{"id":"https://openalex.org/W7165201551","doi":"https://doi.org/10.5281/zenodo.20748838","title":"ADVE: Anchor-Delta Video Embedding for Efficient Semantic Scene Understanding","display_name":"ADVE: Anchor-Delta Video Embedding for Efficient Semantic Scene Understanding","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165201551","doi":"https://doi.org/10.5281/zenodo.20748838"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.20748838","doi":"https://doi.org/10.5281/zenodo.20748838","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20748838","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.20748838","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138543637","display_name":"Asmitha M","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"M, Asmitha","raw_affiliation_strings":["Independent Researcher, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher, Tamil Nadu, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5138543637"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.5586000084877014,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.5586000084877014,"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":0.1607999950647354,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.09459999948740005,"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/video-embedding","display_name":"video embedding","score":0.7670000195503235},{"id":"https://openalex.org/keywords/temporal-redundancy","display_name":"temporal redundancy","score":0.6650000214576721},{"id":"https://openalex.org/keywords/gpu-memory-reduction","display_name":"GPU memory reduction","score":0.6159999966621399},{"id":"https://openalex.org/keywords/real-time-inference","display_name":"real-time inference","score":0.843999981880188},{"id":"https://openalex.org/keywords/edge-deployment","display_name":"edge deployment","score":0.9470000267028809},{"id":"https://openalex.org/keywords/pedestrian-tracking","display_name":"pedestrian tracking","score":0.7490000128746033},{"id":"https://openalex.org/keywords/mot17","display_name":"MOT17","score":0.7860000133514404},{"id":"https://openalex.org/keywords/clip-embeddings","display_name":"CLIP embeddings","score":0.8209999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6639999747276306},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6474000215530396},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6262999773025513},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6067000031471252},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.5867999792098999},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5782999992370605},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.40149998664855957},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.39309999346733093},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3716000020503998},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.34389999508857727},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.25459998846054077},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.20748838","doi":"https://doi.org/10.5281/zenodo.20748838","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20748838","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.20748839","doi":"https://doi.org/10.5281/zenodo.20748839","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20748839","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.20748838","doi":"https://doi.org/10.5281/zenodo.20748838","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20748838","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"ADVE":[2,60,112],"(Anchor-Delta":[3],"Video":[4],"Embedding),":[5],"a":[6,23,100,154],"training-free":[7],"method":[8],"for":[9],"efficient":[10],"semantic":[11],"video":[12,38],"representation":[13],"that":[14],"reduces":[15],"vision":[16,47],"encoder":[17],"invocations":[18],"by":[19],"60.33\u201396.67%":[20],"while":[21],"maintaining":[22],"mean":[24,115],"cosine":[25,116,121],"similarity":[26,117],"of":[27,71],"0.9923":[28,114],"relative":[29,86],"to":[30,87],"ground-truth":[31],"CLIP":[32],"embeddings":[33,70],"on":[34,99,132,153,162],"real-world":[35],"video.":[36],"Current":[37],"understanding":[39],"systems":[40],"independently":[41],"encode":[42],"every":[43,133],"frame":[44],"through":[45],"expensive":[46],"encoders":[48],"such":[49],"as":[50],"CLIP,":[51],"ignoring":[52],"the":[53,69,105,123],"high":[54],"temporal":[55],"redundancy":[56],"between":[57],"consecutive":[58],"frames.":[59],"instead":[61],"encodes":[62],"only":[63],"anchor":[64],"frames":[65,75],"fully":[66],"and":[67,104,118],"approximates":[68],"all":[72],"subsequent":[73],"delta":[74],"using":[76],"spatial":[77],"graph":[78],"deltas\u2014compact":[79],"representations":[80],"measuring":[81],"how":[82],"detected":[83],"objects":[84],"moved":[85],"each":[88],"other.":[89],"The":[90],"core":[91],"approximation,":[92],"\u00ca(ft)":[93],"\u2248":[94],"f(Eanchor,":[95],"\u0394G(t)),":[96],"is":[97,148],"validated":[98],"controlled":[101],"synthetic":[102],"benchmark":[103],"MOT17":[106],"pedestrian":[107],"tracking":[108],"dataset.":[109],"On":[110],"MOT17,":[111],"achieves":[113],"0.9490":[119],"minimum":[120],"similarity\u2014outperforming":[122],"best":[124],"fixed-interval":[125],"baseline":[126],"(Keyframe-30:":[127],"0.9762":[128],"mean,":[129],"0.9054":[130],"minimum)":[131],"accuracy":[134],"metric\u2014while":[135],"consuming":[136],"65%":[137],"less":[138],"GPU":[139,156],"memory":[140],"(330":[141],"MB":[142],"vs.":[143],"950":[144],"MB).":[145],"Real-time":[146],"inference":[147],"demonstrated":[149],"at":[150],"53.5":[151],"FPS":[152],"consumer":[155],"(NVIDIA":[157],"RTX":[158],"4050),":[159],"enabling":[160],"deployment":[161],"edge":[163],"hardware":[164],"where":[165],"existing":[166],"methods":[167],"cannot":[168],"fit.":[169]},"counts_by_year":[],"updated_date":"2026-10-07T09:51:55.459714","created_date":"2026-06-19T00:00:00"}