{"id":"https://openalex.org/W7160236396","doi":"https://doi.org/10.1109/wacv61042.2026.00462","title":"Learning Unified Spatio-temporal Representations for Efficient Compressed Video Understanding","display_name":"Learning Unified Spatio-temporal Representations for Efficient Compressed Video Understanding","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160236396","doi":"https://doi.org/10.1109/wacv61042.2026.00462"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5134390653","display_name":"Shristi Das Biswas","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shristi Das Biswas","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031719209","display_name":"Efstathia Soufleri","orcid":"https://orcid.org/0000-0001-8699-9940"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Efstathia Soufleri","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043335223","display_name":"Arani Roy","orcid":"https://orcid.org/0000-0001-5826-3426"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arani Roy","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135410023","display_name":"Kaushik Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik Roy","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"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":"4755","last_page":"4765"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.31529998779296875,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.31529998779296875,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.20110000669956207,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.13040000200271606,"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/feature","display_name":"Feature (linguistics)","score":0.3118000030517578},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.2955999970436096},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.2919999957084656},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.2912999987602234},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.2768000066280365},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27059999108314514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6438999772071838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5076000094413757},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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":56,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1923404803","https://openalex.org/W1999085092","https://openalex.org/W2010356589","https://openalex.org/W2016053056","https://openalex.org/W2020163092","https://openalex.org/W2024868105","https://openalex.org/W2048812218","https://openalex.org/W2068611653","https://openalex.org/W2076964542","https://openalex.org/W2115907784","https://openalex.org/W2116386142","https://openalex.org/W2126579184","https://openalex.org/W2133099404","https://openalex.org/W2150066425","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2342662179","https://openalex.org/W2507009361","https://openalex.org/W2513853720","https://openalex.org/W2792496964","https://openalex.org/W2883429621","https://openalex.org/W2948048211","https://openalex.org/W2952773607","https://openalex.org/W2963370182","https://openalex.org/W2963524571","https://openalex.org/W2963901365","https://openalex.org/W2964191259","https://openalex.org/W2966081953","https://openalex.org/W2984844508","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2991873135","https://openalex.org/W2992813059","https://openalex.org/W3034572008","https://openalex.org/W3035697644","https://openalex.org/W3092083701","https://openalex.org/W3108241103","https://openalex.org/W3126721948","https://openalex.org/W3138516171","https://openalex.org/W3194397797","https://openalex.org/W4214516465","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4312349930","https://openalex.org/W4312560592","https://openalex.org/W4312658081","https://openalex.org/W4312769131","https://openalex.org/W4372348095","https://openalex.org/W4375868862","https://openalex.org/W4386057769","https://openalex.org/W4390872179","https://openalex.org/W4402716475","https://openalex.org/W4402753480","https://openalex.org/W4411245270","https://openalex.org/W7133215953"],"related_works":[],"abstract_inverted_index":{"Training":[0],"robust":[1],"deep":[2],"video":[3,21,38,100,206],"representations":[4,81,187],"has":[5],"proven":[6],"to":[7,12,131,151,164,171,183],"be":[8,244],"computationally":[9],"challenging":[10],"due":[11],"substantial":[13],"decoding":[14],"overheads,":[15],"the":[16,36,69,85,95,189,210],"enormous":[17],"size":[18],"of":[19,84,98,110],"raw":[20],"streams,":[22],"and":[23,40,48,52,72,90,216,223],"their":[24],"inherent":[25],"high":[26],"temporal":[27,70],"redundancy.":[28],"Different":[29],"from":[30,188],"existing":[31],"schemes,":[32],"operating":[33],"exclusively":[34],"in":[35,200],"compressed":[37],"domain":[39],"exploiting":[41],"all":[42],"freely":[43],"available":[44],"modalities,":[45],"i.e.,":[46],"I-frames,":[47],"P-frames":[49,76],"(motion":[50],"vectors":[51],"residuals)":[53],"offers":[54],"a":[55,64,108,120,141,160,179,201],"compute-efficient":[56],"alternative.":[57],"Existing":[58],"methods":[59],"approach":[60],"this":[61],"task":[62],"as":[63],"naive":[65],"multi-modality":[66],"problem,":[67],"ignoring":[68],"correlation":[71],"implicit":[73],"sparsity":[74],"across":[75,127],"for":[77,82,237],"modeling":[78],"stronger":[79],"shared":[80],"videos":[83],"same":[86],"action,":[87],"making":[88],"training":[89],"generalization":[91],"easier.":[92],"By":[93],"revisiting":[94],"high-level":[96],"design":[97,235],"dominant":[99],"understanding":[101],"backbones,":[102],"we":[103,118],"increase":[104],"inference":[105,133,225],"speed":[106],"by":[107,135],"factor":[109],"56":[111],"while":[112,154],"retaining":[113,155],"similar":[114],"performance.":[115],"For":[116],"this,":[117],"propose":[119],"hybrid":[121],"end-to-end":[122],"framework":[123],"that":[124,196],"factorizes":[125],"learning":[126],"three":[128],"key":[129],"concepts":[130],"reduce":[132],"cost":[134],"113\u00d7":[136],"versus":[137],"prior":[138],"art:":[139],"First,":[140],"specially":[142],"designed":[143],"dual-encoder":[144],"scheme":[145],"with":[146,219],"efficient":[147,238],"Spiking":[148],"Temporal":[149],"Modulators":[150],"minimize":[152],"latency":[153],"cross-domain":[156],"feature":[157],"aggregation.":[158],"Second,":[159],"unified":[161],"transformer":[162],"model":[163,184],"capture":[165],"inter-modal":[166],"dependencies":[167],"using":[168],"global":[169],"self-attention":[170],"enhance":[172],"I-frame":[173],"\u2013":[174],"P-frame":[175],"contextual":[176],"interactions.":[177],"Third,":[178],"Multi-Modal":[180],"Mixer":[181],"Block":[182],"rich":[185],"hierarchical":[186],"joint":[190],"spatiotemporal":[191,240],"token":[192],"embeddings.":[193],"Experiments":[194],"show":[195],"our":[197,228],"method":[198],"results":[199],"lightweight":[202],"architecture":[203],"achieving":[204],"state-of-the-art":[205],"recognition":[207],"performance":[208],"on":[209],"popular":[211],"UCF-101,":[212],"HMDB-51,":[213],"K-400,":[214],"K-600":[215],"SS-v2":[217],"benchmarks":[218],"favorable":[220],"costs":[221],"(0.73J/V)":[222],"fast":[224],"(16V/s).":[226],"Further,":[227],"observations":[229],"bring":[230],"new":[231],"insights":[232],"into":[233],"practical":[234],"choices":[236],"next-generation":[239],"learners.":[241],"Code":[242],"will":[243],"released":[245],"upon":[246],"publication.":[247]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}