{"id":"https://openalex.org/W4399026272","doi":"https://doi.org/10.48550/arxiv.2405.13859","title":"Accurate Quantization for Gait Representation Learning","display_name":"Accurate Quantization for Gait Representation Learning","publication_year":2024,"publication_date":"2024-05-22","ids":{"openalex":"https://openalex.org/W4399026272","doi":"https://doi.org/10.48550/arxiv.2405.13859"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2405.13859","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.13859","pdf_url":"https://arxiv.org/pdf/2405.13859","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.13859","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089519900","display_name":"Senmao Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tian, S.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078470602","display_name":"Haoyu Gao","orcid":"https://orcid.org/0009-0009-3187-2737"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, H.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113229123","display_name":"Gangyi Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, G.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087181779","display_name":"Shuyun Wang","orcid":"https://orcid.org/0000-0002-4533-1386"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, S.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100670457","display_name":"Jingjie Wang","orcid":"https://orcid.org/0000-0001-7999-2556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, J.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003076238","display_name":"Xin Yu","orcid":"https://orcid.org/0000-0002-0269-5649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, X.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101833854","display_name":"Shunli Zhang","orcid":"https://orcid.org/0000-0002-7139-9974"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, S.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5089519900"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12740","display_name":"Gait Recognition and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12740","display_name":"Gait Recognition and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.9531000256538391,"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/gait","display_name":"Gait","score":0.6164531707763672},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6001309156417847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.52785325050354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5043042898178101},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49665313959121704},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44118696451187134},{"id":"https://openalex.org/keywords/physical-medicine-and-rehabilitation","display_name":"Physical medicine and rehabilitation","score":0.2890892028808594},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.0930311381816864}],"concepts":[{"id":"https://openalex.org/C151800584","wikidata":"https://www.wikidata.org/wiki/Q2370000","display_name":"Gait","level":2,"score":0.6164531707763672},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6001309156417847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.52785325050354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5043042898178101},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49665313959121704},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44118696451187134},{"id":"https://openalex.org/C99508421","wikidata":"https://www.wikidata.org/wiki/Q2678675","display_name":"Physical medicine and rehabilitation","level":1,"score":0.2890892028808594},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0930311381816864}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2405.13859","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.13859","pdf_url":"https://arxiv.org/pdf/2405.13859","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.13859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.13859","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:2405.13859","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.13859","pdf_url":"https://arxiv.org/pdf/2405.13859","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Existing":[0],"deep":[1],"learning":[2,51],"methods":[3,37],"have":[4],"made":[5],"significant":[6,131],"progress":[7],"in":[8,122,133,140,158],"gait":[9,18,49],"representation":[10,50],"learning.":[11],"Quantization":[12],"can":[13,99],"facilitate":[14],"the":[15,67,70,77,96,118,123,134,141,146,173,177,187],"application":[16],"of":[17,69,126,137,179,189],"models":[19,28],"as":[20],"a":[21,60,109,114,130,156],"model-agnostic":[22],"general":[23],"compression":[24],"technique.":[25],"Typically,":[26],"appearance-based":[27],"binarize":[29],"inputs":[30],"into":[31],"silhouette":[32],"sequences.":[33],"However,":[34,85,121],"mainstream":[35],"quantization":[36,43],"prioritize":[38],"minimizing":[39],"task":[40],"loss":[41,157],"over":[42],"error,":[44],"which":[45,64],"is":[46,150],"detrimental":[47],"to":[48,79,145,155,171],"with":[52,181],"binarized":[53],"inputs.":[54],"To":[55],"address":[56],"this,":[57,162],"we":[58,128,163],"propose":[59,164],"differentiable":[61],"soft":[62,97,115],"quantizer,":[63],"better":[65],"simulates":[66],"gradient":[68],"round":[71],"function":[72],"during":[73,117],"backpropagation.":[74],"This":[75],"enables":[76],"network":[78,101],"learn":[80],"from":[81],"subtle":[82],"input":[83],"perturbations.":[84],"our":[86,190],"theoretical":[87],"analysis":[88],"and":[89,198],"empirical":[90],"studies":[91],"reveal":[92],"that":[93,153],"directly":[94],"applying":[95],"quantizer":[98,116],"hinder":[100],"convergence.":[102],"We":[103],"addressed":[104],"this":[105,151],"issue":[106],"by":[107],"adopting":[108],"two-stage":[110],"training":[111],"strategy,":[112],"introducing":[113],"fine-tuning":[119],"phase.":[120],"first":[124],"stage":[125],"training,":[127],"observed":[129],"change":[132,152],"output":[135],"distribution":[136],"different":[138,182],"samples":[139,180],"feature":[142],"space":[143],"compared":[144],"full-precision":[147],"network.":[148],"It":[149],"led":[154],"performance.":[159],"Based":[160],"on":[161],"an":[165],"Inter-class":[166],"Distance-guided":[167],"Calibration":[168],"(IDC)":[169],"strategy":[170],"preserve":[172],"relative":[174],"distance":[175],"between":[176],"embeddings":[178],"labels.":[183],"Extensive":[184],"experiments":[185],"validate":[186],"effectiveness":[188],"approach,":[191],"demonstrating":[192],"state-of-the-art":[193],"accuracy":[194],"across":[195],"various":[196],"settings":[197],"datasets.":[199]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2024-05-26T00:00:00"}