interaction Detectors","publication_year":2025,"publication_date":"2025-02-16","ids":{"openalex":"https://openalex.org/W4407606881","doi":"https://doi.org/10.1007/s11263-025-02369-8"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02369-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02369-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02369-8.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02369-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082377384","display_name":"Fangrui Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fangrui Zhu","raw_affiliation_strings":["Northeastern University, Boston, 02115, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, 02115, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101950799","display_name":"Yiming Xie","orcid":"https://orcid.org/0000-0003-1209-9856"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Xie","raw_affiliation_strings":["Northeastern University, Boston, 02115, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, 02115, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076097168","display_name":"Weidi Xie","orcid":"https://orcid.org/0000-0003-3804-2639"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidi Xie","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, 200240, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103861361","display_name":"Huaizu Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaizu Jiang","raw_affiliation_strings":["Northeastern University, Boston, 02115, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, 02115, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082377384"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":4.2089,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93020015,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"133","issue":"4","first_page":"2227","last_page":"2244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9977999925613403,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6951735615730286},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6277869939804077},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5757750868797302},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.546572208404541},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5462540984153748},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5265855193138123}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6951735615730286},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6277869939804077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5757750868797302},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.546572208404541},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5462540984153748},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5265855193138123},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02369-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02369-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02369-8.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-025-02369-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02369-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02369-8.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407606881.pdf","grobid_xml":"https://content.openalex.org/works/W4407606881.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1832500336","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2214124602","https://openalex.org/W2277195237","https://openalex.org/W2463565445","https://openalex.org/W2463955103","https://openalex.org/W2745461083","https://openalex.org/W2902101981","https://openalex.org/W2963191264","https://openalex.org/W2963588253","https://openalex.org/W2963686907","https://openalex.org/W2963743213","https://openalex.org/W2964225075","https://openalex.org/W2964303913","https://openalex.org/W2982232158","https://openalex.org/W2983943451","https://openalex.org/W2990599624","https://openalex.org/W2990818246","https://openalex.org/W3034951775","https://openalex.org/W3035021222","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3109485382","https://openalex.org/W3109923227","https://openalex.org/W3116271762","https://openalex.org/W3135367836","https://openalex.org/W3151099711","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W3191257570","https://openalex.org/W3197395033","https://openalex.org/W4226451586","https://openalex.org/W4297632532","https://openalex.org/W4312446811","https://openalex.org/W4312502942","https://openalex.org/W4312538795","https://openalex.org/W4312613394","https://openalex.org/W4312770707","https://openalex.org/W4312960102","https://openalex.org/W4313176000","https://openalex.org/W4319300851","https://openalex.org/W4386057783","https://openalex.org/W4388579521","https://openalex.org/W4390873645","https://openalex.org/W4402576760","https://openalex.org/W6803025782"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Abstract":[0],"We":[1,82,188],"have":[2],"witnessed":[3],"significant":[4,219],"progress":[5],"in":[6,48,60,221],"human-object":[7,133,150,183],"interaction":[8,137,223],"(HOI)":[9],"detection.":[10],"However,":[11],"relying":[12],"solely":[13],"on":[14,115],"mAP":[15,117],"(mean":[16],"Average":[17],"Precision)":[18],"scores":[19],"as":[20],"a":[21,57,65,85,95,166],"summary":[22],"metric":[23],"does":[24],"not":[25],"provide":[26],"sufficient":[27],"insight":[28],"into":[29,88],"the":[30,75,89,109,116,126,140,146,154,157,161,209],"nuances":[31],"of":[32,69,77,97,111,130,148,156],"model":[33,40,211],"performance":[34],"(":[35],"e.g.":[36],",":[37],"why":[38],"one":[39],"outperforms":[41,213],"another),":[42],"which":[43],"can":[44],"hinder":[45],"further":[46],"innovation":[47],"this":[49,53,61],"field.":[50],"To":[51],"address":[52],"issue,":[54],"we":[55,106,124,144,164],"introduce":[56],"diagnosis":[58,80,206],"toolbox":[59,227],"paper":[62],"to":[63,102,169,178,199,217],"offer":[64],"detailed":[66],"quantitative":[67],"breakdown":[68],"HOI":[70,90,131,192],"detection":[71,79,91,175,193],"models,":[72,194],"inspired":[73],"by":[74],"success":[76],"object":[78],"tools.":[81],"first":[83],"conduct":[84],"holistic":[86],"investigation":[87],"pipeline.":[92],"By":[93],"defining":[94],"set":[96],"errors":[98,113],"and":[99,136,152,173,177,233,235],"using":[100],"oracles":[101],"fix":[103],"each":[104],"one,":[105],"quantitatively":[107],"analyze":[108,189],"significance":[110],"different":[112],"based":[114],"improvement":[118,220],"gained":[119],"from":[120],"fixing":[121],"them.":[122],"Next,":[123],"explore":[125],"two":[127],"key":[128],"sub-tasks":[129],"detection:":[132],"pair":[134,141],"localization":[135,142,158],"classification.":[138],"For":[139,160,203],"task,":[143,163],"compute":[145],"coverage":[147],"ground-truth":[149],"pairs":[151,184],"assess":[153],"noisiness":[155],"results.":[159],"classification":[162,224],"measure":[165],"model\u2019s":[167],"ability":[168],"distinguish":[170],"between":[171],"positive":[172],"negative":[174],"results":[176],"classify":[179],"actual":[180],"interactions":[181],"when":[182],"are":[185],"correctly":[186],"localized.":[187],"eight":[190],"state-of-the-art":[191,210],"providing":[195],"valuable":[196],"diagnostic":[197],"insights":[198],"guide":[200],"future":[201],"research.":[202],"instance,":[204],"our":[205],"reveals":[207],"that":[208],"RLIPv2":[212],"others":[214],"primarily":[215],"due":[216],"its":[218],"multi-label":[222],"accuracy.":[225],"Our":[226],"is":[228,236],"applicable":[229],"across":[230],"various":[231],"methods":[232],"datasets":[234],"available":[237],"at":[238],"https://neu-vi.github.io/Diag-HOI/":[239],".":[240]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-10-10T00:00:00"}