{"id":"https://openalex.org/W4415251606","doi":"https://doi.org/10.1109/icmla66185.2025.00182","title":"Adversarially-Refined VQ-GAN with Dense Motion Tokenization for Spatio-Temporal Heatmaps","display_name":"Adversarially-Refined VQ-GAN with Dense Motion Tokenization for Spatio-Temporal Heatmaps","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4415251606","doi":"https://doi.org/10.1109/icmla66185.2025.00182"},"language":"en","primary_location":{"id":"doi:10.1109/icmla66185.2025.00182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.19252","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032620023","display_name":"Gabriel Maldonado","orcid":null},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gabriel Maldonado","raw_affiliation_strings":["University of North Carolina at Charlotte,Charlotte,NC,USA"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Charlotte,NC,USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036256794","display_name":"Narges Rashvand","orcid":"https://orcid.org/0009-0000-9582-2186"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Narges Rashvand","raw_affiliation_strings":["University of North Carolina at Charlotte,Charlotte,NC,USA"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Charlotte,NC,USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035732467","display_name":"Armin Danesh Pazho","orcid":"https://orcid.org/0000-0003-1366-1919"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Armin Danesh Pazho","raw_affiliation_strings":["University of North Carolina at Charlotte,Charlotte,NC,USA"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Charlotte,NC,USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055615560","display_name":"Ghazal Alinezhad Noghre","orcid":"https://orcid.org/0000-0001-7749-9047"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghazal Alinezhad Noghre","raw_affiliation_strings":["University of North Carolina at Charlotte,Charlotte,NC,USA"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Charlotte,NC,USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089753513","display_name":"Vinit Katariya","orcid":"https://orcid.org/0009-0003-9922-6041"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinit Katariya","raw_affiliation_strings":["University of Wyoming,Laramie,WY,USA"],"affiliations":[{"raw_affiliation_string":"University of Wyoming,Laramie,WY,USA","institution_ids":["https://openalex.org/I12834331"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063615699","display_name":"Hamed Tabkhi","orcid":"https://orcid.org/0000-0001-5420-1121"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Tabkhi","raw_affiliation_strings":["University of North Carolina at Charlotte,Charlotte,NC,USA"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte,Charlotte,NC,USA","institution_ids":["https://openalex.org/I102149020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032620023"],"corresponding_institution_ids":["https://openalex.org/I102149020"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15031703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1189","last_page":"1196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.983299970626831,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.983299970626831,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9729999899864197,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9670000076293945,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6570000052452087},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.6173999905586243},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5113999843597412},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.5092999935150146},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4106000065803528},{"id":"https://openalex.org/keywords/motion-analysis","display_name":"Motion analysis","score":0.38690000772476196},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.3652999997138977},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.36399999260902405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949000000953674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7135999798774719},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6570000052452087},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6173999905586243},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5491999983787537},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4106000065803528},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36399999260902405},{"id":"https://openalex.org/C2777749129","wikidata":"https://www.wikidata.org/wiki/Q17148469","display_name":"Robust principal component analysis","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3276999890804291},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icmla66185.2025.00182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.19252","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.19252","pdf_url":"https://arxiv.org/pdf/2509.19252","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.19252","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.19252","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.19252","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.19252","pdf_url":"https://arxiv.org/pdf/2509.19252","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Continuous":[0],"human":[1,53],"motion":[2,28,41,59,69,116,121,152],"understanding":[3],"remains":[4],"a":[5,112,127,136],"core":[6],"challenge":[7],"in":[8,75],"computer":[9],"vision":[10],"due":[11],"to":[12],"its":[13],"high":[14],"dimensionality":[15],"and":[16,21,71,100],"inherent":[17],"redundancy.":[18],"Efficient":[19],"compression":[20],"representation":[22],"are":[23],"crucial":[24],"for":[25,43,141,158],"analyzing":[26],"complex":[27],"dynamics.":[29],"In":[30],"this":[31,159],"work,":[32],"we":[33],"introduce":[34],"an":[35],"adversarially-refined":[36],"VQ-GAN":[37],"framework":[38],"with":[39,61,126],"dense":[40,58,108],"tokenization":[42,60,109],"compressing":[44],"spatio-temporal":[45],"heatmaps":[46],"while":[47,131],"preserving":[48],"the":[49,81,94],"fine-grained":[50],"traces":[51],"of":[52,89,115],"motion.":[54],"Our":[55,78],"approach":[56],"combines":[57],"adversarial":[62],"refinement,":[63],"which":[64],"eliminates":[65],"reconstruction":[66],"artifacts":[67],"like":[68],"smearing":[70],"temporal":[72,102],"misalignment":[73],"observed":[74],"non-adversarial":[76],"baselines.":[77],"experiments":[79],"on":[80],"CMU":[82],"Panoptic":[83],"dataset":[84],"[7]":[85],"provide":[86],"conclusive":[87],"evidence":[88],"our":[90,107],"method\u2019s":[91],"superiority,":[92],"outperforming":[93],"dVAE":[95],"baseline":[96],"by":[97,104],"9.31%":[98],"SSIM":[99],"reducing":[101],"instability":[103],"37.1%.":[105],"Furthermore,":[106],"strategy":[110],"enables":[111],"novel":[113],"analysis":[114,153],"complexity,":[117],"revealing":[118],"that":[119],"2D":[120],"can":[122],"be":[123],"optimally":[124],"represented":[125],"compact":[128],"128-token":[129],"vocabulary,":[130],"3D":[132],"motion\u2019s":[133],"complexity":[134],"demands":[135],"much":[137],"larger":[138],"1024-token":[139],"codebook":[140],"faithful":[142],"reconstruction.":[143],"These":[144],"results":[145],"establish":[146],"practical":[147],"deployment":[148],"feasibility":[149],"across":[150],"diverse":[151],"applications.":[154],"The":[155],"code":[156],"base":[157],"work":[160],"is":[161],"available":[162],"at":[163],"https://github.com/TeCSAR-UNCC/Pose-Quantization.":[164]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2025-10-16T00:00:00"}