{"id":"https://openalex.org/W4405755127","doi":"https://doi.org/10.1109/tpami.2024.3522124","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","display_name":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","publication_year":2024,"publication_date":"2024-12-24","ids":{"openalex":"https://openalex.org/W4405755127","doi":"https://doi.org/10.1109/tpami.2024.3522124","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030601"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3522124","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3522124","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tpami.2024.3522124","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Peng Jin","orcid":"https://orcid.org/0000-0001-9287-6410"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jin","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China","epartment of Electronic and Computer Engineering, Peking University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9287-6410","affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"epartment of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103204990","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-3200-0270"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China","epartment of Electronic and Computer Engineering, Peking University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3200-0270","affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"epartment of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li Yuan","orcid":"https://orcid.org/0000-0002-2120-5588"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Yuan","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2120-5588","affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["Skywork AI, Singapore","Kunlun 2050 Research and Skywork AI, China"],"raw_orcid":"https://orcid.org/0000-0001-8906-3777","affiliations":[{"raw_affiliation_string":"Skywork AI, Singapore","institution_ids":[]},{"raw_affiliation_string":"Kunlun 2050 Research and Skywork AI, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Jie Chen","orcid":"https://orcid.org/0000-0002-9765-4523"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Chen","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9765-4523","affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":{"value":2495,"currency":"USD","value_usd":2495},"fwci":0.4576,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61515941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"47","issue":"3","first_page":"2125","last_page":"2139"},"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":0.9987999796867371,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9907000064849854,"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/computer-science","display_name":"Computer science","score":0.697808027267456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6910392045974731},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5540324449539185},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5416576862335205},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36701568961143494},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3423312306404114},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33679381012916565}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697808027267456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6910392045974731},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5540324449539185},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5416576862335205},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36701568961143494},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3423312306404114},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33679381012916565},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2024.3522124","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3522124","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40030601","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030601","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 pattern analysis and machine intelligence","raw_type":"Journal Article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/218169","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/218169","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1109/tpami.2024.3522124","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3522124","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":90,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1956340063","https://openalex.org/W2009662043","https://openalex.org/W2038127015","https://openalex.org/W2091836314","https://openalex.org/W2101105183","https://openalex.org/W2103691541","https://openalex.org/W2187089797","https://openalex.org/W2213630128","https://openalex.org/W2268194897","https://openalex.org/W2425121537","https://openalex.org/W2510508396","https://openalex.org/W2556388456","https://openalex.org/W2765716052","https://openalex.org/W2885775891","https://openalex.org/W2946165673","https://openalex.org/W2963017553","https://openalex.org/W2963753226","https://openalex.org/W2963916161","https://openalex.org/W2964220823","https://openalex.org/W2984008963","https://openalex.org/W3008569663","https://openalex.org/W3034730770","https://openalex.org/W3043840704