{"id":"https://openalex.org/W7171388610","doi":"https://doi.org/10.1109/tip.2026.3715157","title":"Scene Graph-Guided SegCaptioning Transformer With Fine-Grained Alignment for Controllable Video Segmentation and Captioning","display_name":"Scene Graph-Guided SegCaptioning Transformer With Fine-Grained Alignment for Controllable Video Segmentation and Captioning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7171388610","doi":"https://doi.org/10.1109/tip.2026.3715157","pmid":"https://pubmed.ncbi.nlm.nih.gov/42507566"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3715157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3715157","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100437310","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0003-3632-4464"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Hunan University"],"raw_orcid":"https://orcid.org/0000-0003-3632-4464","affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100603557","display_name":"Jin Yuan","orcid":"https://orcid.org/0000-0002-9600-7789"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Yuan","raw_affiliation_strings":["Hunan University"],"raw_orcid":"https://orcid.org/0000-0002-9600-7789","affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109736534","display_name":"Binhong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"BinHong Yang","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362298","display_name":"Xuan Liu","orcid":"https://orcid.org/0000-0002-1652-2466"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Liu","raw_affiliation_strings":["Hunan University"],"raw_orcid":"https://orcid.org/0000-0002-1652-2466","affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047903714","display_name":"Qianjun Zhang","orcid":"https://orcid.org/0000-0002-6607-7102"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianjun Zhang","raw_affiliation_strings":["Southwest Jiaotong University"],"raw_orcid":"https://orcid.org/0009-0009-7955-3073","affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102730412","display_name":"Yuyi Wang","orcid":"https://orcid.org/0000-0001-7273-9873"},"institutions":[{"id":"https://openalex.org/I4210126257","display_name":"CRRC (China)","ror":"https://ror.org/033g21894","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126257"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyi Wang","raw_affiliation_strings":["CRRC Zhuzhou Institute Company Ltd"],"raw_orcid":"https://orcid.org/0000-0001-7273-9873","affiliations":[{"raw_affiliation_string":"CRRC Zhuzhou Institute Company Ltd","institution_ids":["https://openalex.org/I4210126257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396723","display_name":"Zhiyong Li","orcid":"https://orcid.org/0000-0001-9720-5915"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Li","raw_affiliation_strings":["Hunan University"],"raw_orcid":"https://orcid.org/0000-0001-9720-5915","affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":"https://orcid.org/0000-0001-7374-8739","affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77759111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"8093","last_page":"8106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8622999787330627,"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":0.8622999787330627,"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":0.03700000047683716,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.02199999988079071,"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/closed-captioning","display_name":"Closed captioning","score":0.7197999954223633},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5817999839782715},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5587000250816345},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.552299976348877},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3937000036239624},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.36910000443458557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541000247001648},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.741100013256073},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7197999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.708299994468689},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5817999839782715},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5587000250816345},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.552299976348877},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.36910000443458557},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.34049999713897705},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.26100000739097595}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3715157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3715157","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42507566","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42507566","