{"id":"https://openalex.org/W3128401049","doi":"https://doi.org/10.1109/tip.2020.3048680","title":"Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval","display_name":"Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3128401049","doi":"https://doi.org/10.1109/tip.2020.3048680","mag":"3128401049","pmid":"https://pubmed.ncbi.nlm.nih.gov/33560984"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2020.3048680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3048680","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/284443","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103041611","display_name":"Mengshi Qi","orcid":"https://orcid.org/0000-0002-6955-6635"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CH","CN"],"is_corresponding":true,"raw_author_name":"Mengshi Qi","raw_affiliation_strings":["Computer Vision Laboratory, EPFL, Lausanne, Switzerland","State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061215231","display_name":"Jie Qin","orcid":"https://orcid.org/0000-0002-0306-534X"},"institutions":[{"id":"https://openalex.org/I4210116052","display_name":"Inception Institute of Artificial Intelligence","ror":"https://ror.org/02664zk40","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210116052"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Jie Qin","raw_affiliation_strings":["Inception Institute of Artificial Intelligence, Abu Dhabi, UAE"],"affiliations":[{"raw_affiliation_string":"Inception Institute of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210116052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Center for Artificial Intelligence, University of Technology Sydney, Ultimo, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398953","display_name":"Yunhong Wang","orcid":"https://orcid.org/0000-0001-8001-2703"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhong Wang","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103041611"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":5.6198,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.96990471,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"2989","last_page":"3004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9995999932289124,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"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":0.8246119022369385},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6737247705459595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5954261422157288},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45700064301490784},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44956183433532715},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4076608419418335},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3546751141548157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246119022369385},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6737247705459595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5954261422157288},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45700064301490784},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44956183433532715},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4076608419418335},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3546751141548157},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2020.3048680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3048680","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:33560984","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33560984","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:infoscience.epfl.ch:284443","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/284443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"research article"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:284443","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/284443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"research article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G8055127673","display_name":null,"funder_award_id":"61421003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321125","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":123,"referenced_works":["https://openalex.org/W199018803","https://openalex.org/W877909479","https://openalex.org/W1485009520","https://openalex.org/W1522734439","https://openalex.org/W1536680647","https://openalex.org/W1573040851","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1777628566","https://openalex.org/W1832693441","https://openalex.org/W1910300841","https://openalex.org/W1922199343","https://openalex.org/W1923332106","https://openalex.org/W1927052826","https://openalex.org/W1931639407","https://openalex.org/W1939575207","https://openalex.org/W1957706851","https://openalex.org/W1974647172","https://openalex.org/W1976258951","https://openalex.org/W2014021126","https://openalex.org/W2064675550","https://openalex.org/W2067766814","https://openalex.org/W2085425470","https://openalex.org/W2086958058","https://openalex.org/W2087193308","https://openalex.org/W2096422142","https://openalex.org/W2108523493","https://openalex.org/W2137117795","https://openalex.org/W2139501017","https://openalex.org/W2142881874","https://openalex.org/W2143017621","https://openalex.org/W2144530948","https://openalex.org/W2151385494","https://openalex.org/W2162006472","https://openalex.org/W2163605009","https://openalex.org/W2176950688","https://openalex.org/W2194775991","https://openalex.org/W2251864938","https://openalex.org/W2266728343","https://openalex.org/W2267050401","https://openalex.org/W2293597654","https://openalex.org/W2341212498","https://openalex.org/W2345649690","https://openalex.org/W2402144811","https://openalex.org/W2425121537","https://openalex.org/W2490414731","https://openalex.org/W2519328139","https://openalex.org/W2520610372","https://openalex.org/W2520889032","https://openalex.org/W2522148122","https://openalex.org/W2527195341","https://openalex.org/W2534101049","https://openalex.org/W2563615176","https://openalex.org/W2588534625","https://openalex.org/W2588651547","https://openalex.org/W2598003564","https://openalex.org/W2736850688","https://openalex.org/W2740825418","https://openalex.org/W2741426839","https://openalex.org/W2742256643","https://openalex.org/W2752903123","https://openalex.org/W2753311918","https://openalex.org/W2759194679","https://openalex.org/W2766126435","https://openalex.org/W2766209167","https://openalex.org/W2786585376","https://openalex.org/W2794284562","https://openalex.org/W2795832645","https://openalex.org/W2798354744","https://openalex.org/W2801036749","https://openalex.org/W2808399042","https://openalex.org/W2894669491","https://openalex.org/W2896695957","https://openalex.org/W2897628926","https://openalex.org/W2900790473","https://openalex.org/W2910905530","https://openalex.org/W2914868535","https://openalex.org/W2948958195","https://openalex.org/W2950077968","https://openalex.org/W2953384591","https://openalex.org/W2962835968","https://openalex.org/W2963001870","https://openalex.org/W2963389687","https://openalex.org/W2963843782","https://openalex.org/W2963902384","https://openalex.org/W2971974407","https://openalex.org/W2973858765","https://openalex.org/W2975813532","https://openalex.org/W2979933490","https://openalex.org/W2987222078","https://openalex.org/W2997199342","https://openalex.org/W2998355566","https://openalex.org/W2998841681","https://openalex.org/W3004085219","https://openalex.org/W3014195143","https://openalex.org/W3022778813","https://openalex.org/W3034734814","https://openalex.org/W3034882096","https://openalex.org/W3035012345","https://openalex.org/W3035043893","https://openalex.org/W3035218869","https://openalex.org/W3035309251","https://openalex.org/W3035356601","https://openalex.org/W3035732386","https://openalex.org/W3093352373","https://openalex.org/W3093471110","https://openalex.org/W3099677434","https://openalex.org/W3099940802","https://openalex.org/W3101429639","https://openalex.org/W3102887392","https://openalex.org/W6608183366","https://openalex.org/W6623995992","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6681077227","https://openalex.org/W6684191040","https://openalex.org/W6691474080","https://openalex.org/W6693399182","https://openalex.org/W6697214482","https://openalex.org/W6713134421","https://openalex.org/W6773916930","https://openalex.org/W6773982136","https://openalex.org/W6779506788"],"related_works":["https://openalex.org/W4213212078","https://openalex.org/W2112788825","https://openalex.org/W2187227032","https://openalex.org/W1921169094","https://openalex.org/W1963735073","https://openalex.org/W366410996","https://openalex.org/W2575246084","https://openalex.org/W106707639","https://openalex.org/W4239902399","https://openalex.org/W4233129888"],"abstract_inverted_index":{"With":[0],"the":[1,32,48,99,146,155],"current":[2],"exponential":[3],"growth":[4],"of":[5,160],"video-based":[6],"social":[7],"networks,":[8],"video":[9,95,143,163],"retrieval":[10,164],"using":[11],"natural":[12,52],"language":[13,53],"is":[14],"receiving":[15],"ever-increasing":[16],"attention.":[17],"Most":[18],"existing":[19],"approaches":[20],"tackle":[21],"this":[22],"task":[23],"by":[24],"extracting":[25],"individual":[26],"frame-level":[27],"spatial":[28],"features":[29],"to":[30,128],"represent":[31],"whole":[33],"video,":[34],"while":[35],"ignoring":[36],"visual":[37],"pattern":[38],"consistencies":[39],"and":[40,55,90,110,118,145],"intrinsic":[41],"temporal":[42],"relationships":[43,92,101],"across":[44],"different":[45],"frames.":[46],"Furthermore,":[47],"semantic":[49,91,100],"correspondence":[50],"between":[51,102],"queries":[54],"person-centric":[56],"actions":[57],"in":[58,158],"videos":[59,117],"has":[60],"not":[61],"been":[62],"fully":[63],"explored.":[64],"To":[65],"address":[66],"these":[67],"problems,":[68],"we":[69,122],"propose":[70],"a":[71],"novel":[72],"binary":[73,113],"representation":[74],"learning":[75],"framework,":[76],"named":[77],"Semantics-aware":[78],"Spatial-temporal":[79],"Binaries":[80],"(":[81],"[Formula:":[82,105,151],"see":[83,106,152],"text]Bin),":[84],"which":[85],"simultaneously":[86],"considers":[87],"spatial-temporal":[88],"context":[89],"for":[93,115],"cross-modal":[94,162],"retrieval.":[96],"By":[97],"exploiting":[98],"two":[103],"modalities,":[104],"text]Bin":[107,153],"can":[108],"efficiently":[109],"effectively":[111],"generate":[112],"codes":[114],"both":[116],"texts.":[119],"In":[120],"addition,":[121],"adopt":[123],"an":[124],"iterative":[125],"optimization":[126],"scheme":[127],"learn":[129],"deep":[130],"encoding":[131],"functions":[132],"with":[133],"attribute-guided":[134],"stochastic":[135],"training.":[136],"We":[137],"evaluate":[138],"our":[139],"model":[140],"on":[141],"three":[142],"datasets":[144],"experimental":[147],"results":[148],"demonstrate":[149],"that":[150],"outperforms":[154],"state-of-the-art":[156],"methods":[157],"terms":[159],"various":[161],"tasks.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}