{"id":"https://openalex.org/W7222655853","doi":"https://doi.org/10.48550/arxiv.2610.21999","title":"VP-EVT: Active Visibility Preservation for Embodied Visual Tracking","display_name":"VP-EVT: Active Visibility Preservation for Embodied Visual Tracking","publication_year":2026,"publication_date":"2026-10-15","ids":{"openalex":"https://openalex.org/W7222655853","doi":"https://doi.org/10.48550/arxiv.2610.21999"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.21999","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.21999","pdf_url":"https://arxiv.org/pdf/2610.21999","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.21999","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132729152","display_name":"Yanci Wen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen, Yanci","raw_affiliation_strings":["Shenzhen Key Laboratory of Robotics and Computer Vision , Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Key Laboratory of Robotics and Computer Vision , Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108991400","display_name":"Tianle Zeng","orcid":"https://orcid.org/0009-0004-1659-6643","observed_orcids":["https://orcid.org/0009-0004-1659-6643"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng, Tianle","raw_affiliation_strings":["Shenzhen Key Laboratory of Robotics and Computer Vision , Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Key Laboratory of Robotics and Computer Vision , Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137534096","display_name":"Jianwei Peng","orcid":"https://orcid.org/0009-0000-3111-4754","observed_orcids":["https://orcid.org/0009-0000-3111-4754"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Jianwei","raw_affiliation_strings":["Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158920012","display_name":"Weixi Situ","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Situ, Weixi","raw_affiliation_strings":["Shenzhen Key Laboratory of Robotics and Computer Vision , Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Key Laboratory of Robotics and Computer Vision , Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005136300","display_name":"Hanjing Ye","orcid":"https://orcid.org/0000-0002-8522-3638","observed_orcids":["https://orcid.org/0000-0002-8522-3638"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye, Hanjing","raw_affiliation_strings":["Shenzhen Key Laboratory of Robotics and Computer Vision , Southern University of Science and Technology , Shenzhen , China","Tencent Robotics X , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Key Laboratory of Robotics and Computer Vision , Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Tencent Robotics X , Shenzhen , China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5158899301","display_name":"Hong Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Hong","raw_affiliation_strings":["Shenzhen Key Laboratory of Robotics and Computer Vision , Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Key Laboratory of Robotics and Computer Vision , Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.6190999746322632,"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":0.6190999746322632,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0966000035405159,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.05429999902844429,"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/occlusion-handling","display_name":"occlusion handling","score":0.6620000004768372},{"id":"https://openalex.org/keywords/robot-following","display_name":"robot following","score":0.6269999742507935},{"id":"https://openalex.org/keywords/egocentric-vision","display_name":"egocentric vision","score":0.7730000019073486},{"id":"https://openalex.org/keywords/human-robot-collaboration","display_name":"human-robot collaboration","score":0.7549999952316284},{"id":"https://openalex.org/keywords/target-loss","display_name":"target loss","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.7771999835968018},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7400000095367432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7166000008583069},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6327000260353088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6151000261306763},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5192999839782715},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5016999840736389},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.32829999923706055},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C48575856","wikidata":"https://www.wikidata.org/wiki/Q852504","display_name":"Motion