{"id":"https://openalex.org/W4400033115","doi":"https://doi.org/10.1109/taslp.2024.3419438","title":"Multi-Granularity Feature Fusion for Image-Guided Story Ending Generation","display_name":"Multi-Granularity Feature Fusion for Image-Guided Story Ending Generation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400033115","doi":"https://doi.org/10.1109/taslp.2024.3419438"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3419438","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2024.3419438","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5033158939","display_name":"Pijian Li","orcid":"https://orcid.org/0009-0005-1924-5248"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pijian Li","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":"https://orcid.org/0009-0005-1924-5248","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061381102","display_name":"Qingbao Huang","orcid":"https://orcid.org/0000-0001-7691-347X"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingbao Huang","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":"https://orcid.org/0000-0001-7691-347X","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033393942","display_name":"Zhigang Li","orcid":"https://orcid.org/0000-0003-1195-3096"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Li","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089123257","display_name":"Yi Cai","orcid":"https://orcid.org/0000-0002-1767-789X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cai","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1767-789X","affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062793914","display_name":"Feng Shuang","orcid":"https://orcid.org/0000-0002-4733-4732"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Shuang","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China","School of Electrical Engineering, Guangxi University, China"],"raw_orcid":"https://orcid.org/0000-0002-4733-4732","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]},{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Department of Computing, Hong Kong Polytechnic University, Hong Kong SAR, China","Department of Computing, Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-3370-471X","affiliations":[{"raw_affiliation_string":"Department of Computing, Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing, Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07898519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"3437","last_page":"3449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9969000220298767,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9916999936103821,"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/granularity","display_name":"Granularity","score":0.7924863696098328},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6637628078460693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6389162540435791},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5634666085243225},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5492633581161499},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49221745133399963},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4812602698802948},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4586280882358551},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.4433775246143341},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05613991618156433},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.04722863435745239}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.7924863696098328},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6637628078460693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6389162540435791},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5634666085243225},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5492633581161499},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49221745133399963},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4812602698802948},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4586280882358551},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.4433775246143341},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05613991618156433},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.04722863435745239},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3419438","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2024.3419438","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1473307615","display_name":null,"funder_award_id":"2022GXNSFAA035627","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"},{"id":"https://openalex.org/G6770297356","display_name":null,"funder_award_id":"62276072","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8189774080","display_name":null,"funder_award_id":"62076100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322768","display_name":"Natural Science Foundation of Guangxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W12154863","https://openalex.org/W25648700","https://openalex.org/W1902237438","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2194775991","https://openalex.org/W2347880541","https://openalex.org/W2479423890","https://openalex.org/W2561529111","https://openalex.org/W2811484521","https://openalex.org/W2883112830","https://openalex.org/W2887684398","https://openalex.org/W2888213795","https://openalex.org/W2888597673","https://openalex.org/W2889002152","https://openalex.org/W2914699769","https://openalex.org/W2914855263","https://openalex.org/W2950028154","https://openalex.org/W2953147883","https://openalex.org/W2963033554","https://openalex.org/W2963464104","https://openalex.org/W2963668753","https://openalex.org/W2963683498","https://openalex.org/W2963829244","https://openalex.org/W2963951835","https://openalex.org/W2965353350","https://openalex.org/W2965962253","https://openalex.org/W2966774251","https://openalex.org/W2970102799","https://openalex.org/W2973007848","https://openalex.org/W2978588083","https://openalex.org/W2997419939","https://openalex.org/W3014521650","https://openalex.org/W3087871082","https://openalex.org/W3092234597","https://openalex.org/W3094098469","https://openalex.org/W3099807503","https://openalex.org/W3101632758","https://openalex.org/W3102302204","https://openalex.org/W3102401511","https://openalex.org/W3104402684","https://openalex.org/W3108364329","https://openalex.org/W3113680985","https://openalex.org/W3125903078","https://openalex.org/W3146753603","https://openalex.org/W3153469116","https://openalex.org/W3158234888","https://openalex.org/W3165424177","https://openalex.org/W3166849521","https://openalex.org/W3173770572","https://openalex.org/W3174225409","https://openalex.org/W3174865495","https://openalex.org/W3175530221","https://openalex.org/W3178145571","https://openalex.org/W3193528885","https://openalex.org/W3215261744","https://openalex.org/W4210263566","https://openalex.org/W4221143434","https://openalex.org/W4221151670","https://openalex.org/W4224308021","https://openalex.org/W4224736673","https://openalex.org/W4285262944","https://openalex.org/W4285306620","https://openalex.org/W4301001724","https://openalex.org/W4304092489","https://openalex.org/W4385245566","https://openalex.org/W4386566756","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6752988165","https://openalex.org/W6755207826","https://openalex.org/W6761205521","https://openalex.org/W6845401030","https://openalex.org/W6856800273"],"related_works":["https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969","https://openalex.org/W2284201331","https://openalex.org/W2095903272","https://openalex.org/W1989561795"],"abstract_inverted_index":{"Image-guided":[0],"Story":[1],"Ending":[2],"Generation":[3],"aims":[4],"at":[5],"generating":[6],"a":[7,13,89,131,193],"reasonable":[8],"and":[9,16,49,53,159,167,183,196],"logical":[10,43,195],"ending":[11,73],"given":[12,82],"story":[14,33,47],"context":[15,34,48],"an":[17,36,109],"ending-related":[18],"image.":[19],"The":[20],"existing":[21],"models":[22,209],"have":[23,54],"achieved":[24],"some":[25],"success":[26],"by":[27,144],"fusing":[28],"global":[29,125,168],"image":[30,51,63,110,120,126,138],"features":[31,60,117,139,161,182],"with":[32,75],"through":[35],"attention":[37],"mechanism.":[38],"However,":[39],"they":[40],"ignore":[41],"the":[42,46,50,57,62,71,76,81,115,119,124,137,141,146,152,157,179,187,207],"relationship":[44],"between":[45],"regions,":[52],"not":[55],"considered":[56],"high-level":[58],"semantic":[59],"of":[61,80,118,123,140,176,186],"such":[64],"as":[65,121,190],"visual":[66,160,184],"sentiment.":[67],"This":[68],"may":[69],"cause":[70],"generated":[72],"inconsistent":[74],"logic":[77],"or":[78],"sentiment":[79,111,116,185],"information.":[83],"In":[84],"this":[85,103],"paper,":[86],"we":[87,106,155],"propose":[88],"<bold":[90,96],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[91,93,97],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</b>ulti-<bold":[92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">G</b>ranularity":[94],"feature":[95],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">F</b>usion":[98],"(MGF)":[99],"model":[100,172,205],"to":[101,113,135,151,191],"solve":[102],"problem.":[104],"Concretely,":[105],"first":[107],"employ":[108],"extractor":[112],"grasp":[114],"part":[122],"features.":[127],"We":[128],"then":[129],"design":[130],"scene":[132,147],"subgraph":[133,148],"selector":[134],"capture":[136],"key":[142,180],"region":[143,165,181],"picking":[145],"most":[149,211],"relevant":[150],"context.":[153],"Finally,":[154],"fuse":[156],"textual":[158],"from":[162],"object":[163],"level,":[164,166,169],"respectively.":[170],"Our":[171],"is":[173],"thereby":[174],"capable":[175],"effectively":[177],"capturing":[178],"image,":[188],"so":[189],"generate":[192],"more":[194],"sentimental":[197],"ending.":[198],"Experimental":[199],"results":[200],"show":[201],"that":[202],"our":[203],"MGF":[204],"outperforms":[206],"state-of-the-art":[208],"on":[210],"metrics.":[212]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}