{"id":"https://openalex.org/W4392903083","doi":"https://doi.org/10.1109/icassp48485.2024.10447826","title":"Proposal Distillation of Multi-Modal Feature Aggregation Network for Video Object Detection","display_name":"Proposal Distillation of Multi-Modal Feature Aggregation Network for Video Object Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903083","doi":"https://doi.org/10.1109/icassp48485.2024.10447826"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5018426248","display_name":"Zhenyu Qiu","orcid":"https://orcid.org/0000-0002-1679-7750"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Qiu","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072002612","display_name":"Qiang Qi","orcid":"https://orcid.org/0000-0002-9127-3404"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Qi","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015745132","display_name":"Yang Lu","orcid":"https://orcid.org/0000-0002-3497-9611"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Lu","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395059","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044594971","display_name":"Hanzi Wang","orcid":"https://orcid.org/0000-0002-6913-9786"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanzi Wang","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3895","last_page":"3899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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":0.9983000159263611,"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":0.7963913083076477},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6360048055648804},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5867164134979248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.57682204246521},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.565718412399292},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5645418763160706},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5603922009468079},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.49959897994995117},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4906567633152008},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.46915924549102783},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4506911039352417},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4455559253692627},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43104174733161926},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4244045317173004},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37272951006889343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7963913083076477},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6360048055648804},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5867164134979248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.57682204246521},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.565718412399292},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5645418763160706},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5603922009468079},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.49959897994995117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4906567633152008},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.46915924549102783},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4506911039352417},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4455559253692627},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43104174733161926},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4244045317173004},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37272951006889343},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/icassp48485.2024.10447826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W1755205674","https://openalex.org/W2117539524","https://openalex.org/W2336589871","https://openalex.org/W2552900565","https://openalex.org/W2898044248","https://openalex.org/W2964286567","https://openalex.org/W2994810768","https://openalex.org/W2996794639","https://openalex.org/W3016072980","https://openalex.org/W3034467781","https://openalex.org/W3103358580","https://openalex.org/W3166089996","https://openalex.org/W3206836360","https://openalex.org/W4224932082","https://openalex.org/W4283795993","https://openalex.org/W4285203457","https://openalex.org/W4293437100","https://openalex.org/W4293584584","https://openalex.org/W4383899713","https://openalex.org/W6620707391","https://openalex.org/W6684515133","https://openalex.org/W6695799263","https://openalex.org/W6750227808"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2963610131","https://openalex.org/W2894651257","https://openalex.org/W3200590620","https://openalex.org/W4200172193","https://openalex.org/W4303926741"],"abstract_inverted_index":{"Video":[0],"object":[1,10],"detection":[2,40,150],"is":[3,21,88,133],"a":[4,49,70,82,100,127,143,160],"challenging":[5],"task":[6],"due":[7],"to":[8,14,22,90,105,113],"deteriorated":[9],"appearances.":[11],"In":[12],"order":[13],"bolster":[15],"per-frame":[16],"feature":[17,35,55,64,79,125,145],"representations,":[18],"one":[19],"way":[20],"aggregate":[23],"features":[24,94,97],"from":[25],"relevant":[26],"frames.":[27],"However,":[28],"relying":[29],"exclusively":[30],"on":[31,163],"RGB":[32],"modal":[33],"for":[34,42],"aggregation":[36,56,130],"may":[37],"limit":[38],"the":[39,63,115,137,149,156,164],"performance":[41],"lacking":[43],"of":[44,53,117],"motion":[45],"robustness.":[46],"We":[47],"propose":[48],"novel":[50],"proposal":[51,128],"distillation":[52],"multi-modal":[54,123],"network":[57],"(PDMAN).":[58],"Specially,":[59],"it":[60],"initially":[61],"aligns":[62],"domain":[65,68],"and":[66,75,98,119],"flow":[67,72],"via":[69],"lightweight":[71],"module":[73,86,131],"(LFM)":[74],"then":[76],"facilities":[77],"frame-level":[78],"aggregation.":[80],"Subsequently,":[81],"global-based":[83],"semantic":[84,93],"embedding":[85],"(GSEM)":[87],"designed":[89],"incorporate":[91],"global":[92,101],"into":[95],"instance":[96,138],"introduce":[99],"multi-label":[102],"classification":[103],"loss":[104],"guide":[106],"encoding":[107],"with":[108],"high":[109],"class-wise":[110],"responsiveness.":[111],"Finally,":[112],"alleviate":[114],"presence":[116],"insufficient":[118],"redundant":[120],"information":[121],"in":[122],"instance-level":[124],"aggregation,":[126,146],"distilled":[129],"(PDAM)":[132],"employed.":[134],"By":[135],"distilling":[136],"set,":[139],"this":[140],"approach":[141],"realizes":[142],"fine-grained":[144],"ultimately":[147],"boosting":[148],"performance.":[151],"Experimental":[152],"results":[153],"demonstrate":[154],"that":[155],"proposed":[157],"PDMAN":[158],"achieves":[159],"favorable":[161],"result":[162],"most":[165],"representative":[166],"large-scale":[167],"ImageNet":[168],"VID":[169],"dataset.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}