{"id":"https://openalex.org/W7168349179","doi":"https://doi.org/10.1145/3805712.3809835","title":"A Multi-Granularity Game-Theoretic Approach to Weakly Supervised Temporal Article Grounding","display_name":"A Multi-Granularity Game-Theoretic Approach to Weakly Supervised Temporal Article Grounding","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7168349179","doi":"https://doi.org/10.1145/3805712.3809835"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809835","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809835","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140887168","display_name":"Shuyi He","orcid":"https://orcid.org/0009-0004-0003-8452"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyi He","raw_affiliation_strings":["State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0003-8452","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140751992","display_name":"Hao Wen","orcid":"https://orcid.org/0009-0003-4087-1505"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Wen","raw_affiliation_strings":["Beijing Wenge Technology Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-4087-1505","affiliations":[{"raw_affiliation_string":"Beijing Wenge Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140847199","display_name":"Pu Zou","orcid":"https://orcid.org/0009-0004-2554-4984"},"institutions":[{"id":"https://openalex.org/I4210133666","display_name":"Tiandi Science & Technology (China)","ror":"https://ror.org/03ssr6t63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210133666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pu Zou","raw_affiliation_strings":["Tianwen Digital Media Technology (Hunan) Co., Ltd., Changsha, China"],"raw_orcid":"https://orcid.org/0009-0004-2554-4984","affiliations":[{"raw_affiliation_string":"Tianwen Digital Media Technology (Hunan) Co., Ltd., Changsha, China","institution_ids":["https://openalex.org/I4210133666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140959492","display_name":"Song Zhou","orcid":"https://orcid.org/0009-0008-9687-3610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Zhou","raw_affiliation_strings":["Beijing Wenge Technology Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9687-3610","affiliations":[{"raw_affiliation_string":"Beijing Wenge Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140805814","display_name":"Qingchao Kong","orcid":"https://orcid.org/0000-0002-1929-8404"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingchao Kong","raw_affiliation_strings":["State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1929-8404","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3781","last_page":"3786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.30880001187324524},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.29589998722076416},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2540000081062317},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.25119999051094055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5199999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5083000063896179},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2694000005722046},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2590000033378601},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25119999051094055},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809835","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809835","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2052493079","https://openalex.org/W2487898712","https://openalex.org/W2883429621","https://openalex.org/W2883891001","https://openalex.org/W2963017553","https://openalex.org/W2963541336","https://openalex.org/W2964089981","https://openalex.org/W2964121718","https://openalex.org/W3035356601","https://openalex.org/W3035635319","https://openalex.org/W3043840704","https://openalex.org/W3174572181","https://openalex.org/W3186567887","https://openalex.org/W4298364821","https://openalex.org/W4312680331","https://openalex.org/W4385573643","https://openalex.org/W4386076265","https://openalex.org/W4390872513","https://openalex.org/W4390874127","https://openalex.org/W4393159035","https://openalex.org/W4402727225","https://openalex.org/W4402727272","https://openalex.org/W4402754238","https://openalex.org/W4403243537","https://openalex.org/W4409369885"],"related_works":[],"abstract_inverted_index":{"Weakly":[0],"Supervised":[1],"temporal":[2],"Article":[3],"Grounding":[4],"(WSAG)":[5],"is":[6],"an":[7],"important":[8],"task":[9],"in":[10,130],"the":[11,24,27,73,77,151,160,186,190,227,236],"field":[12],"of":[13,185],"video":[14,29,54,81,116,170,251],"understanding":[15],"and":[16,83,118,125,172,196,211,221,249],"retrieval,":[17],"which":[18,114],"aims":[19],"to":[20,51,93,153,194,200],"ground":[21],"sentences":[22],"from":[23],"article":[25,74,119],"with":[26,72,214],"corresponding":[28],"clips":[30,82,117,171],"(segments),":[31],"using":[32],"only":[33],"video-text":[34],"pairwise":[35],"annotations":[36],"during":[37],"training.":[38],"Existing":[39],"methods":[40,248],"typically":[41],"rely":[42],"on":[43,68,239],"a":[44,104,131,155,164],"proposal-based":[45],"approach":[46],"that":[47,233],"utilizes":[48],"contrastive":[49],"learning":[50],"score":[52],"candidate":[53],"clips.":[55],"However,":[56],"these":[57,100],"approaches":[58],"often":[59],"face":[60],"two":[61,138],"main":[62],"drawbacks:":[63],"(1)":[64,140],"They":[65,87],"mainly":[66],"focus":[67],"global":[69],"video-level":[70],"alignment":[71,220],"while":[75],"neglecting":[76],"multi-level":[78],"relationships":[79],"between":[80,167],"text":[84],"hierarchy;":[85],"(2)":[86,177],"overlook":[88],"intra-modal":[89,210],"feature":[90,142,157,224],"learning,":[91],"failing":[92],"adequately":[94],"distinguish":[95],"salient":[96,156,223],"patterns.":[97],"To":[98],"address":[99],"issues,":[101],"we":[102,147,188],"propose":[103],"novel":[105],"multi-granularity":[106],"game-theoretic":[107],"method,":[108],"namely":[109],"Hierarchical":[110],"Cooperative":[111],"Network":[112],"(HCN),":[113],"models":[115],"units":[120],"(i.e.,":[121],"at":[122],"word,":[123],"sentence,":[124],"paragraph":[126],"layers)":[127],"as":[128,159],"players":[129],"game.":[132],"Specifically,":[133],"our":[134],"proposed":[135],"method":[136],"introduces":[137],"mechanisms:":[139],"Intra-modal":[141],"cooperation:":[143,180],"Within":[144],"each":[145],"modality,":[146],"encourage":[148],"cooperation":[149],"among":[150],"features":[152],"obtain":[154],"set":[158],"effective":[161],"representations,":[162],"enabling":[163],"sharper":[165],"distinction":[166],"semantically":[168],"overlapping":[169],"enhancing":[173],"discriminative":[174],"textual":[175],"cues;":[176],"Layered":[178],"cross-modal":[179,203,212],"For":[181],"different":[182],"semantic":[183],"layers":[184],"article,":[187],"employ":[189],"Shapley":[191],"interaction":[192],"index":[193],"quantify":[195],"promote":[197],"synergistic":[198],"effects":[199],"further":[201],"enhance":[202],"matching.":[204],"By":[205],"decomposing":[206],"multi-modal":[207],"interactions":[208],"into":[209],"cooperations":[213],"multi-layer":[215],"semantics,":[216],"HCN":[217,234],"achieves":[218,235],"fine-grained":[219],"strengthens":[222],"representations":[225],"for":[226],"WSAG":[228,241],"task.":[229],"Experimental":[230],"results":[231],"demonstrate":[232],"state-of-the-art":[237],"performances":[238],"representative":[240],"benchmarks,":[242],"significantly":[243],"outperforming":[244],"existing":[245],"weakly":[246],"supervised":[247],"competitive":[250],"large":[252],"language":[253],"models.":[254]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-16T00:00:00"}