{"id":"https://openalex.org/W4414491137","doi":"https://doi.org/10.1109/tip.2025.3611174","title":"HOVER: Hyperbolic Video-Text Retrieval","display_name":"HOVER: Hyperbolic Video-Text Retrieval","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414491137","doi":"https://doi.org/10.1109/tip.2025.3611174","pmid":"https://pubmed.ncbi.nlm.nih.gov/40986591"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3611174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3611174","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jun Wen","orcid":"https://orcid.org/0000-0001-5067-2647"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Wen","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5067-2647","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103271230","display_name":"Yufeng Chen","orcid":"https://orcid.org/0009-0004-4088-0126"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yufeng Chen","raw_affiliation_strings":["National University of Singapore, Queenstown, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruiqi Shi","orcid":"https://orcid.org/0009-0001-8850-040X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ruiqi Shi","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0001-8850-040X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101397422","display_name":"Wei Ji","orcid":"https://orcid.org/0000-0002-8106-9768"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Ji","raw_affiliation_strings":["National University of Singapore, Queenstown, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091585620","display_name":"Meng\u2010Lin Yang","orcid":"https://orcid.org/0000-0003-2510-5282"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Menglin Yang","raw_affiliation_strings":["Department of Computer Science, Yale University, New Haven, CT, USA"],"raw_orcid":"https://orcid.org/0000-0003-2510-5282","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001133932","display_name":"Difei Gao","orcid":"https://orcid.org/0000-0001-8494-3492"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Difei Gao","raw_affiliation_strings":["National University of Singapore, Queenstown, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085245110","display_name":"Junsong Yuan","orcid":"https://orcid.org/0000-0002-7324-7034"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsong Yuan","raw_affiliation_strings":["Department of Computer Science and Engineering,, University at Buffalo, Buffalo, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-7324-7034","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering,, University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058575315","display_name":"Roger Zimmermann","orcid":"https://orcid.org/0000-0002-7410-2590"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Roger Zimmermann","raw_affiliation_strings":["National University of Singapore, Queenstown, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85054389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"34","issue":null,"first_page":"6192","last_page":"6203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9983000159263611,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9983000159263611,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9948999881744385,"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":0.9847000241279602,"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/generalization","display_name":"Generalization","score":0.6758000254631042},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6312999725341797},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5382999777793884},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5274999737739563},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47699999809265137},{"id":"https://openalex.org/keywords/hyperbolic-tree","display_name":"Hyperbolic tree","score":0.46790000796318054},{"id":"https://openalex.org/keywords/hyperbolic-space","display_name":"Hyperbolic space","score":0.426800012588501},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41029998660087585},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.40959998965263367},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4043000042438507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7089999914169312},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6758000254631042},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6312999725341797},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5382999777793884},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47189998626708984},{"id":"https://openalex.org/C97654310","wikidata":"https://www.wikidata.org/wiki/Q574023","display_name":"Hyperbolic tree","level":4,"score":0.46790000796318054},{"id":"https://openalex.org/C83677898","wikidata":"https://www.wikidata.org/wiki/Q1878538","display_name":"Hyperbolic