{"id":"https://openalex.org/W4386597239","doi":"https://doi.org/10.1109/icip49359.2023.10222323","title":"ScratchHOI: Training Human-Object Interaction Detectors from Scratch","display_name":"ScratchHOI: Training Human-Object Interaction Detectors from Scratch","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386597239","doi":"https://doi.org/10.1109/icip49359.2023.10222323"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222323","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109517233","display_name":"JunYi Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"JunYi Lim","raw_affiliation_strings":["Monash University Malaysia,School of Engineering,Malaysia","Monash University Malaysia,School of Information Technology,Malaysia","School of Information Technology, Monash University Malaysia, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University Malaysia,School of Engineering,Malaysia","institution_ids":["https://openalex.org/I11662577"]},{"raw_affiliation_string":"Monash University Malaysia,School of Information Technology,Malaysia","institution_ids":["https://openalex.org/I11662577"]},{"raw_affiliation_string":"School of Information Technology, Monash University Malaysia, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023680401","display_name":"Vishnu Monn Baskaran","orcid":"https://orcid.org/0000-0001-6809-5817"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Vishnu Monn Baskaran","raw_affiliation_strings":["Monash University Malaysia,School of Information Technology,Malaysia","School of Information Technology, Monash University Malaysia, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University Malaysia,School of Information Technology,Malaysia","institution_ids":["https://openalex.org/I11662577"]},{"raw_affiliation_string":"School of Information Technology, Monash University Malaysia, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103432527","display_name":"Joanne Mun-Yee Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Joanne MunYee Lim","raw_affiliation_strings":["Monash University Malaysia,School of Engineering,Malaysia","Monash University Malaysia,School of Information Technology,Malaysia","School of Engineering, Monash University Malaysia, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University Malaysia,School of Engineering,Malaysia","institution_ids":["https://openalex.org/I11662577"]},{"raw_affiliation_string":"Monash University Malaysia,School of Information Technology,Malaysia","institution_ids":["https://openalex.org/I11662577"]},{"raw_affiliation_string":"School of Engineering, Monash University Malaysia, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053268072","display_name":"Ricky Sutopo","orcid":"https://orcid.org/0000-0002-0812-728X"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ricky Sutopo","raw_affiliation_strings":["Monash University Malaysia,School of Information Technology,Malaysia","School of Information Technology, Monash University Malaysia, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University Malaysia,School of Information Technology,Malaysia","institution_ids":["https://openalex.org/I11662577"]},{"raw_affiliation_string":"School of Information Technology, Monash University Malaysia, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069916756","display_name":"KokSheik Wong","orcid":"https://orcid.org/0000-0002-4893-2291"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"KokSheik Wong","raw_affiliation_strings":["Monash University Malaysia,School of Information Technology,Malaysia","School of Information Technology, Monash University Malaysia, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University Malaysia,School of Information Technology,Malaysia","institution_ids":["https://openalex.org/I11662577"]},{"raw_affiliation_string":"School of Information Technology, Monash University Malaysia, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064744996","display_name":"M\u00e1ssimo Tistarelli","orcid":"https://orcid.org/0000-0002-3406-3048"},"institutions":[{"id":"https://openalex.org/I159650629","display_name":"University of Sassari","ror":"https://ror.org/01bnjbv91","country_code":"IT","type":"education","lineage":["https://openalex.org/I159650629"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimo Tistarelli","raw_affiliation_strings":["University of Sassari,Department of Biomedical Sciences and Information Technology,Italy","Department of Biomedical Sciences and Information Technology, University of Sassari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sassari,Department of Biomedical Sciences and Information Technology,Italy","institution_ids":["https://openalex.org/I159650629"]},{"raw_affiliation_string":"Department of Biomedical Sciences and Information Technology, University of