{"id":"https://openalex.org/W7129523147","doi":"https://doi.org/10.1109/icipw68931.2025.11386241","title":"Ma-Yolo: Video Object Detection Via Motion-Assisted Yolo","display_name":"Ma-Yolo: Video Object Detection Via Motion-Assisted Yolo","publication_year":2025,"publication_date":"2025-09-14","ids":{"openalex":"https://openalex.org/W7129523147","doi":"https://doi.org/10.1109/icipw68931.2025.11386241"},"language":null,"primary_location":{"id":"doi:10.1109/icipw68931.2025.11386241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11386241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing Workshops (ICIPW)","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/A5100352780","display_name":"Xinyu Wang","orcid":"https://orcid.org/0000-0002-0151-9133"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinyu Wang","raw_affiliation_strings":["University of Southern California,Los Angeles,California,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,California,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019897543","display_name":"Hong-Shuo Chen","orcid":"https://orcid.org/0009-0006-7071-0237"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong-Shuo Chen","raw_affiliation_strings":["University of Southern California,Los Angeles,California,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,California,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009667712","display_name":"Zhiruo Zhou","orcid":"https://orcid.org/0000-0002-3303-9185"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiruo Zhou","raw_affiliation_strings":["University of Southern California,Los Angeles,California,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,California,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063106174","display_name":"Jie-En Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie-En Yao","raw_affiliation_strings":["University of Southern California,Los Angeles,California,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,California,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055084059","display_name":"C. Jay Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.-C. Jay Kuo","raw_affiliation_strings":["University of Southern California,Los Angeles,California,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,California,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100352780"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74062131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"440","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.48399999737739563,"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":0.48399999737739563,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.12960000336170197,"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/T11448","display_name":"Face recognition and analysis","score":0.0640999972820282,"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/object-detection","display_name":"Object detection","score":0.7096999883651733},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.583899974822998},{"id":"https://openalex.org/keywords/motion-detection","display_name":"Motion detection","score":0.5174000263214111},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4927000105381012},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4560000002384186},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4528000056743622},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44179999828338623},{"id":"https://openalex.org/keywords/edge-detection","display_name":"Edge detection","score":0.4106000065803528},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4072999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826200008392334},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7800999879837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7348999977111816},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7096999883651733},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.5174000263214111},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.4106000065803528},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.38429999351501465},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.3142000138759613},{"id":"https://openalex.org/C2779020251","wikidata":"https://www.wikidata.org/wiki/Q3555171","display_name":"Motion vector","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.2800999879837036},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icipw68931.2025.11386241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11386241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing Workshops (ICIPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4218640625476837}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2336589871","https://openalex.org/W2552900565","https://openalex.org/W2555618208","https://openalex.org/W2570343428","https://openalex.org/W2793130599","https://openalex.org/W2891336752","https://openalex.org/W2893538180","https://openalex.org/W2953099022","https://openalex.org/W2962855257","https://openalex.org/W2963037989","https://openalex.org/W2963653352","https://openalex.org/W2963795951","https://openalex.org/W2964286567","https://openalex.org/W2989883318","https://openalex.org/W2994810768","https://openalex.org/W3164864928","https://openalex.org/W3194397797","https://openalex.org/W4382775073","https://openalex.org/W4386076325"],"related_works":[],"abstract_inverted_index":{"Video":[0],"object":[1],"detection":[2,32,78,121],"(VOD)":[3],"is":[4],"vital":[5],"in":[6,28],"edge":[7,66],"intelligence":[8],"applications":[9],"such":[10,22,46],"as":[11,23],"surveillance,":[12],"autonomous":[13],"systems,":[14],"and":[15,40,83,100,147],"wearable":[16],"devices.":[17],"Although":[18],"high-performance":[19],"still-image":[20],"detectors":[21],"YOLO":[24,77],"are":[25],"commonly":[26],"employed":[27],"VOD":[29,62],"tasks,":[30],"applying":[31],"to":[33,87,114,126],"every":[34,72],"video":[35,152],"frame":[36],"has":[37],"redundant":[38],"computation":[39],"a":[41,47,60,108,145],"higher":[42],"energy":[43],"cost,":[44],"making":[45],"solution":[48,149],"less":[49],"attractive":[50],"for":[51,65,150],"resource-constrained":[52],"platforms.":[53],"This":[54],"paper":[55],"proposes":[56],"MA-YOLO":[57,74,136],"(Motion-Assisted":[58],"YOLO),":[59],"lightweight":[61],"framework":[63],"tailored":[64,113],"environments.":[67],"Instead":[68],"of":[69],"inferring":[70],"on":[71,80,129],"frame,":[73],"executes":[75],"complete":[76],"only":[79],"sparse":[81],"keyframes":[82,125],"propagates":[84],"the":[85,124,130],"results":[86],"intermediate":[88],"frames":[89],"using":[90],"motion":[91,98],"information":[92],"derived":[93],"from":[94,103,123],"precomputed":[95],"H.":[96],"264":[97],"vectors":[99],"geometric":[101,116],"offsets":[102],"reference":[104],"detections.":[105],"We":[106],"introduce":[107],"lightweight,":[109],"XGBoost-based":[110],"decision":[111],"module":[112],"each":[115],"offset":[117],"regression,":[118],"realizing":[119],"efficient":[120,148],"propagation":[122],"non-keyframes.":[127],"Experiments":[128],"ImageNet":[131],"VID":[132],"dataset":[133],"demonstrate":[134],"that":[135],"reduces":[137],"inference":[138],"cost":[139],"while":[140],"maintaining":[141],"competitive":[142],"accuracy,":[143],"offering":[144],"practical":[146],"edge-based":[151],"analysis.":[153]},"counts_by_year":[],"updated_date":"2026-02-19T06:27:42.648592","created_date":"2026-02-18T00:00:00"}