{"id":"https://openalex.org/W7143398107","doi":"https://doi.org/10.1109/tip.2026.3676899","title":"Spatial-Temporal Scene Graph Generation for Open-Vocabulary Multiple Object Tracking","display_name":"Spatial-Temporal Scene Graph Generation for Open-Vocabulary Multiple Object Tracking","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7143398107","doi":"https://doi.org/10.1109/tip.2026.3676899","pmid":"https://pubmed.ncbi.nlm.nih.gov/41911147"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3676899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3676899","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/A5130930993","display_name":"Guangyao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyao Li","raw_affiliation_strings":["Fujian Key Laboratory of Sensing and Computing for Smart City, the School of Informatics, and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0004-2510-6378","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Sensing and Computing for Smart City, the School of Informatics, and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130975433","display_name":"Siping Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siping Zhuang","raw_affiliation_strings":["Fujian Key Laboratory of Sensing and Computing for Smart City, the School of Informatics, and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0001-9708-6925","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Sensing and Computing for Smart City, the School of Informatics, and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042786745","display_name":"Yajun Jian","orcid":"https://orcid.org/0000-0003-3068-6771"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yajun Jian","raw_affiliation_strings":["Fujian Key Laboratory of Sensing and Computing for Smart City, the School of Informatics, and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Sensing and Computing for Smart City, the School of Informatics, and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Fujian Key Laboratory of Sensing and Computing for Smart City, the School of Informatics, and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-3674-7160","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Sensing and Computing for Smart City, the School of Informatics, and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129658010","display_name":"Hanzi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanzi Wang","raw_affiliation_strings":["Fujian Key Laboratory of Sensing and Computing for Smart City, the School of Informatics, and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-6913-9786","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Sensing and Computing for Smart City, the School of Informatics, and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31869698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"3437","last_page":"3450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8970999717712402,"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":0.8970999717712402,"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/T12031","display_name":"Speech and dialogue systems","score":0.02810000069439411,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.013000000268220901,"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/image-segmentation","display_name":"Image segmentation","score":0.459199994802475},{"id":"https://openalex.org/keywords/cut","display_name":"Cut","score":0.4546000063419342},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4359000027179718},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4357999861240387},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4052000045776367},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3991999924182892},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3937999904155731},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36399999260902405},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.3483999967575073}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7457000017166138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.725600004196167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6047000288963318},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.459199994802475},{"id":"https://openalex.org/C5134670","wikidata":"https://www.wikidata.org/wiki/Q1626444","display_name":"Cut","level":4,"score":0.4546000063419342},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4359000027179718},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4052000045776367},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3937999904155731},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C32283439","wikidata":"https://www.wikidata.org/wiki/Q1407014","display_name":"Radar tracker","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C159246509","wikidata":"https://www.wikidata.org/wiki/Q5428725","display_name":"Factor graph","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26339998841285706},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.2515000104904175},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3676899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3676899","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:41911147","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41911147","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":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6619552373886108}],"awards":[{"id":"https://openalex.org/G3877124827","display_name":null,"funder_award_id":"U25A20531","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4031016800","display_name":null,"funder_award_id":"3502Z20241029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4782616423","display_name":null,"funder_award_id":"62372388","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8872334155","display_name":null,"funder_award_id":"3502Z20241027","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"multiple":[1],"object":[2,21,63],"tracking":[3,68,211,230],"(MOT)":[4],"aims":[5],"to":[6,47,94,162,205],"track":[7],"arbitrary":[8],"objects":[9,112,170],"in":[10,20,32,56,66,70],"the":[11,25,57,127,132,139,147,164,200,203,222],"real":[12],"world.":[13],"Although":[14],"significant":[15],"progress":[16],"has":[17],"been":[18],"achieved":[19],"classification":[22],"by":[23,97,121],"leveraging":[24],"knowledge":[26],"from":[27,126,138,189],"large":[28],"vision-language":[29],"models,":[30],"advances":[31],"data":[33,95],"association":[34,96],"for":[35],"open-vocabulary":[36,80],"MOT":[37,81,219],"remain":[38],"limited.":[39],"Existing":[40],"methods":[41],"primarily":[42],"rely":[43],"on":[44,216],"appearance":[45],"cues":[46,52],"establish":[48],"associations.":[49],"However,":[50],"these":[51],"are":[53,144],"often":[54],"unreliable":[55],"face":[58],"of":[59,131,166,202,224],"occlusions":[60],"and":[61,108,141,155,171,192],"ambiguous":[62],"appearances,":[64],"resulting":[65],"suboptimal":[67],"performance":[69],"complex":[71],"scenarios.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76,174],"propose":[77,175],"a":[78,90,99,176],"novel":[79],"method,":[82,226],"Spatial-temporal":[83,100],"Scene":[84,101],"Graph":[85,102],"Tracker":[86],"(SSGTrack),":[87],"which":[88,227],"introduces":[89],"fundamentally":[91],"different":[92],"approach":[93],"building":[98],"(SSG)":[103],"that":[104,186],"captures":[105],"rich":[106],"semantic":[107],"spatial":[109],"relationships":[110,120],"between":[111],"across":[113],"adjacent":[114],"frames.":[115],"Specifically,":[116],"SSGTrack":[117],"constructs":[118],"proposal-level":[119],"extracting":[122],"diverse":[123],"contextual":[124],"information":[125],"multi-head":[128],"self-attention":[129],"layers":[130],"Transformer":[133],"decoder.":[134],"These":[135],"relationships,":[136],"derived":[137],"keyframe":[140],"reference":[142],"frame,":[143],"compressed":[145],"into":[146],"compact":[148],"SSG,":[149],"where":[150],"nodes":[151],"represent":[152],"detected":[153],"objects,":[154],"edge":[156],"weights":[157],"denote":[158],"frame-level":[159],"connectivity.":[160],"Furthermore,":[161],"address":[163],"challenge":[165],"differentiating":[167],"visually":[168],"similar":[169],"background":[172,184],"distractors,":[173],"Context-aware":[177],"Contrastive":[178],"Learning":[179],"(CCL)":[180],"strategy.":[181],"By":[182],"identifying":[183],"features":[185],"significantly":[187],"differ":[188],"positive":[190],"samples":[191],"incorporating":[193],"them":[194],"as":[195],"negative":[196],"samples,":[197],"CCL":[198],"enhances":[199],"ability":[201],"model":[204],"learn":[206],"discriminative":[207],"representations,":[208],"thus":[209],"improving":[210],"robustness.":[212],"Extensive":[213],"experiments":[214],"conducted":[215],"several":[217],"challenging":[218],"benchmarks":[220],"demonstrate":[221],"effectiveness":[223],"our":[225],"achieves":[228],"superior":[229],"performance.":[231]},"counts_by_year":[],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2026-03-31T00:00:00"}