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2484792918","display_name":null,"funder_award_id":"62406263","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2470139095","https://openalex.org/W2506483933","https://openalex.org/W2952132648","https://openalex.org/W2963536419","https://openalex.org/W2984862483","https://openalex.org/W3003442407","https://openalex.org/W3093026747","https://openalex.org/W3138516171","https://openalex.org/W3176514808","https://openalex.org/W3204116406","https://openalex.org/W3212555189","https://openalex.org/W4226024706","https://openalex.org/W4312355936","https://openalex.org/W4312906427","https://openalex.org/W4313007081","https://openalex.org/W4386066385","https://openalex.org/W4386072307","https://openalex.org/W4386882931","https://openalex.org/W4389169206","https://openalex.org/W4389403405","https://openalex.org/W4390872074","https://openalex.org/W4390874496","https://openalex.org/W4390874575","https://openalex.org/W4390874578","https://openalex.org/W4394593033","https://openalex.org/W4394842360","https://openalex.org/W4400032968","https://openalex.org/W4401506914","https://openalex.org/W4402660154","https://openalex.org/W4402671548","https://openalex.org/W4402702917","https://openalex.org/W4402726946","https://openalex.org/W4402727272","https://openalex.org/W4402727770","https://openalex.org/W4402754134","https://openalex.org/W4402776403","https://openalex.org/W4402780269","https://openalex.org/W4402832800","https://openalex.org/W4402952501","https://openalex.org/W4402979682","https://openalex.org/W4403791860","https://openalex.org/W4404294163","https://openalex.org/W4404739628","https://openalex.org/W4404769790","https://openalex.org/W4404893957","https://openalex.org/W4408609670","https://openalex.org/W4409129237","https://openalex.org/W4409366304","https://openalex.org/W4409369752","https://openalex.org/W4412747935","https://openalex.org/W4413145095","https://openalex.org/W4413917265","https://openalex.org/W7103749380","https://openalex.org/W7133229638","https://openalex.org/W7133240979"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2],"multimodal":[3,20,37,191],"large":[4],"models":[5],"have":[6],"significantly":[7],"bridged":[8],"the":[9,16,124,130,166],"representation":[10],"gap":[11],"between":[12,156],"diverse":[13],"modalities,":[14],"catalyzing":[15],"evolution":[17],"of":[18,26,78,169],"video":[19,27,36],"interpretation,":[21],"which":[22,63],"enhances":[23],"users'":[24],"understanding":[25],"content":[28,126],"by":[29],"generating":[30,189],"correlated":[31,83],"modalities.":[32],"However,":[33],"most":[34],"existing":[35],"interpretation":[38],"methods":[39],"primarily":[40],"concentrate":[41],"on":[42,174],"global":[43],"comprehension":[44,168],"with":[45,129],"limited":[46],"user":[47,90,115,186,195],"interaction.":[48],"To":[49],"address":[50],"this,":[51],"we":[52],"propose":[53],"a":[54,72,105,137,148],"novel":[55],"task,":[56],"Controllable":[57],"Video":[58],"Segmentation":[59],"and":[60,85,113,159,188],"Captioning":[61],"(SegCaptioning),":[62],"empowers":[64],"users":[65],"to":[66,80,103,110,141,194],"provide":[67],"specific":[68],"prompts,":[69],"such":[70],"as":[71],"bounding":[73],"box":[74],"around":[75],"an":[76,118],"object":[77],"interest,":[79],"simultaneously":[81],"generate":[82],"masks":[84],"captions":[86],"that":[87,123,179],"precisely":[88],"embody":[89],"intent.":[91],"An":[92],"innovative":[93],"framework,":[94],"Scene":[95],"Graph-guided":[96],"Fine-grained":[97,138],"SegCaptioning":[98],"Transformer":[99],"(SG-FSCFormer),":[100],"is":[101,199],"designed":[102],"integrate":[104],"Prompt-guided":[106],"Temporal":[107],"Graph":[108],"Former":[109],"effectively":[111,184],"capture":[112],"represent":[114],"intent":[116,187],"through":[117],"adaptive":[119],"prompt":[120],"adaptor,":[121],"ensuring":[122],"generated":[125],"aligns":[127],"well":[128],"user's":[131,167],"requirements.":[132],"Furthermore,":[133],"our":[134],"model":[135],"introduces":[136],"Mask-linguistic":[139],"Decoder":[140],"collaboratively":[142],"predict":[143],"high-quality":[144],"caption-mask":[145],"pairs":[146],"using":[147],"Multi-entity":[149],"Contrastive":[150],"loss,":[151],"while":[152],"providing":[153],"fine-grained":[154],"alignment":[155],"each":[157],"mask":[158],"its":[160],"corresponding":[161],"caption":[162],"tokens,":[163],"thereby":[164],"enhancing":[165],"videos.":[170],"Comprehensive":[171],"experiments":[172],"conducted":[173],"two":[175],"benchmark":[176],"datasets":[177],"demonstrate":[178],"SG-FSCFormer":[180],"achieves":[181],"remarkable":[182],"performance,":[183],"capturing":[185],"precise":[190],"outputs":[192],"tailored":[193],"specifications.":[196],"Our":[197],"code":[198],"available":[200],"at":[201],"https://github.com/XuZhang1211/SG-FSCFormer.":[202]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-28T00:00:00"}