{"id":"https://openalex.org/W4401991051","doi":"https://doi.org/10.1109/icmew63481.2024.10645365","title":"Enhancing Video Grounding with Dual-Path Modality Fusion on Animal Kingdom Datasets","display_name":"Enhancing Video Grounding with Dual-Path Modality Fusion on Animal Kingdom Datasets","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401991051","doi":"https://doi.org/10.1109/icmew63481.2024.10645365"},"language":"en","primary_location":{"id":"doi:10.1109/icmew63481.2024.10645365","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmew63481.2024.10645365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077093362","display_name":"Chengpeng Xiong","orcid":"https://orcid.org/0009-0001-4501-2617"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chengpeng Xiong","raw_affiliation_strings":["Macao Polytechnic University,Macao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Macao,China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042546702","display_name":"Zhengxuan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Zhengxuan Chen","raw_affiliation_strings":["Macao Polytechnic University,Macao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Macao,China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113355158","display_name":"Nuoer Long","orcid":"https://orcid.org/0009-0003-8719-7722"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Nuoer Long","raw_affiliation_strings":["Macao Polytechnic University,Macao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Macao,China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106807992","display_name":"Kin-Seong Un","orcid":null},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Kin-Seong Un","raw_affiliation_strings":["Macao Polytechnic University,Macao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Macao,China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007102073","display_name":"Zhuolin Li","orcid":"https://orcid.org/0009-0003-3861-5879"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Zhuolin Li","raw_affiliation_strings":["Macao Polytechnic University,Macao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Macao,China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005571749","display_name":"Shaobin Chen","orcid":"https://orcid.org/0000-0002-2306-1856"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Shaobin Chen","raw_affiliation_strings":["Macao Polytechnic University,Macao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Macao,China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100712425","display_name":"Tao Tan","orcid":"https://orcid.org/0009-0003-7977-9749"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Tao Tan","raw_affiliation_strings":["Macao Polytechnic University,Macao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Macao,China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089368710","display_name":"Chan\u2013Tong Lam","orcid":"https://orcid.org/0000-0002-8022-7744"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chan-Tong Lam","raw_affiliation_strings":["Macao Polytechnic University,Macao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Macao,China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101549114","display_name":"Yue Sun","orcid":"https://orcid.org/0000-0003-0301-5112"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Yue Sun","raw_affiliation_strings":["Macao Polytechnic University,Macao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Macao,China","institution_ids":["https://openalex.org/I49835588"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I49835588"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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":0.9958000183105469,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6818699836730957},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6599956154823303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6338282823562622},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5745551586151123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47441431879997253},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4605637192726135},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4139999449253082},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09912469983100891},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.0659809410572052}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6818699836730957},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6599956154823303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6338282823562622},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5745551586151123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47441431879997253},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4605637192726135},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4139999449253082},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09912469983100891},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0659809410572052},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew63481.2024.10645365","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmew63481.2024.10645365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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":16,"referenced_works":["https://openalex.org/W2111078031","https://openalex.org/W2798354744","https://openalex.org/W2962907723","https://openalex.org/W2963017553","https://openalex.org/W2963393391","https://openalex.org/W2964089981","https://openalex.org/W2979933490","https://openalex.org/W3034743747","https://openalex.org/W3035339529","https://openalex.org/W3166396011","https://openalex.org/W3186024896","https://openalex.org/W3205786327","https://openalex.org/W4224285690","https://openalex.org/W4385571423","https://openalex.org/W4385573866","https://openalex.org/W4390873341"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W2793967660","https://openalex.org/W2515288625"],"abstract_inverted_index":{"Video":[0],"grounding,":[1],"which":[2,43],"involves":[3],"aligning":[4],"spoken":[5],"language":[6],"descriptions":[7],"with":[8],"corresponding":[9],"video":[10,149],"segments,":[11],"plays":[12],"a":[13,65,85,92],"critical":[14],"role":[15],"in":[16,27,122,142],"advancing":[17],"multimedia":[18],"content":[19],"understanding.":[20],"De-spite":[21],"progress":[22],"enabled":[23],"by":[24,51],"deep":[25],"learning":[26],"multi-modal":[28,87],"learning,":[29],"this":[30,62,117],"task":[31],"faces":[32],"significant":[33,120],"challenges":[34],"within":[35],"complex":[36,107],"datasets":[37],"such":[38],"as":[39,126,128],"the":[40,52,70,75,78,106,110,137,144],"Animal":[41,111],"Kingdom,":[42],"features":[44],"diverse":[45],"and":[46,58,84,99,124],"intricate":[47],"natural":[48,147],"scenes.":[49],"Motivated":[50],"need":[53],"to":[54,95],"en-hance":[55],"cross-modal":[56],"alignment":[57],"achieve":[59],"robust":[60],"localization,":[61],"study":[63],"introduces":[64],"refined":[66],"approach":[67,141],"based":[68],"on":[69,116],"Uni-VTG":[71],"model.":[72],"We":[73],"enhance":[74],"model":[76],"through":[77],"integration":[79],"of":[80,109,139,146],"dual-path":[81,93],"modality":[82],"fusion":[83],"sophisticated":[86],"encoder.":[88],"This":[89],"method":[90],"employs":[91],"mechanism":[94],"effectively":[96],"fuse":[97],"modalities":[98],"an":[100,129],"advanced":[101],"training":[102],"strategy":[103],"tailored":[104],"for":[105],"requirements":[108],"King-dom":[112],"dataset.":[113],"The":[114],"evaluation":[115],"dataset":[118],"shows":[119],"improvements":[121],"accuracy":[123],"robustness,":[125],"well":[127],"enhanced":[130],"mean":[131],"Intersection":[132],"over":[133],"Union":[134],"(IoU),":[135],"validating":[136],"effectiveness":[138],"our":[140],"navigating":[143],"complexities":[145],"environment":[148],"grounding.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
