{"id":"https://openalex.org/W4416078604","doi":"https://doi.org/10.1145/3746252.3760857","title":"Structuring Video Semantics with Temporal Triplets for Zero-Shot Video Question Answering","display_name":"Structuring Video Semantics with Temporal Triplets for Zero-Shot Video Question Answering","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W4416078604","doi":"https://doi.org/10.1145/3746252.3760857"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3760857","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760857","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3760857","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3760857","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030649664","display_name":"Linlin Zong","orcid":"https://orcid.org/0000-0002-1116-1016"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linlin Zong","raw_affiliation_strings":["Dalian University Of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-1116-1016","affiliations":[{"raw_affiliation_string":"Dalian University Of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007193615","display_name":"Xinyu Zhai","orcid":"https://orcid.org/0009-0002-0031-8847"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Zhai","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0002-0031-8847","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036472945","display_name":"Xinyue Liu","orcid":"https://orcid.org/0000-0001-9036-4665"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyue Liu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-9036-4665","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000836998","display_name":"Wenxin Liang","orcid":"https://orcid.org/0000-0002-9166-3138"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Liang","raw_affiliation_strings":["Dalian University Of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-9166-3138","affiliations":[{"raw_affiliation_string":"Dalian University Of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006269113","display_name":"Xianchao Zhang","orcid":"https://orcid.org/0000-0002-0180-3740"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianchao Zhang","raw_affiliation_strings":["Dalian University Of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-0180-3740","affiliations":[{"raw_affiliation_string":"Dalian University Of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062895972","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0001-5453-978X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Dalian University Of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-5453-978X","affiliations":[{"raw_affiliation_string":"Dalian University Of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37911884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5545","last_page":"5549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9940999746322632,"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":0.9940999746322632,"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/T10028","display_name":"Topic Modeling","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/generality","display_name":"Generality","score":0.7405999898910522},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.626800000667572},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5960000157356262},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5932000279426575},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5235000252723694},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.39089998602867126},{"id":"https://openalex.org/keywords/subtitle","display_name":"Subtitle","score":0.37959998846054077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8323000073432922},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7405999898910522},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.626800000667572},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5960000157356262},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5932000279426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5493000149726868},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5235000252723694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4309000074863434},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3760857","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760857","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3760857","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746252.3760857","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760857","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3760857","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7778113852","display_name":null,"funder_award_id":"DUT24MS003","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416078604.pdf","grobid_xml":"https://content.openalex.org/works/W4416078604.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2765716052","https://openalex.org/W3175961224","https://openalex.org/W4226094317","https://openalex.org/W4312846625","https://openalex.org/W4391407221","https://openalex.org/W4402727142","https://openalex.org/W4402727536","https://openalex.org/W4402727574","https://openalex.org/W4402727624","https://openalex.org/W4402727922","https://openalex.org/W4415798317"],"related_works":[],"abstract_inverted_index":{"Current":[0],"large":[1],"vision-language":[2],"models":[3],"(VLMs)":[4],"exhibit":[5],"remarkable":[6],"performance":[7,134],"in":[8,67],"basic":[9],"video":[10,84,111],"understanding":[11,26],"tasks.":[12],"However,":[13],"existing":[14],"VLMs":[15],"are":[16],"still":[17],"limited":[18],"to":[19,45,62],"surface-level":[20],"perception":[21],"and":[22,27,72,80,85,126,141],"lack":[23],"fine-grained":[24],"spatio-temporal":[25],"combinatorial":[28],"reasoning":[29],"capabilities.":[30],"Existing":[31],"methods":[32],"typically":[33],"rely":[34],"on":[35,59,118],"expensive":[36],"human":[37],"annotations":[38],"or":[39],"subtitle":[40],"extraction,":[41],"yet":[42],"they":[43],"struggle":[44],"effectively":[46],"model":[47],"temporal":[48,60,70,87,99],"relations":[49],"between":[50],"frames.":[51],"This":[52,101],"paper":[53],"proposes":[54],"a":[55,96],"structured":[56,102],"representation":[57,103],"based":[58],"triplets":[61],"address":[63],"two":[64],"major":[65],"challenges":[66],"traditional":[68],"approaches:":[69],"fragmentation":[71],"entity":[73],"reference":[74],"ambiguity.":[75],"By":[76],"modeling":[77],"objects,":[78],"attributes,":[79],"relationships":[81],"within":[82],"the":[83],"incorporating":[86],"information,":[88],"we":[89],"convert":[90],"semantic":[91],"content":[92],"from":[93],"keyframes":[94],"into":[95],"sequence":[97],"of":[98],"triplets.":[100],"is":[104],"then":[105],"used":[106],"as":[107],"input":[108],"for":[109],"zero-shot":[110],"question":[112],"answering":[113],"(VideoQA).":[114],"Experiments":[115],"were":[116],"conducted":[117],"four":[119],"benchmark":[120],"VideoQA":[121],"datasets:":[122],"NExT-QA,":[123],"STAR,":[124],"MSVD-QA,":[125],"MSRVTT-QA,":[127],"showing":[128],"that":[129],"our":[130],"method":[131],"achieves":[132],"competitive":[133],"without":[135],"requiring":[136],"fine-tuning,":[137],"validating":[138],"its":[139],"generality":[140],"effectiveness.":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-10T00:00:00"}
