{"id":"https://openalex.org/W4387968589","doi":"https://doi.org/10.1145/3581783.3612152","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","display_name":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968589","doi":"https://doi.org/10.1145/3581783.3612152"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612152","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612152","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612152","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612152","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100411534","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0003-4879-2169"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen & JD.com Inc., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4879-2169","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen & JD.com Inc., Shenzhen, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101533503","display_name":"Yaoyu Li","orcid":"https://orcid.org/0000-0002-7362-7897"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoyu Li","raw_affiliation_strings":["JD.com Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7362-7897","affiliations":[{"raw_affiliation_string":"JD.com Inc., Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654958","display_name":"Tian Gan","orcid":"https://orcid.org/0000-0003-3197-5698"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Gan","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-3197-5698","affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080624259","display_name":"Zheng Zhang","orcid":"https://orcid.org/0009-0002-6391-4814"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["JD.com Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6391-4814","affiliations":[{"raw_affiliation_string":"JD.com Inc., Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023067350","display_name":"Jingjing Lv","orcid":"https://orcid.org/0009-0000-5518-7077"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Lv","raw_affiliation_strings":["JD.com Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-5518-7077","affiliations":[{"raw_affiliation_string":"JD.com Inc., Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6324,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89681219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"557","last_page":"566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9922999739646912,"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":0.9912999868392944,"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":0.887384831905365},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7358068227767944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5463552474975586},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5107779502868652},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4991157054901123},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49862098693847656},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4578060805797577},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35446056723594666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.887384831905365},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7358068227767944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5463552474975586},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5107779502868652},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4991157054901123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49862098693847656},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4578060805797577},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35446056723594666},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612152","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612152","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612152","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2312.00347","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.00347","pdf_url":"https://arxiv.org/pdf/2312.00347","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612152","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612152","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612152","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1789959723","display_name":null,"funder_award_id":"62006140","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2733153709","display_name":null,"funder_award_id":"62176137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7035795116","display_name":null,"funder_award_id":"No.: 62176137, and No.: 62006140","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968589.pdf","grobid_xml":"https://content.openalex.org/works/W4387968589.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W2164290393","https://openalex.org/W2425121537","https://openalex.org/W2765716052","https://openalex.org/W2896457183","https://openalex.org/W2949135277","https://openalex.org/W2956959730","https://openalex.org/W2963017553","https://openalex.org/W2963916161","https://openalex.org/W2990152177","https://openalex.org/W3094502228","https://openalex.org/W3155230099","https://openalex.org/W3166396011","https://openalex.org/W3166968943","https://openalex.org/W3168640669","https://openalex.org/W3175961224","https://openalex.org/W3184735396","https://openalex.org/W3197804339","https://openalex.org/W3204588463","https://openalex.org/W3205021045","https://openalex.org/W4200631219","https://openalex.org/W4214510096","https://openalex.org/W4221142658","https://openalex.org/W4225323055","https://openalex.org/W4225414521","https://openalex.org/W4225868495","https://openalex.org/W4226065437","https://openalex.org/W4226182655","https://openalex.org/W4285606530","https://openalex.org/W4287125738","https://openalex.org/W4295990387","https://openalex.org/W4296151206","https://openalex.org/W4298613318","https://openalex.org/W4304080347","https://openalex.org/W4304092645","https://openalex.org/W4311252325","https://openalex.org/W4312121894","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312463400","https://openalex.org/W4312535570","https://openalex.org/W4312614039","https://openalex.org/W4312974690","https://openalex.org/W4313071966","https://openalex.org/W4313447121","https://openalex.org/W4319049530","https://openalex.org/W4320712030","https://openalex.org/W4364353722","https://openalex.org/W4382240279","https://openalex.org/W4383112678","https://openalex.org/W4386057717","https://openalex.org/W4386065892","https://openalex.org/W4386072365","https://openalex.org/W4386076424","https://openalex.org/W4394659899","https://openalex.org/W6600234944","https://openalex.org/W6607733003","https://openalex.org/W6717243457"],"related_works":["https://openalex.org/W2067317451","https://openalex.org/W2154771632","https://openalex.org/W4211085505","https://openalex.org/W3122478268","https://openalex.org/W2084758217","https://openalex.org/W408804804","https://openalex.org/W4231021675","https://openalex.org/W3086365953","https://openalex.org/W4226072953","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,15,44,120],"video-language":[3,28,124],"understanding":[4,29],"have":[5,54],"been":[6],"established":[7],"on":[8],"the":[9,20,35,111,121,127],"foundation":[10],"of":[11,37,67,74,123],"image-text":[12],"models,":[13],"resulting":[14],"promising":[16],"outcomes":[17],"due":[18,33],"to":[19,34,134],"shared":[21],"knowledge":[22],"between":[23],"images":[24],"and":[25,49,60,86,106,126],"videos.":[26,112],"However,":[27],"presents":[30],"unique":[31],"challenges":[32,91],"inclusion":[36],"highly":[38],"complex":[39],"semantic":[40],"details,":[41],"which":[42,88],"result":[43],"information":[45,98,109],"redundancy,":[46],"temporal":[47,102],"dependency,":[48],"scene":[50],"complexity.":[51],"Current":[52],"techniques":[53],"only":[55],"partially":[56],"tackled":[57],"these":[58,68,90],"issues,":[59],"our":[61,114],"quantitative":[62],"analysis":[63],"indicates":[64],"that":[65],"some":[66],"methods":[69],"are":[70,129],"complementary.":[71],"In":[72],"light":[73],"this,":[75],"we":[76],"propose":[77],"a":[78],"novel":[79],"framework":[80],"called":[81],"RTQ":[82],"(Refine,":[83],"Temporal":[84],"model,":[85],"Query),":[87],"addresses":[89],"simultaneously.":[92],"The":[93],"approach":[94],"involves":[95],"refining":[96],"redundant":[97],"within":[99],"frames,":[100,105],"modeling":[101],"relations":[103],"among":[104],"querying":[107],"task-specific":[108],"from":[110],"Remarkably,":[113],"model":[115],"demonstrates":[116],"outstanding":[117],"performance":[118],"even":[119],"absence":[122],"pre-training,":[125],"results":[128],"comparable":[130],"with":[131],"or":[132],"superior":[133],"those":[135],"achieved":[136],"by":[137],"state-of-the-art":[138],"pre-training":[139],"methods.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}