{"id":"https://openalex.org/W4415537069","doi":"https://doi.org/10.1145/3746027.3755537","title":"GraphVideoAgent: Enhancing Long-form Video Understanding with Entity Relation Graphs","display_name":"GraphVideoAgent: Enhancing Long-form Video Understanding with Entity Relation Graphs","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537069","doi":"https://doi.org/10.1145/3746027.3755537"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5112620143","display_name":"Meng Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Meng Chu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0003-7105-5439","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101762861","display_name":"Yicong Li","orcid":"https://orcid.org/0000-0002-5659-793X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yicong Li","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5659-793X","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112620143"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28634134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4639","last_page":"4648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9921000003814697,"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/set","display_name":"Set (abstract data type)","score":0.6419000029563904},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5946999788284302},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5878000259399414},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5313000082969666},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4812999963760376},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3659999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753999829292297},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6419000029563904},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5946999788284302},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5313000082969666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.499099999666214},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2963536419","https://openalex.org/W2988743243","https://openalex.org/W3093017735","https://openalex.org/W3118598912","https://openalex.org/W3168640669","https://openalex.org/W3175961224","https://openalex.org/W3177399480","https://openalex.org/W3183092879","https://openalex.org/W3197457832","https://openalex.org/W3205572000","https://openalex.org/W3206633059","https://openalex.org/W4200631219","https://openalex.org/W4247816684","https://openalex.org/W4304098887","https://openalex.org/W4312299780","https://openalex.org/W4312936847","https://openalex.org/W4312974690","https://openalex.org/W4313038481","https://openalex.org/W4313071966","https://openalex.org/W4383112678","https://openalex.org/W4386071468","https://openalex.org/W4386076314","https://openalex.org/W4390041933","https://openalex.org/W4390723197","https://openalex.org/W4390871765","https://openalex.org/W4390872733","https://openalex.org/W4390872747","https://openalex.org/W4390873732","https://openalex.org/W4393148430","https://openalex.org/W4402667024","https://openalex.org/W4402702917","https://openalex.org/W4402702986","https://openalex.org/W4402727474","https://openalex.org/W4402727803","https://openalex.org/W4402753874","https://openalex.org/W4403760933","https://openalex.org/W4403947192"],"related_works":[],"abstract_inverted_index":{"Long-form":[0],"video":[1,13],"understanding":[2],"(LVU)":[3],"addresses":[4],"the":[5,71,90],"challenge":[6],"of":[7,35],"answering":[8],"complex":[9],"questions":[10],"over":[11,40],"extended":[12],"length,":[14],"where":[15],"informative":[16],"cues":[17],"are":[18],"sparse":[19],"and":[20,38,57,76,86,98],"easily":[21],"overwhelmed":[22],"by":[23],"redundant":[24],"content.":[25],"To":[26],"tackle":[27],"this,":[28],"it":[29],"requires":[30],"selecting":[31],"a":[32,65],"small":[33],"set":[34],"question-relevant":[36],"keyframes":[37],"reasoning":[39],"long-range,":[41],"temporally":[42],"dispersed":[43],"visual":[44],"evidence.":[45],"However,":[46],"current":[47],"methods":[48],"typically":[49],"extract":[50],"frame-level":[51],"features":[52],"with":[53],"limited":[54],"temporal":[55],"context":[56],"store":[58],"them":[59],"in":[60,89],"sequential":[61],"memory":[62],"structures.":[63],"As":[64],"result,":[66],"they":[67],"struggle":[68],"to":[69,78],"capture":[70],"evolving":[72],"relations":[73],"among":[74],"entities":[75,83],"fail":[77],"maintain":[79],"identity":[80],"consistency":[81],"when":[82],"temporarily":[84],"leave":[85],"later":[87],"reappear":[88],"video.":[91],"These":[92],"limitations":[93],"prevent":[94],"accurate":[95],"keyframe":[96],"localization":[97],"coherent":[99],"reasoning.":[100]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}
