{"id":"https://openalex.org/W7126109460","doi":"https://doi.org/10.1007/s11263-025-02645-7","title":"HACG: Leveraging Hierarchical Alignment and Caption Generation for Text-Video Retrieval","display_name":"HACG: Leveraging Hierarchical Alignment and Caption Generation for Text-Video Retrieval","publication_year":2026,"publication_date":"2026-01-29","ids":{"openalex":"https://openalex.org/W7126109460","doi":"https://doi.org/10.1007/s11263-025-02645-7"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02645-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-025-02645-7","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-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/A5101658131","display_name":"Donglin Zhang","orcid":"https://orcid.org/0000-0002-0716-0918"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]},{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Donglin Zhang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, GU2 7XH, Guildford, U.K","School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-0716-0918","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, GU2 7XH, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122, Jiangsu, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084816002","display_name":"Zhiwen Wang","orcid":"https://orcid.org/0000-0002-2648-5769"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwen Wang","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122, Jiangsu, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124273632","display_name":"Xiao-Jun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao-Jun Wu","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122, Jiangsu, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085515769","display_name":"J. Kittler","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josef Kittler","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, GU2 7XH, Guildford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, GU2 7XH, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5124273632"],"corresponding_institution_ids":["https://openalex.org/I111599522"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":null,"fwci":17.3836,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97346139,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"134","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.968999981880188,"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":0.968999981880188,"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":0.014999999664723873,"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":0.002899999963119626,"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/leverage","display_name":"Leverage (statistics)","score":0.6463000178337097},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.5321000218391418},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.5084999799728394},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4738999903202057},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4058000147342682},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3666999936103821},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3596000075340271},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.3529999852180481},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.34869998693466187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9057999849319458},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6463000178337097},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5685999989509583},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.5321000218391418},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4738999903202057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4560999870300293},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4058000147342682},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3596000075340271},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.34869998693466187},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.31949999928474426},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.290800005197525},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02645-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-025-02645-7","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4692016002","display_name":null,"funder_award_id":"62202204","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W914561379","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2049125285","https://openalex.org/W2255466643","https://openalex.org/W2425121537","https://openalex.org/W2526417872","https://openalex.org/W2558834163","https://openalex.org/W2560346187","https://openalex.org/W2885195348","https://openalex.org/W2962681491","https://openalex.org/W2963017553","https://openalex.org/W2963177403","https://openalex.org/W2963267809","https://openalex.org/W3035356601","https://openalex.org/W3035524453","https://openalex.org/W3043840704","https://openalex.org/W3145807616","https://openalex.org/W3153005511","https://openalex.org/W3168640669","https://openalex.org/W3174873881","https://openalex.org/W3196974791","https://openalex.org/W3198985204","https://openalex.org/W3204588463","https://openalex.org/W3205021045","https://openalex.org/W3207042189","https://openalex.org/W3211076469","https://openalex.org/W3217340782","https://openalex.org/W4200635486","https://openalex.org/W4221142658","https://openalex.org/W4225414521","https://openalex.org/W4285606530","https://openalex.org/W4289940197","https://openalex.org/W4304014690","https://openalex.org/W4312247461","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312463400","https://openalex.org/W4375869474","https://openalex.org/W4382458743","https://openalex.org/W4385767942","https://openalex.org/W4386066385","https://openalex.org/W4386072365","https://openalex.org/W4386076265","https://openalex.org/W4386076661","https://openalex.org/W4386942867","https://openalex.org/W4390872366","https://openalex.org/W4390872434","https://openalex.org/W4390873165","https://openalex.org/W4390874542","https://openalex.org/W4390874668","https://openalex.org/W4391407093","https://openalex.org/W4392904725","https://openalex.org/W4400892527","https://openalex.org/W4402704596","https://openalex.org/W4402727904","https://openalex.org/W4402777374","https://openalex.org/W4403636136","https://openalex.org/W4404724811","https://openalex.org/W4412458988"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2026-01-30T00:00:00"}
