{"id":"https://openalex.org/W4402352189","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650930","title":"MMFENet:Multi-Modal Feature Enhancement Network with Transformer for Human-Object Interaction Detection","display_name":"MMFENet:Multi-Modal Feature Enhancement Network with Transformer for Human-Object Interaction Detection","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352189","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650930"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5100396141","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0003-3098-009X"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Key Laboratory of Network System and Network Culture,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Network System and Network Culture,Beijing,China","institution_ids":["https://openalex.org/I4210108629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060751096","display_name":"Wenhao Yang","orcid":"https://orcid.org/0000-0003-2837-1412"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Yang","raw_affiliation_strings":["Key Laboratory of Network System and Network Culture,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Network System and Network Culture,Beijing,China","institution_ids":["https://openalex.org/I4210108629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053619472","display_name":"Zhicheng Zhao","orcid":"https://orcid.org/0000-0001-6506-7298"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Zhao","raw_affiliation_strings":["Key Laboratory of Network System and Network Culture,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Network System and Network Culture,Beijing,China","institution_ids":["https://openalex.org/I4210108629"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101754632","display_name":"Fei Su","orcid":"https://orcid.org/0000-0003-4245-4687"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Su","raw_affiliation_strings":["Key Laboratory of Network System and Network Culture,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Network System and Network Culture,Beijing,China","institution_ids":["https://openalex.org/I4210108629"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210108629"],"apc_list":null,"apc_paid":null,"fwci":0.5259,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6885182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9995999932289124,"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":0.9965000152587891,"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/modal","display_name":"Modal","score":0.6071251034736633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5825474262237549},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5459761023521423},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4799811542034149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47658345103263855},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4733572006225586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4576408565044403},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4122144877910614},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36439359188079834},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18083587288856506},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.14667600393295288},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.13576167821884155},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07070320844650269}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6071251034736633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5825474262237549},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5459761023521423},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4799811542034149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47658345103263855},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4733572006225586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4576408565044403},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4122144877910614},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36439359188079834},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18083587288856506},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.14667600393295288},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.13576167821884155},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07070320844650269},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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":46,"referenced_works":["https://openalex.org/W1551928752","https://openalex.org/W2077069816","https://openalex.org/W2131774270","https://openalex.org/W2214124602","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2888096830","https://openalex.org/W2908510526","https://openalex.org/W2963084599","https://openalex.org/W2963758027","https://openalex.org/W2963762755","https://openalex.org/W2964225075","https://openalex.org/W2990818246","https://openalex.org/W3009811369","https://openalex.org/W3010277541","https://openalex.org/W3034538190","https://openalex.org/W3034951775","https://openalex.org/W3035017890","https://openalex.org/W3035598501","https://openalex.org/W3090476579","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3097802466","https://openalex.org/W3106121867","https://openalex.org/W3107081247","https://openalex.org/W3109754877","https://openalex.org/W3109813419","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/W3195860412","https://openalex.org/W3197395033","https://openalex.org/W3212153990","https://openalex.org/W4288329833","https://openalex.org/W6632922691","https://openalex.org/W6757817989","https://openalex.org/W6763643401","https://openalex.org/W6785527955","https://openalex.org/W6799822930"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W3147584709","https://openalex.org/W2714992399","https://openalex.org/W2977677679","https://openalex.org/W2383812217"],"abstract_inverted_index":{"Transformer":[0,41],"model":[1],"has":[2,18],"been":[3],"successfully":[4],"applied":[5],"to":[6,44,64,75,101],"human-object":[7,91],"interaction":[8,55,70,107],"(HOI)":[9],"detection":[10,49,139],"in":[11,118],"a":[12,45,58,111],"one-stage":[13],"mode.":[14],"However,":[15],"this":[16,39],"mode":[17],"not":[19],"fully":[20],"leveraged":[21],"rich":[22],"and":[23,29,57,82,121,142],"valuable":[24],"clues":[25],"such":[26],"as":[27],"scenes":[28],"linguistics":[30],"etc,":[31],"thereby":[32],"weakening":[33],"the":[34,69,87,95,103,135],"Transformer\u2019s":[35],"representation":[36],"power.":[37],"In":[38,93],"paper,":[40],"is":[42,72,99],"introduced":[43],"novel":[46],"two-stage":[47],"HOI":[48,138],"framework,":[50],"named":[51],"MMFENet,":[52],"where":[53],"an":[54],"subnet":[56,61,71,98],"feature":[59,96],"enhancement":[60,97],"are":[62],"constructed":[63,74],"jointly":[65],"detect":[66],"HOIs.":[67],"Specifically,":[68],"firstly":[73],"effectively":[76],"fuse":[77],"visual":[78,120],"(or":[79],"semantic)":[80],"features":[81,108],"spatial":[83],"information,":[84],"thus":[85],"enhancing":[86],"relationships":[88],"of":[89,106,114],"all":[90],"pairs.":[92],"addition,":[94],"built":[100],"improve":[102],"contextual":[104],"comprehension":[105],"by":[109],"incorporating":[110],"diverse":[112],"range":[113],"scene":[115],"information":[116],"encoded":[117],"both":[119],"linguistic":[122],"modalities.":[123],"Extensive":[124],"experimental":[125],"results":[126,133],"show":[127],"that":[128],"MMFENet":[129],"achieves":[130],"very":[131],"competitive":[132],"on":[134],"two":[136],"public":[137],"benchmarks":[140],"(HICO-DET":[141],"V-COCO).":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}