{"id":"https://openalex.org/W4416251424","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229177","title":"Conceptualizing Multi-scale Wavelet Attention and Ray-based Encoding for Human-Object Interaction Detection","display_name":"Conceptualizing Multi-scale Wavelet Attention and Ray-based Encoding for Human-Object Interaction Detection","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251424","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229177"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5119896860","display_name":"Quan Bi Pay","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":true,"raw_author_name":"Quan Bi Pay","raw_affiliation_strings":["Monash University,School of Information Technology,Malaysia"],"affiliations":[{"raw_affiliation_string":"Monash University,School of Information Technology,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,School of Information Technology,Malaysia"],"affiliations":[{"raw_affiliation_string":"Monash University,School of Information Technology,Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045821623","display_name":"Junn Yong Loo","orcid":"https://orcid.org/0000-0001-9370-600X"},"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":"Junn Yong Loo","raw_affiliation_strings":["Monash University,School of Information Technology,Malaysia"],"affiliations":[{"raw_affiliation_string":"Monash University,School of Information Technology,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,School of Information Technology,Malaysia"],"affiliations":[{"raw_affiliation_string":"Monash University,School of Information Technology,Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077539496","display_name":"Simon See","orcid":"https://orcid.org/0000-0002-4958-9237"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon See","raw_affiliation_strings":["NVIDIA AI Technology Center"],"affiliations":[{"raw_affiliation_string":"NVIDIA AI Technology Center","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5119896860"],"corresponding_institution_ids":["https://openalex.org/I11662577"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34492845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7286999821662903,"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":0.7286999821662903,"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":0.10740000009536743,"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":0.05939999967813492,"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/discriminative-model","display_name":"Discriminative model","score":0.7786999940872192},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6571999788284302},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6248999834060669},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5996999740600586},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5968000292778015},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5530999898910522},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42410001158714294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37929999828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883999943733215},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7786999940872192},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6571999788284302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6254000067710876},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6248999834060669},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5996999740600586},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42410001158714294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3788999915122986},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320971","display_name":"Monash University","ror":"https://ror.org/02bfwt286"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2776107444","https://openalex.org/W2888096830","https://openalex.org/W2953303875","https://openalex.org/W2962858109","https://openalex.org/W2963037989","https://openalex.org/W2963598268","https://openalex.org/W2964087130","https://openalex.org/W3025199923","https://openalex.org/W3043680005","https://openalex.org/W3046768359","https://openalex.org/W3092829565","https://openalex.org/W3096609285","https://openalex.org/W3106121867","https://openalex.org/W3109754877","https://openalex.org/W3138516171","https://openalex.org/W3151099711","https://openalex.org/W3168488421","https://openalex.org/W3199716252","https://openalex.org/W3204052007","https://openalex.org/W3213003795","https://openalex.org/W4205564931","https://openalex.org/W4312443924","https://openalex.org/W4312574495","https://openalex.org/W4319998180","https://openalex.org/W4362714880","https://openalex.org/W4385245566","https://openalex.org/W4386065823","https://openalex.org/W4386072519","https://openalex.org/W4388579521","https://openalex.org/W4396918399","https://openalex.org/W4402351863"],"related_works":[],"abstract_inverted_index":{"Human-object":[0],"interaction":[1],"(HOI)":[2],"detection":[3],"is":[4,157],"essential":[5],"for":[6,63,136],"accurately":[7],"localizing":[8],"and":[9,14,43,56,83,110,146],"characterizing":[10],"interactions":[11,75,85],"between":[12],"humans":[13],"objects,":[15],"providing":[16],"a":[17,52,57,115],"comprehensive":[18],"understanding":[19],"of":[20,72,102,108,117,122,134,151],"complex":[21],"visual":[22],"scenes":[23],"across":[24],"various":[25],"domains.":[26],"However,":[27],"existing":[28],"HOI":[29,64],"detectors":[30],"often":[31],"struggle":[32],"to":[33],"deliver":[34],"reliable":[35],"predictions":[36],"efficiently,":[37],"relying":[38],"on":[39,105,141],"resource-intensive":[40],"training":[41],"methods":[42],"inefficient":[44],"architectures.":[45],"To":[46],"address":[47],"these":[48],"challenges,":[49],"we":[50],"conceptualize":[51],"wavelet":[53,67],"attention-like":[54],"backbone":[55,68],"novel":[58],"ray-based":[59,93],"encoder":[60,94],"architecture":[61],"tailored":[62],"detection.":[65],"Our":[66],"addresses":[69],"the":[70,81,92,100,103,119,149],"limitations":[71],"expressing":[73],"middle-order":[74],"by":[76,98],"aggregating":[77],"discriminative":[78],"features":[79],"from":[80,87],"low-":[82],"high-order":[84],"extracted":[86],"diverse":[88],"convolutional":[89],"filters.":[90],"Concurrently,":[91],"facilitates":[95],"multi-scale":[96],"attention":[97],"optimizing":[99],"focus":[101],"decoder":[104,127],"relevant":[106],"regions":[107,133],"interest":[109,135],"mitigating":[111],"computational":[112],"overhead.":[113],"As":[114],"result":[116],"harnessing":[118],"attenuated":[120],"intensity":[121],"learnable":[123],"ray":[124],"origins,":[125],"our":[126,152],"aligns":[128],"query":[129],"embeddings":[130],"with":[131],"emphasized":[132],"accurate":[137],"predictions.":[138],"Experimental":[139],"results":[140],"benchmark":[142],"datasets,":[143],"including":[144],"ImageNet":[145],"HICO-DET,":[147],"showcase":[148],"potential":[150],"proposed":[153],"architecture.":[154],"The":[155],"code":[156],"publicly":[158],"available":[159],"at":[160],"[https://github.com/henrypay/RayEncoder].":[161]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}