Sassari, Italy","institution_ids":["https://openalex.org/I159650629"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"1690","last_page":"1694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9988999962806702,"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/scratch","display_name":"Scratch","score":0.8490585088729858},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7930217385292053},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7198948860168457},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7107159495353699},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6526228785514832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6049777269363403},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4549923837184906},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44126221537590027},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41494515538215637},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4147798418998718},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3648107051849365},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3605959117412567},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3210863173007965},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08311125636100769},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06889504194259644}],"concepts":[{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.8490585088729858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930217385292053},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7198948860168457},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7107159495353699},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6526228785514832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6049777269363403},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4549923837184906},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44126221537590027},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41494515538215637},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4147798418998718},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3648107051849365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3605959117412567},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3210863173007965},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08311125636100769},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06889504194259644},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222323","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2796191958","https://openalex.org/W2963813458","https://openalex.org/W2964225075","https://openalex.org/W3034934229","https://openalex.org/W3035598501","https://openalex.org/W3047999543","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3109754877","https://openalex.org/W3151099711","https://openalex.org/W3168279596","https://openalex.org/W3168488421","https://openalex.org/W3171206729","https://openalex.org/W3174164794","https://openalex.org/W3179066717","https://openalex.org/W3181762391","https://openalex.org/W3199761064","https://openalex.org/W3212153990","https://openalex.org/W3214395274","https://openalex.org/W4212774754","https://openalex.org/W4214634256","https://openalex.org/W4312538795","https://openalex.org/W4312718069","https://openalex.org/W4312770707","https://openalex.org/W4312848112","https://openalex.org/W4312960102","https://openalex.org/W4312979210","https://openalex.org/W4313155487","https://openalex.org/W4313176000","https://openalex.org/W4319998180","https://openalex.org/W4386072519","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6799822930","https://openalex.org/W6803916128"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623","https://openalex.org/W2494989134","https://openalex.org/W2509444723","https://openalex.org/W2004958254"],"abstract_inverted_index":{"Transformer-based":[0],"approaches":[1,16,126],"have":[2,23],"exhibited":[3],"outstanding":[4],"performances":[5],"in":[6],"the":[7,28,35,71,114],"field":[8],"of":[9,37,130],"human-object":[10,61],"interaction":[11,62],"(HOI)":[12],"detection.":[13],"However,":[14],"these":[15],"rely":[17],"on":[18,27,113],"underlying":[19],"object":[20,75],"detectors":[21],"that":[22,64,118],"undergone":[24],"large-scale":[25],"pre-trainings":[26],"ImageNet":[29],"and":[30,41,80,88,104,110],"MS-COCO":[31],"dataset.":[32],"This":[33],"limits":[34],"potential":[36],"unique":[38],"architectural":[39],"designs":[40],"induces":[42],"a":[43,57,128],"learning":[44],"bias,":[45],"causing":[46],"ineffective":[47],"HOI":[48],"representation":[49],"learning.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"ScratchHOI,":[56],"transformer-based":[58],"method":[59],"for":[60,73,85,108],"detection":[63,99],"can":[65],"be":[66],"trained":[67],"from":[68],"scratch,":[69],"eliminating":[70],"need":[72],"pre-trained":[74],"detectors.":[76],"ScratchHOI":[77,119],"employs":[78],"dynamic":[79,103],"static":[81],"affinity-based":[82],"feature":[83],"aggregation":[84],"processing":[86],"local":[87],"long-range":[89],"visual":[90],"information.":[91],"Additional":[92],"techniques":[93],"are":[94],"also":[95],"employed":[96],"to":[97],"improve":[98],"performance,":[100],"such":[101],"as":[102],"interactive":[105],"anchor":[106],"refinement":[107],"objects":[109],"interactions.":[111],"Experiments":[112],"HICO-Det":[115],"dataset":[116],"show":[117],"achieves":[120],"competitive":[121],"performance":[122],"against":[123],"other":[124],"state-of-the-art":[125],"over":[127],"variety":[129],"different":[131],"evaluation":[132],"measures.":[133]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
