{"id":"https://openalex.org/W4402915774","doi":"https://doi.org/10.1109/icip51287.2024.10647455","title":"Efficient Visual Question Answering on Embedded Devices: Cross-Modality Attention With Evolutionary Quantization","display_name":"Efficient Visual Question Answering on Embedded Devices: Cross-Modality Attention With Evolutionary Quantization","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915774","doi":"https://doi.org/10.1109/icip51287.2024.10647455"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647455","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","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/A5009532727","display_name":"Aakansha Mishra","orcid":"https://orcid.org/0000-0002-0792-3006"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aakansha Mishra","raw_affiliation_strings":["Samsung Research Institute,Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111343879","display_name":"Aditya Agarwala","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Agarwala","raw_affiliation_strings":["Samsung Research Institute,Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079533117","display_name":"Utsav P. Tiwari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Utsav Tiwari","raw_affiliation_strings":["Samsung Research Institute,Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079783021","display_name":"Vikram N Rajendiran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vikram N Rajendiran","raw_affiliation_strings":["Samsung Research Institute,Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057645083","display_name":"Srinivas Soumitri Miriyala","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Srinivas S Miriyala","raw_affiliation_strings":["Samsung Research Institute,Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009532727"],"corresponding_institution_ids":["https://openalex.org/I4210139030"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54107977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"28","issue":null,"first_page":"2142","last_page":"2148"},"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":0.9993000030517578,"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":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9876000285148621,"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/computer-science","display_name":"Computer science","score":0.6397109627723694},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6242890357971191},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5590683817863464},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5234907865524292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42850008606910706},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.41054001450538635},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2525095045566559},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.17621278762817383},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.147219717502594},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.11588165163993835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6397109627723694},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6242890357971191},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5590683817863464},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5234907865524292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42850008606910706},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.41054001450538635},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2525095045566559},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.17621278762817383},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.147219717502594},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.11588165163993835}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647455","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2250539671","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2963191264","https://openalex.org/W2963656855","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2970231061","https://openalex.org/W3002557610","https://openalex.org/W3034594935","https://openalex.org/W3090449556","https://openalex.org/W3202028501","https://openalex.org/W4225791300","https://openalex.org/W4226109952","https://openalex.org/W4238076109","https://openalex.org/W4284892042","https://openalex.org/W4327808595","https://openalex.org/W4328120750","https://openalex.org/W4366978765","https://openalex.org/W4382463788","https://openalex.org/W4385376328","https://openalex.org/W4386065596","https://openalex.org/W4386076140","https://openalex.org/W4389518864","https://openalex.org/W4390356856","https://openalex.org/W4401515857","https://openalex.org/W6620707391","https://openalex.org/W6736769356","https://openalex.org/W6739901393","https://openalex.org/W6748581942","https://openalex.org/W6796815506","https://openalex.org/W6849177959","https://openalex.org/W6857125280","https://openalex.org/W6863799804"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W2385859805"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"lies":[4],"at":[5],"the":[6,20,29,47,62,72,107,111,120,155,164,167],"intersection":[7],"of":[8,71,110,134,166],"vision":[9],"and":[10,144],"language":[11],"domains":[12],"necessitating":[13],"learning":[14],"representations":[15],"from":[16,172],"multiple":[17],"modalities.":[18],"While":[19],"model":[21,64,74,113,126,174],"development":[22,175],"for":[23,31,58,77,84,127],"VQA":[24,59,73,112,128,173],"has":[25],"witnessed":[26],"tremendous":[27],"growth,":[28],"efforts":[30],"its":[32,41,151,177],"deployment":[33,79,153],"on":[34,61,154],"embedded":[35],"devices":[36],"have":[37],"been":[38],"lagging":[39],"limiting":[40],"true":[42],"potential.":[43],"In":[44],"this":[45,50],"work,":[46],"authors":[48],"address":[49],"challenge":[51],"by":[52],"designing":[53],"a":[54,81,91,130],"novel":[55],"hardware-friendly":[56],"architecture":[57],"based":[60],"transformer":[63],"with":[65,114,129],"cross-modality":[66],"attention.":[67],"The":[68,96,124,160],"memory":[69,142],"footprint":[70],"is":[75,99],"optimized":[76],"on-device":[78],"using":[80,101],"distributed":[82],"framework":[83],"Post":[85],"Training":[86],"Quantization":[87],"(PTQ)":[88],"formulated":[89],"as":[90],"Non-Linear":[92],"Programming":[93],"(NLP)":[94],"problem.":[95],"NLP":[97],"problem":[98],"solved":[100],"an":[102],"Evolutionary":[103],"algorithm":[104],"to":[105,119,176],"determine":[106],"low-bit":[108],"representation":[109],"minimal":[115],"accuracy":[116,132],"drop":[117,133],"compared":[118],"full":[121],"precision":[122],"model.":[123],"quantized":[125],"marginal":[131],"less":[135],"than":[136],"2%,":[137],"resulted":[138],"in":[139],"4":[140],"times":[141,147],"improvement,":[143,149],"over":[145],"2":[146],"latency":[148],"enabling":[150],"successful":[152],"Samsung":[156],"Galaxy":[157],"S23":[158],"device.":[159],"comprehensive":[161],"study":[162],"explores":[163],"potential":[165],"proposed":[168],"generic":[169],"end-to-end":[170],"pipeline":[171],"deployment.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}