{"id":"https://openalex.org/W4387969759","doi":"https://doi.org/10.1145/3581783.3612581","title":"Learning from Easy to Hard Pairs: Multi-step Reasoning Network for Human-Object Interaction Detection","display_name":"Learning from Easy to Hard Pairs: Multi-step Reasoning Network for Human-Object Interaction Detection","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969759","doi":"https://doi.org/10.1145/3581783.3612581"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612581","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5060753538","display_name":"Yuchen Zhou","orcid":"https://orcid.org/0000-0002-2470-0293"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Zhou","raw_affiliation_strings":["School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2470-0293","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062708755","display_name":"Guang Tan","orcid":"https://orcid.org/0000-0002-0658-8867"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Tan","raw_affiliation_strings":["School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0658-8867","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042786242","display_name":"Mengtang Li","orcid":"https://orcid.org/0000-0002-3594-4808"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengtang Li","raw_affiliation_strings":["School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3594-4808","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042895349","display_name":"Chao Gou","orcid":"https://orcid.org/0000-0002-4128-886X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Gou","raw_affiliation_strings":["School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4128-886X","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6842,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.86739892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4368","last_page":"4377"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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"}},{"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/computer-science","display_name":"Computer science","score":0.8237581849098206},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7569637298583984},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6563875079154968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6550811529159546},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6205710768699646},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5829434394836426},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5439810752868652},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4482290744781494},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.277413547039032},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08148285746574402}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237581849098206},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7569637298583984},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6563875079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6550811529159546},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6205710768699646},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5829434394836426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5439810752868652},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4482290744781494},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.277413547039032},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08148285746574402},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612581","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G793950477","display_name":null,"funder_award_id":"2023A1515030264","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G7978321733","display_name":null,"funder_award_id":"JCYJ20200109142217397","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2888096830","https://openalex.org/W2962844592","https://openalex.org/W2963097937","https://openalex.org/W2963351448","https://openalex.org/W3034205192","https://openalex.org/W3034895839","https://openalex.org/W3034951775","https://openalex.org/W3035598501","https://openalex.org/W3049440217","https://openalex.org/W3096609285","https://openalex.org/W3097802466","https://openalex.org/W3101631402","https://openalex.org/W3106988096","https://openalex.org/W3107081247","https://openalex.org/W3109754877","https://openalex.org/W3151099711","https://openalex.org/W3168279596","https://openalex.org/W3168488421","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W3174480456","https://openalex.org/W3181762391","https://openalex.org/W3191257570","https://openalex.org/W3197395033","https://openalex.org/W3205607545","https://openalex.org/W3207158043","https://openalex.org/W3212153990","https://openalex.org/W4283777642","https://openalex.org/W4284681282","https://openalex.org/W4304080274","https://openalex.org/W4304087062","https://openalex.org/W4312241193","https://openalex.org/W4312446811","https://openalex.org/W4312770707","https://openalex.org/W4312848112","https://openalex.org/W4312960102","https://openalex.org/W4313057390","https://openalex.org/W4313169234","https://openalex.org/W4313176000","https://openalex.org/W4386057783"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W4287991909","https://openalex.org/W4390721878","https://openalex.org/W1834370135","https://openalex.org/W4292830139"],"abstract_inverted_index":{"Human-object":[0],"interaction":[1,123],"(HOI)":[2],"detection":[3],"aims":[4],"to":[5,89,100,120],"interpret":[6],"the":[7,40,56,102],"interactions":[8],"of":[9,104],"human-object":[10],"pairs.":[11],"Existing":[12],"methods":[13],"adopt":[14],"a":[15,79,114],"one-step":[16],"reasoning":[17],"paradigm":[18],"that":[19,55,84,135],"simultaneously":[20],"outputs":[21],"multi-label":[22,122],"results":[23],"for":[24],"all":[25],"HOI":[26,37,106],"pairs":[27,38,107],"without":[28],"distinguishing":[29],"difficulties.":[30],"However,":[31],"there":[32],"are":[33],"significant":[34],"variations":[35],"among":[36],"in":[39,47],"same":[41],"image,":[42],"making":[43],"their":[44],"performance":[45],"degrade":[46],"challenging":[48,143],"situations.":[49],"In":[50,92],"this":[51,75],"paper,":[52],"we":[53,77,112],"argue":[54],"model":[57],"should":[58],"prioritize":[59],"hard":[60,67,90,105],"samples":[61,68],"after":[62],"inferring":[63],"easy":[64,72,88],"ones,":[65],"and":[66,129],"can":[69],"benefit":[70],"from":[71,87],"ones.":[73],"To":[74],"end,":[76],"propose":[78,113],"novel":[80],"Multi-step":[81,115],"Reasoning":[82,116],"Network":[83],"progressively":[85],"learns":[86],"samples.":[91],"particular,":[93],"an":[94],"Easy-to-Hard":[95],"Learning":[96],"Block":[97],"is":[98],"introduced":[99],"enhance":[101,121],"representation":[103],"by":[108],"prior":[109],"associations.":[110],"Additionally,":[111],"Probability":[117],"Transfer":[118],"mechanism":[119],"classifications,":[124],"which":[125],"leverages":[126],"cognitive":[127],"associations":[128],"semantic":[130],"dependencies.":[131],"Extensive":[132],"experiments":[133],"demonstrate":[134],"our":[136],"method":[137],"outperforms":[138],"other":[139],"state-of-the-art":[140],"on":[141],"two":[142],"benchmark":[144],"datasets.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}