{"id":"https://openalex.org/W7204460469","doi":"https://doi.org/10.1109/tpami.2026.3728164","title":"Diff-MM: Exploring Pre-Trained Text-to-Image Generation Models for Unified Multi-Modal Object Tracking","display_name":"Diff-MM: Exploring Pre-Trained Text-to-Image Generation Models for Unified Multi-Modal Object Tracking","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204460469","doi":"https://doi.org/10.1109/tpami.2026.3728164","pmid":"https://pubmed.ncbi.nlm.nih.gov/42658709"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3728164","doi":"https://doi.org/10.1109/tpami.2026.3728164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3728164","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","doyens","jufo-3","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"volume":null,"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/A5088499366","display_name":"Shiyu Xuan","orcid":"https://orcid.org/0000-0001-9950-6025","observed_orcids":["https://orcid.org/0000-0001-9950-6025"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Xuan","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017096005","display_name":"Zechao Li","orcid":"https://orcid.org/0000-0002-5341-5985","observed_orcids":["https://orcid.org/0000-0002-5341-5985","https://orcid.org/0000-0001-5698-6022"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zechao Li","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126307307","display_name":"Jinhui Tang","orcid":"https://orcid.org/0000-0001-9008-222X","observed_orcids":["https://orcid.org/0000-0001-9008-222X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinhui Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004667502","display_name":"Maocheng Zhao","orcid":"https://orcid.org/0000-0002-3940-5326","observed_orcids":["https://orcid.org/0000-0002-3940-5326"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maocheng Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.6150944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"PP","issue":null,"first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9961000084877014,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9961000084877014,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0010999999940395355,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pre-trained-diffusion-models","display_name":"pre-trained diffusion models","score":0.7860000133514404},{"id":"https://openalex.org/keywords/stable-diffusion","display_name":"Stable Diffusion","score":0.9649999737739563},{"id":"https://openalex.org/keywords/parallel-feature-extraction","display_name":"parallel feature extraction","score":0.765999972820282},{"id":"https://openalex.org/keywords/depth-tracking","display_name":"depth tracking","score":0.5479999780654907},{"id":"https://openalex.org/keywords/thermal-infrared-tracking","display_name":"thermal infrared tracking","score":0.9850000143051147}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7221999764442444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6948000192642212},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6703000068664551},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.38749998807907104},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.37049999833106995},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.33009999990463257},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3116999864578247},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C32283439","wikidata":"https://www.wikidata.org/wiki/Q1407014","display_name":"Radar tracker","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3728164","doi":"https://doi.org/10.1109/tpami.2026.3728164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3728164","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","doyens","jufo-3","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:42658709","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42658709","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,"listed_in":[],"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 pattern analysis and machine intelligence","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417301612","https://openalex.org/W4402753948","https://openalex.org/W7160447221","https://openalex.org/W4410742003","https://openalex.org/W4399852316","https://openalex.org/W4398796647","https://openalex.org/W7202152114","https://openalex.org/W4367369809","https://openalex.org/W7161998831","https://openalex.org/W7133309892"],"abstract_inverted_index":{"Multi-modal":[0],"object":[1,115],"tracking":[2,27,99],"integrates":[3],"auxiliary":[4,44],"modalities":[5,45],"such":[6],"as":[7,97],"depth,":[8],"thermal":[9],"infrared,":[10],"event":[11],"flow,":[12],"and":[13,40,167],"language":[14],"to":[15,42,127],"provide":[16],"additional":[17],"information":[18,130],"beyond":[19],"RGB":[20],"images,":[21],"showing":[22],"great":[23],"potential":[24],"in":[25,29,140],"improving":[26],"stabilization":[28],"complex":[30],"scenarios.":[31],"Existing":[32],"methods":[33,61],"typically":[34],"start":[35],"from":[36,47],"an":[37],"RGB-based":[38],"tracker":[39,74,148],"learn":[41],"understand":[43],"only":[46],"training":[48,55],"data.":[49],"Constrained":[50],"by":[51,76,188],"the":[52,57,78,83,90,103,136,141,160,172],"limited":[53],"multi-modal":[54,73,79,121],"data,":[56],"performance":[58,174],"of":[59,82,93,175],"these":[60],"is":[62],"unsatisfactory.":[63],"To":[64],"alleviate":[65],"this":[66,68],"limitation,":[67],"work":[69],"proposes":[70],"a":[71,98,120,146],"unified":[72,147],"Diff-MM":[75,88],"exploiting":[77],"understanding":[80],"capability":[81],"pre-trained":[84,94],"text-to-image":[85],"generation":[86,142],"model.":[87],"leverages":[89],"denoising":[91],"network":[92],"Stable":[95],"Diffusion":[96],"feature":[100,106],"extractor":[101],"through":[102],"proposed":[104,181],"parallel":[105],"extraction":[107],"pipeline,":[108],"which":[109],"enables":[110],"pairwise":[111],"image":[112],"inputs":[113],"for":[114,152],"tracking.":[116,154],"We":[117],"further":[118],"introduce":[119],"sub-module":[122],"tuning":[123],"method":[124,177],"that":[125],"learns":[126],"gain":[128],"complementary":[129],"between":[131],"different":[132],"modalities.":[133],"By":[134],"harnessing":[135],"extensive":[137],"prior":[138],"knowledge":[139],"model,":[143],"we":[144],"achieve":[145],"with":[149,179],"uniform":[150],"parameters":[151],"RGB-N/D/T/E":[153],"Extensive":[155],"experiments":[156],"are":[157],"conducted":[158],"on":[159,190],"mainstream":[161],"diffusion":[162],"model":[163],"architectures,":[164],"e.g.,":[165,183],"UNet":[166],"MMDiT.":[168],"Experimental":[169],"results":[170],"demonstrate":[171],"promising":[173],"our":[176],"compared":[178],"recently":[180],"trackers,":[182],"its":[184],"AUC":[185],"outperforms":[186],"OneTracker":[187],"10.4%":[189],"TNL2K.":[191],"Our":[192],"code":[193],"will":[194],"be":[195],"released.":[196]},"counts_by_year":[],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2026-08-28T00:00:00"}