{"id":"https://openalex.org/W4414359951","doi":"https://doi.org/10.24963/ijcai.2025/215","title":"Wave-wise Discriminative Tracking by Phase-Amplitude Separation, Augmentation and Mixture","display_name":"Wave-wise Discriminative Tracking by Phase-Amplitude Separation, Augmentation and Mixture","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359951","doi":"https://doi.org/10.24963/ijcai.2025/215"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/215","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5004941473","display_name":"Huibin Tan","orcid":"https://orcid.org/0000-0003-4060-8793"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huibin Tan","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108853518","display_name":"Mingyu Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Cao","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006591448","display_name":"Kun Hu","orcid":"https://orcid.org/0009-0002-0831-8059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Hu","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021686580","display_name":"Xiaoming He","orcid":"https://orcid.org/0000-0003-0125-6086"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihuai He","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112177860","display_name":"Zhe Wang","orcid":"https://orcid.org/0009-0005-0633-2238"},"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":"Zhe Wang","raw_affiliation_strings":["Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348558","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-1752-5167"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060251766","display_name":"Long Lan","orcid":"https://orcid.org/0000-0002-4238-8985"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Lan","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101791333","display_name":"Mengzhu Wang","orcid":"https://orcid.org/0009-0004-9431-1383"},"institutions":[{"id":"https://openalex.org/I184843921","display_name":"Hebei University of Technology","ror":"https://ror.org/018hded08","country_code":"CN","type":"education","lineage":["https://openalex.org/I184843921"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengzhu Wang","raw_affiliation_strings":["Hebei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hebei University of Technology","institution_ids":["https://openalex.org/I184843921"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1927","last_page":"1935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13493","display_name":"Optical and Acousto-Optic Technologies","score":0.8429999947547913,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13493","display_name":"Optical and Acousto-Optic Technologies","score":0.8429999947547913,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.8378000259399414,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.8230000138282776,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/discriminative-model","display_name":"Discriminative model","score":0.8389000296592712},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.670799970626831},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6021999716758728},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4814000129699707},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.46799999475479126},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4456000030040741},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3855000138282776},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.3817000091075897}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8389000296592712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7766000032424927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.670799970626831},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5920000076293945},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5139999985694885},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4814000129699707},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3855000138282776},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C125245961","wikidata":"https://www.wikidata.org/wiki/Q221656","display_name":"Brightness","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C2777316791","wikidata":"https://www.wikidata.org/wiki/Q17105246","display_name":"Phase congruency","level":3,"score":0.3776000142097473},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29409998655319214},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/215","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Distinguishing":[0],"key":[1],"features":[2,62,83,116,135],"in":[3,117],"complex":[4],"visual":[5],"tasks":[6],"is":[7,99],"challenging.":[8],"A":[9],"novel":[10],"approach":[11],"treats":[12],"image":[13,45],"patches":[14],"(tokens)":[15],"as":[16],"waves.":[17,132],"By":[18],"using":[19],"both":[20],"phase":[21,80,147,156],"and":[22,28,35,67,81,91,108,121,130,151,160,166,173],"amplitude,":[23],"it":[24],"captures":[25],"richer":[26],"semantics":[27],"specific":[29],"invariances":[30],"compared":[31],"to":[32,78,127],"pixel-based":[33],"methods,":[34],"allows":[36],"for":[37,42,170],"feature":[38],"fusion":[39],"across":[40],"regions":[41],"a":[43,72],"holistic":[44],"representation.":[46],"Based":[47],"on":[48,180],"this,":[49],"we":[50,70],"propose":[51],"the":[52,114,118,122,139,145,164,184],"Wave-wise":[53,96],"Discriminative":[54],"Transformer":[55],"Tracker":[56],"(WDT).":[57],"During":[58],"tracking,":[59],"WDT":[60],"represents":[61],"via":[63],"phase-amplitude":[64],"separation,":[65],"enhancement,":[66],"mixture.":[68],"First,":[69],"designed":[71],"Mutual":[73],"Exclusive":[74],"Phase-Amplitude":[75,105],"Extractor":[76],"(MEPAE)":[77],"separate":[79],"amplitude":[82],"with":[84,102],"distinct":[85],"semantics,":[86],"representing":[87],"spatial":[88],"target":[89],"info":[90],"background":[92],"brightness":[93],"respectively.":[94],"Then,":[95],"Feature":[97,106],"Augmentation":[98,107],"carried":[100],"out":[101],"two":[103],"submodules:":[104],"Mixture.":[109],"The":[110,133],"augmentation":[111],"module":[112,124],"disrupts":[113],"separated":[115],"same":[119,146],"batch,":[120],"mixture":[123],"recombines":[125],"them":[126],"generate":[128],"positive":[129],"negative":[131,152,174],"original":[134,140],"are":[136],"aggregated":[137],"into":[138],"wave.":[141],"Positive":[142],"waves":[143,153],"have":[144,154],"but":[148],"different":[149,155],"amplitudes,":[150],"components.":[157],"Finally,":[158],"self-supervised":[159],"tracking-supervised":[161],"losses":[162],"guide":[163],"global":[165],"local":[167],"representation":[168],"learning":[169],"original,":[171],"positive,":[172],"waves,":[175],"enhancing":[176],"wave-level":[177],"discrimination.":[178],"Experiments":[179],"five":[181],"benchmarks":[182],"prove":[183],"effectiveness":[185],"of":[186],"our":[187],"method.":[188]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}