{"id":"https://openalex.org/W7134131964","doi":"https://doi.org/10.1109/tcsvt.2026.3671271","title":"Occlusion-Aware Multi-Object Tracking via Joint Diffusion Motion Prediction and Appearance Purification","display_name":"Occlusion-Aware Multi-Object Tracking via Joint Diffusion Motion Prediction and Appearance Purification","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7134131964","doi":"https://doi.org/10.1109/tcsvt.2026.3671271"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3671271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3671271","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5009598331","display_name":"Wen Guo","orcid":"https://orcid.org/0000-0002-3691-4942"},"institutions":[{"id":"https://openalex.org/I83776822","display_name":"Shandong Institute of Business and Technology","ror":"https://ror.org/03rrkrc24","country_code":"CN","type":"education","lineage":["https://openalex.org/I83776822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Guo","raw_affiliation_strings":["School of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, China"],"raw_orcid":"https://orcid.org/0000-0002-3691-4942","affiliations":[{"raw_affiliation_string":"School of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, China","institution_ids":["https://openalex.org/I83776822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128320924","display_name":"Tuo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I83776822","display_name":"Shandong Institute of Business and Technology","ror":"https://ror.org/03rrkrc24","country_code":"CN","type":"education","lineage":["https://openalex.org/I83776822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tuo Wang","raw_affiliation_strings":["School of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, China"],"raw_orcid":"https://orcid.org/0009-0006-1191-167X","affiliations":[{"raw_affiliation_string":"School of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, China","institution_ids":["https://openalex.org/I83776822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069767386","display_name":"Junyu Gao","orcid":"https://orcid.org/0000-0002-1340-443X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Gao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianzhu Zhang","orcid":"https://orcid.org/0000-0003-1856-9564"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzhu Zhang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-1856-9564","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128306459","display_name":"Changsheng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8343-9665","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.27953629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"7","first_page":"10852","last_page":"10867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.4352000057697296,"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":0.4352000057697296,"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/T11448","display_name":"Face recognition and analysis","score":0.3402000069618225,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.03750000149011612,"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/tracking","display_name":"Tracking (education)","score":0.6032000184059143},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5512999892234802},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4790000021457672},{"id":"https://openalex.org/keywords/active-appearance-model","display_name":"Active appearance model","score":0.45419999957084656},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.37940001487731934},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.37540000677108765},{"id":"https://openalex.org/keywords/match-moving","display_name":"Match moving","score":0.33489999175071716},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3240000009536743}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6732000112533569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050000190734863},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6032000184059143},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5329999923706055},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.45419999957084656},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2777000069618225},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C32283439","wikidata":"https://www.wikidata.org/wiki/Q1407014","display_name":"Radar tracker","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.25369998812675476},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3671271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3671271","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2407878474","display_name":null,"funder_award_id":"62072286","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":{"Occlusion,":[0],"a":[1,86,139],"pervasive":[2],"challenge":[3],"in":[4,33],"Multi-Object":[5,72],"Tracking":[6,73],"(MOT)":[7],"within":[8],"complex":[9],"scenes,":[10],"severely":[11],"degrades":[12],"tracking":[13,179],"performance.":[14],"Current":[15],"methods":[16],"still":[17],"face":[18],"numerous":[19],"problems":[20],"when":[21],"handling":[22],"occlusions.":[23,37],"Motion":[24,77,88],"prediction":[25],"struggles":[26],"to":[27,51,101,134,150],"accommodate":[28],"diverse":[29],"motion":[30,107],"patterns,":[31],"resulting":[32],"failure":[34],"during":[35,154],"short-term":[36,84],"Concurrently,":[38],"appearance":[39],"features":[40],"possess":[41],"insufficient":[42],"discriminative":[43],"power":[44],"under":[45,63,105],"occluded":[46],"conditions,":[47,66],"which":[48,94],"frequently":[49],"leads":[50],"identity":[52],"switches":[53],"following":[54],"long-term":[55,110],"occlusion.":[56],"To":[57],"enhance":[58,135],"the":[59,112,122,125,147,163,171],"performance":[60],"of":[61,129],"MOT":[62],"such":[64],"challenging":[65],"we":[67],"propose":[68],"an":[69],"innovative":[70],"Occlusion-Aware":[71],"via":[74],"Joint":[75],"Diffusion":[76,87],"Prediction":[78],"and":[79,97,166],"Appearance":[80,114],"Purification":[81,115],"(OAMOT).":[82],"For":[83,109],"occlusions,":[85,111],"Recovery":[89],"Model":[90],"(DMRM)":[91],"is":[92,120,144],"developed,":[93],"integrates":[95],"residual":[96],"noise":[98],"diffusion":[99],"branches":[100],"recover":[102],"trajectories":[103],"precisely":[104],"varied":[106],"patterns.":[108],"SAM":[113,130],"for":[116],"ReID":[117,148],"(SAPR)":[118],"module":[119,123],"proposed;":[121],"leverages":[124],"mask":[126],"generation":[127],"mechanism":[128],"as":[131],"foreground":[132],"attention":[133,153],"feature":[136],"discriminability.":[137],"Furthermore,":[138],"Lightweight":[140],"Attention":[141],"Predictor":[142],"(LAP)":[143],"integrated":[145],"into":[146],"network":[149],"achieve":[151],"SAM-quality":[152],"inference":[155],"without":[156],"significant":[157],"computational":[158],"overhead.":[159],"Experimental":[160],"results":[161],"on":[162,190],"MOT17,":[164],"MOT20,":[165],"DanceTrack":[167],"datasets":[168],"demonstrate":[169],"that":[170],"proposed":[172],"OAMOT":[173],"method":[174],"outperforms":[175],"current":[176],"state-of-the-art":[177],"multi-object":[178],"techniques":[180],"across":[181],"multiple":[182],"evaluation":[183],"metrics.":[184],"The":[185],"code":[186],"can":[187],"be":[188],"available":[189],"https://github.com/wangtuo111/OAMOT.":[191]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-08T00:00:00"}