","https://openalex.org/W3120164061","https://openalex.org/W3130796238","https://openalex.org/W3153005511","https://openalex.org/W3160891393","https://openalex.org/W3166608351","https://openalex.org/W3168640669","https://openalex.org/W3169472988","https://openalex.org/W3171927989","https://openalex.org/W3174873881","https://openalex.org/W3175888430","https://openalex.org/W3176689360","https://openalex.org/W3204588463","https://openalex.org/W3205021045","https://openalex.org/W3217340782","https://openalex.org/W4210900713","https://openalex.org/W4214692497","https://openalex.org/W4225414521","https://openalex.org/W4229449886","https://openalex.org/W4252547120","https://openalex.org/W4281560470","https://openalex.org/W4285606530","https://openalex.org/W4297808394","https://openalex.org/W4300906944","https://openalex.org/W4312271977","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312463400","https://openalex.org/W4312791030","https://openalex.org/W4312954271","https://openalex.org/W4312974690","https://openalex.org/W4312999114","https://openalex.org/W4313071966","https://openalex.org/W4313178921","https://openalex.org/W4313186260","https://openalex.org/W4377235294","https://openalex.org/W4378805076","https://openalex.org/W4385572712","https://openalex.org/W4385764570","https://openalex.org/W4385767942","https://openalex.org/W4386065436","https://openalex.org/W4386075541","https://openalex.org/W4386076265","https://openalex.org/W4386076661","https://openalex.org/W4386122702","https://openalex.org/W4386902900","https://openalex.org/W4390872434","https://openalex.org/W4390874374","https://openalex.org/W4390874542","https://openalex.org/W4390889802","https://openalex.org/W4391454521","https://openalex.org/W4393147969","https://openalex.org/W4393156126","https://openalex.org/W4394659899","https://openalex.org/W4403924524","https://openalex.org/W6631190155","https://openalex.org/W6678262379","https://openalex.org/W6766582784","https://openalex.org/W6784184991","https://openalex.org/W6791353385","https://openalex.org/W6796494063","https://openalex.org/W6811844594","https://openalex.org/W6838434436","https://openalex.org/W6841299521","https://openalex.org/W6844194202","https://openalex.org/W6846822233","https://openalex.org/W6864544085"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2961085424","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W2055929693","https://openalex.org/W4224009465","https://openalex.org/W4324271173","https://openalex.org/W1967645776","https://openalex.org/W2352227742"],"abstract_inverted_index":{"Multimodal":[0],"representation":[1,20,121,132],"learning,":[2,5],"with":[3,78,186],"contrastive":[4],"plays":[6],"an":[7,16],"important":[8,17],"role":[9],"in":[10,112],"the":[11,89,95,110,120,140,146,165,190],"artificial":[12],"intelligence":[13],"domain.":[14],"As":[15],"subfield,":[18],"video-language":[19],"learning":[21,24],"focuses":[22],"on":[23,175],"representations":[25],"using":[26,66],"global":[27,41],"semantic":[28,76],"interactions":[29,45,77],"between":[30,98],"pre-defined":[31],"video-text":[32,62],"pairs.":[33],"However,":[34],"to":[35,71,93,108,137,167,169],"enhance":[36],"and":[37,83,101,127,182,192],"refine":[38],"such":[39],"coarse-grained":[40],"interactions,":[42],"more":[43],"detailed":[44],"are":[46],"necessary":[47],"for":[48],"fine-grained":[49,75],"multimodal":[50],"learning.":[51],"In":[52],"this":[53],"study,":[54],"we":[55,87,117,154],"introduce":[56],"a":[57,123,160],"creative":[58],"approach":[59],"that":[60,138],"models":[61],"as":[63],"game":[64,69],"players":[65],"multivariate":[67],"cooperative":[68],"theory":[70],"handle":[72],"uncertainty":[73],"during":[74],"diverse":[79],"granularity,":[80],"flexible":[81,161],"combination,":[82],"vague":[84],"intensity.":[85],"Specifically,":[86],"design":[88],"Hierarchical":[90],"Banzhaf":[91,115],"Interaction":[92],"simulate":[94],"finegrained":[96],"correspondence":[97],"video":[99,183],"clips":[100],"textual":[102],"words":[103],"from":[104],"hierarchical":[105],"perspectives.":[106],"Furthermore,":[107],"mitigate":[109],"bias":[111],"calculations":[113],"within":[114],"Interaction,":[116],"propose":[118],"reconstructing":[119],"through":[122],"fusion":[124],"of":[125,139,150,194],"single-modal":[126,141],"crossmodal":[128],"components.":[129],"This":[130],"reconstructed":[131],"ensures":[133],"fine":[134],"granularity":[135],"comparable":[136],"representation,":[142],"while":[143],"also":[144],"preserving":[145],"adaptive":[147],"encoding":[148],"characteristics":[149],"cross-modal":[151],"representation.":[152],"Additionally,":[153],"extend":[155],"our":[156,195],"original":[157],"structure":[158],"into":[159],"encoder-decoder":[162],"framework,":[163],"enabling":[164],"model":[166],"adapt":[168],"various":[170],"downstream":[171],"tasks.":[172],"Extensive":[173],"experiments":[174],"commonly":[176],"used":[177],"text-video":[178],"retrieval,":[179],"video-question":[180],"answering,":[181],"captioning":[184],"benchmarks,":[185],"superior":[187],"performance,":[188],"validate":[189],"effectiveness":[191],"generalization":[193],"method.":[196],"The":[197],"code":[198],"is":[199],"available":[200],"at":[201],"https://github.com/jpthu17/HBI.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}