{"id":"https://openalex.org/W4293518124","doi":"https://doi.org/10.1109/icme52920.2022.9859803","title":"HOIG: End-to-End Human-Object Interactions Grounding with Transformers","display_name":"HOIG: End-to-End Human-Object Interactions Grounding with Transformers","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518124","doi":"https://doi.org/10.1109/icme52920.2022.9859803"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859803","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5030001981","display_name":"Zeyu Ma","orcid":"https://orcid.org/0000-0002-2553-0679"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zeyu Ma","raw_affiliation_strings":["Xi'an Jiaotong University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101947241","display_name":"Ping Wei","orcid":"https://orcid.org/0000-0002-8535-9527"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Wei","raw_affiliation_strings":["Xi'an Jiaotong University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107340627","display_name":"Huan Li","orcid":"https://orcid.org/0000-0003-4302-5120"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Li","raw_affiliation_strings":["Xi'an Jiaotong University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Xi'an Jiaotong University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030001981"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.2998,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63161272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9990000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9947999715805054,"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":0.7718468308448792},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.7665486931800842},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7028524279594421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6034334897994995},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5845657587051392},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5332434177398682},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4586145877838135},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4553660750389099},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.43619489669799805},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4329938590526581},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4287303686141968},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1602972149848938},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08769771456718445},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08613172173500061},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07143154740333557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7718468308448792},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.7665486931800842},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7028524279594421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6034334897994995},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5845657587051392},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5332434177398682},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4586145877838135},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4553660750389099},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.43619489669799805},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4329938590526581},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4287303686141968},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1602972149848938},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08769771456718445},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08613172173500061},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07143154740333557},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859803","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4678327438","display_name":null,"funder_award_id":"61876149,62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G577169378","display_name":null,"funder_award_id":"2018AAA0102501","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1551928752","https://openalex.org/W1905882502","https://openalex.org/W2194775991","https://openalex.org/W2416798379","https://openalex.org/W2795378892","https://openalex.org/W2896457183","https://openalex.org/W2962766617","https://openalex.org/W2962844592","https://openalex.org/W2963097937","https://openalex.org/W2963125676","https://openalex.org/W2963383024","https://openalex.org/W2963800628","https://openalex.org/W2964225075","https://openalex.org/W2964276121","https://openalex.org/W2987734933","https://openalex.org/W3014611590","https://openalex.org/W3030520226","https://openalex.org/W3035635363","https://openalex.org/W3159619744","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W4214490042","https://openalex.org/W4385245566","https://openalex.org/W6632922691","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6775188310","https://openalex.org/W6778485988"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2021787609","https://openalex.org/W2097328689","https://openalex.org/W4234899305","https://openalex.org/W1537063595","https://openalex.org/W2379604501","https://openalex.org/W1999612375","https://openalex.org/W2373854414","https://openalex.org/W2938107654","https://openalex.org/W2522183581"],"abstract_inverted_index":{"Visual":[0],"grounding":[1,22,85],"is":[2,26],"a":[3,36,56,72,84],"crucial":[4],"and":[5,83,94,100],"challenging":[6,114],"problem":[7,75],"in":[8,52,102],"many":[9],"applications.":[10],"While":[11],"it":[12],"has":[13],"been":[14],"extensively":[15],"investigated":[16],"over":[17],"the":[18,47,69,117],"past":[19],"years,":[20],"human-centric":[21],"with":[23,55],"multiple":[24],"instances":[25,51],"still":[27],"an":[28,53,64,103],"open":[29],"problem.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"introduce":[35],"new":[37],"task":[38,70],"of":[39,119],"Human-Object":[40],"Interactions":[41],"(HOI)":[42],"Grounding":[43],"to":[44,67,89],"localize":[45],"all":[46],"referring":[48],"human-object":[49],"pair":[50],"image":[54],"given":[57],"\u27e8human,":[58],"interaction,":[59],"object\u27e9":[60],"phrase.":[61],"We":[62],"design":[63],"encoder-decoder":[65],"architecture":[66],"model":[68,97],"as":[71],"set":[73],"prediction":[74,101],"based":[76],"on":[77,112],"transformers.":[78],"A":[79],"vision-language":[80],"alignment":[81,99],"module":[82],"decoder":[86],"are":[87],"designed":[88],"learn":[90],"accurate":[91],"cross-modal":[92],"contexts":[93],"interactions.":[95],"Our":[96],"accomplishes":[98],"end-to-end":[104],"manner":[105],"without":[106],"pre-trained":[107],"detectors":[108],"or":[109],"post-processing.":[110],"Experiments":[111],"two":[113],"datasets":[115],"prove":[116],"strength":[118],"our":[120],"model.":[121]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}