{"id":"https://openalex.org/W7136796678","doi":"https://doi.org/10.1109/ants66931.2025.11430018","title":"VisionStack: Multi-Layered Object Detection and Classification Framework","display_name":"VisionStack: Multi-Layered Object Detection and Classification Framework","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7136796678","doi":"https://doi.org/10.1109/ants66931.2025.11430018"},"language":null,"primary_location":{"id":"doi:10.1109/ants66931.2025.11430018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ants66931.2025.11430018","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 Advanced Networks and Telecommunications Systems (ANTS)","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/A5129609766","display_name":"Akhil Kumar Tiwari","orcid":null},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Akhil Kumar Tiwari","raw_affiliation_strings":["Indian Institute of Technology,Department of Computer Science and Engineering,Patna,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Department of Computer Science and Engineering,Patna,India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129505707","display_name":"Prince Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prince Kumar","raw_affiliation_strings":["Indian Institute of Technology,Department of Computer Science and Engineering,Patna,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Department of Computer Science and Engineering,Patna,India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025858723","display_name":"Arijit Bardhan Roy","orcid":"https://orcid.org/0000-0002-5246-5825"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arijit Roy","raw_affiliation_strings":["Indian Institute of Technology,Department of Computer Science and Engineering,Patna,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Department of Computer Science and Engineering,Patna,India","institution_ids":["https://openalex.org/I132153292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5129609766"],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76245038,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.17239999771118164,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.17239999771118164,"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":0.08110000193119049,"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":0.06750000268220901,"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":0.5230000019073486},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40880000591278076},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3939000070095062},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.34060001373291016},{"id":"https://openalex.org/keywords/viola\u2013jones-object-detection-framework","display_name":"Viola\u2013Jones object detection framework","score":0.33980000019073486},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32760000228881836}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.631600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5637000203132629},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5533999800682068},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5230000019073486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.34060001373291016},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.33980000019073486},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.3052000105381012},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.3043999969959259},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.2833999991416931},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27079999446868896}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ants66931.2025.11430018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ants66931.2025.11430018","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 Advanced Networks and Telecommunications Systems (ANTS)","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":12,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W1536680647","https://openalex.org/W2161969291","https://openalex.org/W2164598857","https://openalex.org/W2193145675","https://openalex.org/W2194011657","https://openalex.org/W2567210518","https://openalex.org/W2780740184","https://openalex.org/W2963037989","https://openalex.org/W2963122961","https://openalex.org/W2969985801","https://openalex.org/W4399468713"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"object":[1],"detection":[2,27,64,84,126,145],"and":[3,29,35,47,65,92,118,127,150,171,187],"subclass":[4,76],"classification":[5,128,152],"are":[6],"essential":[7],"in":[8,13,45,89,125,179],"computer":[9],"vision":[10],"applications,":[11],"particularly":[12],"environments":[14],"constrained":[15],"by":[16,167],"limited":[17,115],"annotated":[18],"data.":[19],"However,":[20],"existing":[21,140,160],"methods":[22],"often":[23],"struggle":[24],"to":[25,86,97,109],"balance":[26],"speed":[28],"accuracy,":[30],"requiring":[31],"extensive":[32],"computational":[33,119,165],"resources":[34],"large":[36],"amounts":[37],"of":[38,114,148,154],"labeled":[39],"data,":[40],"which":[41],"limits":[42],"their":[43],"applicability":[44],"real-time":[46,83],"resource-constrained":[48,180],"environments.":[49],"This":[50,104],"paper":[51],"proposes":[52],"VisionStack,":[53],"a":[54,144,151],"novel":[55],"multi-layered":[56],"framework":[57,80],"that":[58,137],"integrates":[59],"YOLOv8":[60],"for":[61,74,177],"efficient":[62],"parent-class":[63],"EfficientNet":[66,96],"enhanced":[67],"with":[68],"an":[69],"Additive":[70],"Angular":[71],"Margin":[72],"Loss":[73],"fine-grained":[75],"classification.":[77],"The":[78],"VisionStack":[79,108,138,163],"leverages":[81],"YOLOv8\u2019s":[82],"capability":[85],"identify":[87],"objects":[88],"broad":[90],"categories":[91],"applies":[93],"the":[94,112],"modified":[95],"refine":[98],"these":[99],"detections":[100],"into":[101],"specific":[102],"subclasses.":[103],"hierarchical":[105],"structure":[106],"enables":[107],"effectively":[110],"address":[111],"challenges":[113],"data":[116],"availability":[117],"constraints":[120],"while":[121],"maintaining":[122],"high":[123],"accuracy":[124,153],"tasks.":[129],"Experimental":[130],"results":[131],"on":[132],"standard":[133],"benchmark":[134],"datasets":[135],"demonstrate":[136],"outperforms":[139],"state-of-the-art":[141],"models,":[142],"achieving":[143],"precision":[146],"(mAP)":[147],"85.2%":[149],"92.5%,":[155],"representing":[156],"significant":[157],"improvements":[158],"over":[159],"models.":[161],"Additionally,":[162],"reduces":[164],"overhead":[166],"incorporating":[168],"model":[169],"pruning":[170],"quantization":[172],"techniques,":[173],"making":[174],"it":[175],"suitable":[176],"deployment":[178],"environments,":[181],"such":[182],"as":[183],"autonomous":[184],"systems,":[185],"surveillance,":[186],"defense":[188],"operations.":[189]},"counts_by_year":[],"updated_date":"2026-03-18T06:27:02.140700","created_date":"2026-03-17T00:00:00"}