{"id":"https://openalex.org/W4392910009","doi":"https://doi.org/10.1109/icassp48485.2024.10446442","title":"Differentiable Resolution Compression and Alignment for Efficient Video Classification and Retrieval","display_name":"Differentiable Resolution Compression and Alignment for Efficient Video Classification and Retrieval","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910009","doi":"https://doi.org/10.1109/icassp48485.2024.10446442"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5006470125","display_name":"Rui Deng","orcid":"https://orcid.org/0000-0002-6666-9095"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Deng","raw_affiliation_strings":["NetEase Yidun AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109996614","display_name":"Qian Wu","orcid":"https://orcid.org/0009-0006-2491-0035"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Wu","raw_affiliation_strings":["NetEase Yidun AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697195","display_name":"Yuke Li","orcid":"https://orcid.org/0000-0001-9204-9239"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Li","raw_affiliation_strings":["NetEase Yidun AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048813984","display_name":"Haoran Fu","orcid":"https://orcid.org/0000-0002-5400-3042"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Fu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.655,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66898072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3200","last_page":"3204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9955999851226807,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9955999851226807,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9926000237464905,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.991100013256073,"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":0.7101077437400818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6086894273757935},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5538396835327148},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5387211441993713},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5254912972450256},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48963767290115356},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.44869449734687805},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.4271901845932007},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41003215312957764},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13791105151176453},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07917216420173645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7101077437400818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086894273757935},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5538396835327148},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5387211441993713},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5254912972450256},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48963767290115356},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.44869449734687805},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.4271901845932007},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41003215312957764},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13791105151176453},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07917216420173645},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":29,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2194775991","https://openalex.org/W2547875792","https://openalex.org/W2619947201","https://openalex.org/W2623912370","https://openalex.org/W2769342113","https://openalex.org/W2949298458","https://openalex.org/W2970671370","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2990730805","https://openalex.org/W3046271479","https://openalex.org/W3101275901","https://openalex.org/W3112828033","https://openalex.org/W3119259789","https://openalex.org/W3126721948","https://openalex.org/W3138516171","https://openalex.org/W3177141386","https://openalex.org/W3203618782","https://openalex.org/W4221156615","https://openalex.org/W4226397718","https://openalex.org/W4284678911","https://openalex.org/W4312266966","https://openalex.org/W4386596970","https://openalex.org/W4393158630","https://openalex.org/W6729448088","https://openalex.org/W6784333009","https://openalex.org/W6787247333","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W2334570605","https://openalex.org/W3181683615","https://openalex.org/W4286826125","https://openalex.org/W1633485514","https://openalex.org/W1604739066","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"Optimizing":[0],"video":[1,13,48,102,173,180],"inference":[2],"efficiency":[3,23,168],"has":[4],"become":[5],"increasingly":[6],"important":[7],"with":[8,51,124],"the":[9,62,66,87,96,106,150,153,164],"growing":[10],"demand":[11],"for":[12],"analysis":[14],"in":[15,35,61,138],"various":[16],"fields.":[17],"Some":[18],"existing":[19],"methods":[20],"achieve":[21],"high":[22],"by":[24,133],"explicit":[25],"discard":[26],"of":[27,65,152],"spatial":[28,129,136],"or":[29],"temporal":[30,75,119],"information,":[31],"which":[32,57],"poses":[33],"challenges":[34],"fast-changing":[36],"and":[37,55,89,94,169,175],"fine-grained":[38],"scenarios.":[39],"To":[40,104],"address":[41],"these":[42],"issues,":[43],"we":[44,78,109],"propose":[45],"an":[46],"efficient":[47],"representation":[49],"network":[50,67,144],"Differentiable":[52,81],"Resolution":[53],"Compression":[54,83],"Alignment,":[56],"compresses":[58],"non-essential":[59],"information":[60],"early":[63],"stage":[64],"to":[68,85,116,183],"reduce":[69],"computational":[70],"costs":[71,131],"while":[72,127],"maintaining":[73],"consistent":[74],"correlations.":[76],"Specifically,":[77],"leverage":[79],"a":[80,99,111],"Context-aware":[82],"Module":[84],"encode":[86],"saliency":[88],"non-saliency":[90,140],"frame":[91,122],"features,":[92],"refining":[93],"updating":[95],"features":[97,123],"into":[98],"high-low":[100],"resolution":[101],"sequence.":[103],"process":[105],"new":[107,112],"sequence,":[108],"introduce":[110],"Resolution-Align":[113],"Transformer":[114],"Layer":[115],"capture":[117],"global":[118],"correlations":[120],"among":[121],"different":[125],"resolutions,":[126],"reducing":[128],"computation":[130],"quadratically":[132],"utilizing":[134],"fewer":[135],"tokens":[137],"low-resolution":[139],"frames.":[141],"The":[142],"entire":[143],"can":[145],"be":[146],"end-to-end":[147],"optimized":[148],"via":[149],"integration":[151],"differentiable":[154],"compression":[155],"module.":[156],"Experimental":[157],"results":[158,177],"show":[159],"that":[160],"our":[161],"method":[162],"achieves":[163],"best":[165],"trade-off":[166],"between":[167],"performance":[170],"on":[171,178],"near-duplicate":[172],"retrieval":[174],"competitive":[176],"dynamic":[179],"classification":[181],"compared":[182],"state-of-the-art":[184],"methods.Code:https://github.com/dun-research/DRCA":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}