perception","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.21999","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.21999","pdf_url":"https://arxiv.org/pdf/2610.21999","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.21999","doi":"https://doi.org/10.48550/arxiv.2610.21999","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.21999","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.21999","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.21999","pdf_url":"https://arxiv.org/pdf/2610.21999","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222655853.pdf","grobid_xml":"https://content.openalex.org/works/W7222655853.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2891033863","https://openalex.org/W4286974389","https://openalex.org/W4393972750","https://openalex.org/W4414050622","https://openalex.org/W4415087020","https://openalex.org/W4415318156","https://openalex.org/W4416750034","https://openalex.org/W4417103177","https://openalex.org/W4417517003","https://openalex.org/W7154499979","https://openalex.org/W7160873541","https://openalex.org/W7212022965","https://openalex.org/W7212387950"],"related_works":["https://openalex.org/W4415318156","https://openalex.org/W2034016056","https://openalex.org/W2057555009","https://openalex.org/W2790031333","https://openalex.org/W7212052843","https://openalex.org/W4417517003","https://openalex.org/W7170172133","https://openalex.org/W7128598672","https://openalex.org/W4312736824","https://openalex.org/W2001202832"],"abstract_inverted_index":{"Embodied":[0],"Visual":[1],"Tracking":[2],"(EVT)":[3],"is":[4,157,163],"an":[5,15,72],"essential":[6],"capability":[7],"for":[8,192,202],"intelligent":[9],"robots":[10],"in":[11,23,36],"human-robot":[12],"collaboration,":[13],"requiring":[14],"agent":[16],"to":[17,42,108,127,178,185,215],"follow":[18],"a":[19,65,80,166,216],"designated":[20],"target":[21,56,69,94,111],"person":[22],"dynamic":[24,37],"environments":[25],"relying":[26],"solely":[27],"on":[28,85],"egocentric":[29],"visual":[30,123],"perception.":[31],"However,":[32],"persistent":[33,196],"pedestrian":[34,113],"occlusions":[35],"scenes":[38],"pose":[39],"critical":[40],"challenges":[41],"existing":[43],"EVT":[44],"methods.":[45],"Lacking":[46],"proactive":[47],"visibility":[48,70,221],"preservation,":[49],"reactive":[50],"tracking":[51],"methods":[52],"frequently":[53],"experience":[54],"prolonged":[55],"loss":[57],"under":[58],"severe":[59],"occlusions.":[60],"Therefore,":[61],"we":[62,189],"propose":[63],"VP-EVT,":[64],"framework":[66],"that":[67,101],"treats":[68],"as":[71],"explicit":[73],"objective":[74,87],"of":[75,82,130,195],"motion":[76,98,162],"control":[77],"rather":[78],"than":[79],"by-product":[81],"following.":[83,187],"Acting":[84],"this":[86],"requires":[88],"understanding":[89],"both":[90],"what":[91],"obstructs":[92],"the":[93,140,151,154,159,183],"and":[95,112,134,139,182,198,219,223,229],"how":[96],"robot":[97],"can":[99],"change":[100],"obstruction.":[102,152],"VP-EVT":[103,121,144,208],"therefore":[104],"uses":[105],"language-guided":[106],"perception":[107],"extract":[109],"separate":[110],"observations.":[114],"When":[115,153],"occlusion":[116,197],"makes":[117],"current":[118,141],"observations":[119],"incomplete,":[120],"combines":[122,169],"history":[124],"with":[125,172],"ego-motion":[126],"maintain":[128],"estimates":[129,138,171],"their":[131],"relative":[132,214],"positions":[133],"motion.":[135],"Using":[136],"these":[137],"following":[142,148,161],"waypoints,":[143],"predicts":[145],"whether":[146],"continued":[147],"will":[149],"sustain":[150],"predicted":[155],"risk":[156],"low,":[158],"original":[160],"retained;":[164],"otherwise,":[165],"recurrent":[167],"controller":[168],"updated":[170],"maneuver":[173],"context":[174],"from":[175],"preceding":[176],"decisions":[177],"coordinate":[179],"viewpoint":[180],"adjustment":[181],"return":[184],"stable":[186],"Moreover,":[188],"introduce":[190],"OccEVT-Bench":[191],"closed-loop":[193],"evaluation":[194],"collect":[199],"expert":[200],"demonstrations":[201],"training.":[203],"On":[204],"its":[205],"Risk":[206],"split,":[207],"improves":[209],"success":[210],"rate":[211],"by":[212,227],"121.4%":[213],"competitive":[217],"baseline":[218],"reduces":[220],"deficit":[222],"longest":[224],"target-loss":[225],"duration":[226],"78.8%":[228],"74.4%,":[230],"respectively.":[231]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-17T00:00:00"}