space","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4189000129699707},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.40959998965263367},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4043000042438507},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4025999903678894},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3944999873638153},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.3314000070095062},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3611174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3611174","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:40986591","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40986591","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W1971215074","https://openalex.org/W2078238240","https://openalex.org/W2199357291","https://openalex.org/W2425121537","https://openalex.org/W2897439619","https://openalex.org/W2963841265","https://openalex.org/W2964089981","https://openalex.org/W3034694537","https://openalex.org/W3035102141","https://openalex.org/W3035700349","https://openalex.org/W3105232955","https://openalex.org/W3130796238","https://openalex.org/W3177564060","https://openalex.org/W3180463990","https://openalex.org/W3204588463","https://openalex.org/W3217321712","https://openalex.org/W4205175531","https://openalex.org/W4224295683","https://openalex.org/W4285606530","https://openalex.org/W4296899566","https://openalex.org/W4304014690","https://openalex.org/W4312364543","https://openalex.org/W4312372711","https://openalex.org/W4312533318","https://openalex.org/W4313127305","https://openalex.org/W4321614506","https://openalex.org/W4376607849","https://openalex.org/W4385245566","https://openalex.org/W4385804753","https://openalex.org/W4386072365","https://openalex.org/W4386076409","https://openalex.org/W4390872366","https://openalex.org/W4390874668","https://openalex.org/W4390889802","https://openalex.org/W4402727663","https://openalex.org/W4402753632"],"related_works":[],"abstract_inverted_index":{"Video-text":[0],"retrieval":[1,18,64],"is":[2,218],"a":[3,24,90,98,126,187],"crucial":[4],"task":[5],"in":[6,45,62,89,157,180],"numerous":[7],"computer":[8],"vision":[9],"applications.":[10],"In":[11],"this":[12,68],"paper,":[13],"we":[14,70],"focus":[15],"on":[16],"video-text":[17,116,196],"involving":[19],"complex":[20,140],"action":[21,128,141,213],"compositions,":[22],"where":[23,130],"single":[25],"video":[26,124],"encompasses":[27],"multiple":[28],"primitive":[29,131],"actions":[30],"such":[31,48],"as":[32,135,143],"\"sitting":[33],"up\",":[34],"\"opening":[35],"door\",":[36],"\"cooking":[37],"food\",":[38],"and":[39,84,112,138,149,165],"\"eating.\"":[40],"Despite":[41],"the":[42,78,194],"common":[43],"occurrences":[44],"real-world":[46],"scenarios,":[47],"action-compositional":[49],"videos":[50,83,208],"have":[51],"received":[52],"limited":[53,183],"research":[54],"attention,":[55],"often":[56],"leading":[57],"to":[58],"significant":[59],"performance":[60,189],"degradations":[61],"existing":[63],"methods.":[65],"To":[66],"address":[67],"challenge,":[69],"present":[71],"Hyperbolic":[72],"Video-tExt":[73],"Retrieval":[74],"(HOVER),":[75],"which":[76],"models":[77],"hierarchical":[79,105,127],"semantic":[80,117,147],"relationships":[81],"between":[82],"texts":[85],"by":[86,160,199],"embedding":[87],"them":[88],"low-dimensional":[91],"hyperbolic":[92,95,158,162,195],"space.":[93],"Since":[94],"space":[96,159],"provides":[97],"geometric":[99],"prior":[100],"that":[101,172],"naturally":[102],"aligns":[103],"with":[104,182,209],"data,":[106],"it":[107],"allows":[108],"for":[109],"more":[110],"efficient":[111],"generalizable":[113],"representations":[114],"of":[115,152,191,212],"hierarchies.":[118],"HOVER":[119,173,200],"first":[120],"longitudinally":[121],"decomposes":[122],"each":[123],"into":[125],"tree,":[129],"mono-actions":[132],"are":[133,154],"represented":[134],"leaf":[136],"nodes":[137],"increasingly":[139],"compositions":[142],"parent":[144],"nodes.":[145],"The":[146,215],"structures":[148],"temporal":[150],"dependencies":[151],"videos/texts":[153],"then":[155],"encoded":[156],"exploiting":[161],"distance,":[163],"norm,":[164],"relative":[166],"cosine":[167],"similarity.":[168],"Experimental":[169],"results":[170],"show":[171],"significantly":[174],"outperforms":[175],"traditional":[176],"Euclidean-based":[177],"methods,":[178],"particularly":[179],"scenarios":[181],"training":[184],"labels,":[185],"achieving":[186],"notable":[188],"improvement":[190],"28.83%.":[192],"Additionally,":[193],"embeddings":[197],"learned":[198],"demonstrate":[201],"strong":[202],"generalization":[203],"across":[204],"new":[205],"datasets":[206],"containing":[207],"varying":[210],"levels":[211],"complexity.":[214],"source":[216],"code":[217],"available":[219],"at":[220],"https://github.com/shi-rq/HOVER.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}