{"id":"https://openalex.org/W7131272263","doi":"https://doi.org/10.1109/vcip67698.2025.11396912","title":"PITR-Select: Partial Image Token Reduction via Temporal Selection for Efficient Video Understanding on Edge","display_name":"PITR-Select: Partial Image Token Reduction via Temporal Selection for Efficient Video Understanding on Edge","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7131272263","doi":"https://doi.org/10.1109/vcip67698.2025.11396912"},"language":null,"primary_location":{"id":"doi:10.1109/vcip67698.2025.11396912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","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/A5126666264","display_name":"Fadoua Ghourabi","orcid":null},"institutions":[{"id":"https://openalex.org/I76078494","display_name":"Japan College of Social Work","ror":"https://ror.org/04whwem28","country_code":"JP","type":"education","lineage":["https://openalex.org/I76078494"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fadoua Ghourabi","raw_affiliation_strings":["AWL, Inc.,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWL, Inc.,Tokyo,Japan","institution_ids":["https://openalex.org/I76078494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126685261","display_name":"Kittinun Aukkapinyo","orcid":null},"institutions":[{"id":"https://openalex.org/I76078494","display_name":"Japan College of Social Work","ror":"https://ror.org/04whwem28","country_code":"JP","type":"education","lineage":["https://openalex.org/I76078494"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kittinun Aukkapinyo","raw_affiliation_strings":["AWL, Inc.,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWL, Inc.,Tokyo,Japan","institution_ids":["https://openalex.org/I76078494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126672983","display_name":"Hiroshi Fujimura","orcid":null},"institutions":[{"id":"https://openalex.org/I76078494","display_name":"Japan College of Social Work","ror":"https://ror.org/04whwem28","country_code":"JP","type":"education","lineage":["https://openalex.org/I76078494"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Fujimura","raw_affiliation_strings":["AWL, Inc.,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWL, Inc.,Tokyo,Japan","institution_ids":["https://openalex.org/I76078494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126722450","display_name":"Kriti Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I76078494","display_name":"Japan College of Social Work","ror":"https://ror.org/04whwem28","country_code":"JP","type":"education","lineage":["https://openalex.org/I76078494"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kriti Agarwal","raw_affiliation_strings":["AWL, Inc.,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWL, Inc.,Tokyo,Japan","institution_ids":["https://openalex.org/I76078494"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126745009","display_name":"Wasu Wasusatein","orcid":null},"institutions":[{"id":"https://openalex.org/I76078494","display_name":"Japan College of Social Work","ror":"https://ror.org/04whwem28","country_code":"JP","type":"education","lineage":["https://openalex.org/I76078494"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wasu Wasusatein","raw_affiliation_strings":["AWL, Inc.,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWL, Inc.,Tokyo,Japan","institution_ids":["https://openalex.org/I76078494"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76078494"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66368453,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7971000075340271,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7971000075340271,"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":0.05460000038146973,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.04230000078678131,"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/frame","display_name":"Frame (networking)","score":0.6766999959945679},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5928000211715698},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5383999943733215},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5117999911308289},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.5083000063896179},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.48030000925064087},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.46059998869895935},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43320000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531999945640564},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6875},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6766999959945679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6381999850273132},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5117999911308289},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.5083000063896179},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.400299996137619},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3312000036239624},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C2988454689","wikidata":"https://www.wikidata.org/wiki/Q173131","display_name":"Digital video","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.2612999975681305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip67698.2025.11396912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2897811261","https://openalex.org/W3175961224","https://openalex.org/W4293773179","https://openalex.org/W4394625561","https://openalex.org/W4402753874","https://openalex.org/W4403886626","https://openalex.org/W4405429615","https://openalex.org/W4409262204","https://openalex.org/W4411447392","https://openalex.org/W4413144805","https://openalex.org/W4413147303","https://openalex.org/W4413147844","https://openalex.org/W4413278083"],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"demonstrated":[4],"powerful":[5],"capabilities":[6],"in":[7],"video":[8,34,53,84],"understanding,":[9],"but":[10],"their":[11],"high":[12],"computational":[13],"cost":[14],"makes":[15],"real-time":[16,29,92],"deployment":[17],"on":[18,36,86,94,116],"edge":[19,37,96],"devices":[20],"challenging.":[21],"Our":[22],"research":[23],"target":[24],"is":[25],"to":[26,55,79,101,107],"achieve":[27],"the":[28,41,61],"processing":[30,75,93],"of":[31,43,68],"VLM":[32,62,67,74],"for":[33,81],"understanding":[35],"devices.":[38],"We":[39],"introduce":[40],"method":[42,72],"partial":[44],"frame":[45,126],"token":[46],"reduction":[47],"that":[48,59],"selects":[49],"temporal":[50],"clues":[51],"from":[52,77],"frames":[54],"construct":[56],"localized":[57],"prompts":[58],"guide":[60],"attention.":[63],"Using":[64],"a":[65,82,108],"lightweight":[66],"SmolVLM":[69],"0.5B,":[70],"our":[71],"reduces":[73],"time":[76],"840.56s":[78],"149.48s":[80],"302s":[83],"dataset":[85],"Jetson":[87],"Orin":[88],"AGX.":[89],"This":[90],"enables":[91],"an":[95,123],"device,":[97],"with":[98],"only":[99],"7.75":[100],"10.12":[102],"points":[103],"accuracy":[104],"drop":[105],"comparing":[106],"14":[109],"times":[110],"heavier":[111],"baseline":[112],"model":[113],"(LLaVA-1.6":[114],"7B)":[115],"NExt-QA":[117],"and":[118,121],"STAR-QA":[119],"benchmarks,":[120],"despite":[122],"aggressive":[124],"80%":[125],"reduction.":[127]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-25T00:00:00"}