{"id":"https://openalex.org/W4403662217","doi":"https://doi.org/10.48550/arxiv.2409.08887","title":"Visual Language Tracking with Multi-modal Interaction: A Robust Benchmark","display_name":"Visual Language Tracking with Multi-modal Interaction: A Robust Benchmark","publication_year":2024,"publication_date":"2024-09-13","ids":{"openalex":"https://openalex.org/W4403662217","doi":"https://doi.org/10.48550/arxiv.2409.08887"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.08887","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08887","pdf_url":"https://arxiv.org/pdf/2409.08887","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/2409.08887","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102674051","display_name":"Xuchen Li","orcid":"https://orcid.org/0009-0009-2565-8857","observed_orcids":["https://orcid.org/0009-0009-2565-8857"]},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Xuchen","raw_affiliation_strings":["CRISE , Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRISE , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050320530","display_name":"Shiyu Hu","orcid":"https://orcid.org/0009-0000-2873-6341","observed_orcids":["https://orcid.org/0009-0000-2873-6341","https://orcid.org/0009-0004-7836-7109"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hu, Shiyu","raw_affiliation_strings":["School of Physical and Mathematical Sciences , Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Physical and Mathematical Sciences , Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088002825","display_name":"Xiaokun Feng","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng, Xiaokun","raw_affiliation_strings":["CRISE , Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRISE , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077385545","display_name":"Dailing Zhang","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Dailing","raw_affiliation_strings":["CRISE , Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRISE , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101480388","display_name":"Meiqi Wu","orcid":"https://orcid.org/0009-0007-3155-4013","observed_orcids":["https://orcid.org/0009-0007-3155-4013"]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Meiqi","raw_affiliation_strings":["School of Computer Science and Technology , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066905801","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-5230-6285","observed_orcids":["https://orcid.org/0000-0002-5230-6285","https://orcid.org/0000-0003-4301-9089"]},"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":"Zhang, Jing","raw_affiliation_strings":["CRISE , Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRISE , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028693655","display_name":"Kaiqi Huang","orcid":"https://orcid.org/0000-0002-2677-9273","observed_orcids":["https://orcid.org/0000-0002-2677-9273","https://orcid.org/0009-0003-1985-4153"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Kaiqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"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":0.7103999853134155,"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":0.7103999853134155,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2583000063896179,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.006000000052154064,"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/multimodal-interaction","display_name":"multimodal interaction","score":0.6779999732971191},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.4740000069141388},{"id":"https://openalex.org/keywords/human-machine-interaction","display_name":"human-machine interaction","score":0.6890000104904175},{"id":"https://openalex.org/keywords/cognitive-alignment","display_name":"cognitive alignment","score":0.6959999799728394},{"id":"https://openalex.org/keywords/object-recovery","display_name":"object recovery","score":0.628000020980835},{"id":"https://openalex.org/keywords/tracking-failure","display_name":"tracking failure","score":0.3709999918937683},{"id":"https://openalex.org/keywords/video-language-models","display_name":"video-language models","score":0.7429999709129333}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7892041206359863},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6712586879730225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6219528913497925},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.555706262588501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4362964630126953},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37990665435791016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36339515447616577},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19760438799858093},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1212897002696991},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.10535761713981628},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.08887","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08887","pdf_url":"https://arxiv.org/pdf/2409.08887","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.2409.08887","doi":"https://doi.org/10.48550/arxiv.2409.08887","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.08887","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:2409.08887","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08887","pdf_url":"https://arxiv.org/pdf/2409.08887","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403662217.pdf","grobid_xml":"https://content.openalex.org/works/W4403662217.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4393159404"],"related_works":["https://openalex.org/W4403346031","https://openalex.org/W4402916152","https://openalex.org/W4404986536","https://openalex.org/W7140165784","https://openalex.org/W7162848251","https://openalex.org/W4415798002","https://openalex.org/W7140657560","https://openalex.org/W4399344486","https://openalex.org/W4408930345","https://openalex.org/W7163710316"],"abstract_inverted_index":{"Visual":[0],"Language":[1,109],"Tracking":[2,110],"(VLT)":[3],"enhances":[4],"tracking":[5,85,170],"by":[6],"mitigating":[7],"the":[8,14,26,48,77,89,93,119,123,145,175,188,209,216,227,248],"limitations":[9],"of":[10,25,35,52,92,148,190,213,234,255],"relying":[11],"solely":[12],"on":[13,137,199],"visual":[15],"modality,":[16],"utilizing":[17],"high-level":[18],"semantic":[19],"information":[20,44],"through":[21,162,184],"language.":[22],"This":[23,219],"integration":[24],"language":[27],"enables":[28],"more":[29,178],"advanced":[30],"human-machine":[31],"interaction.":[32],"The":[33],"essence":[34],"interaction":[36,83,117,135,156,161],"is":[37],"cognitive":[38],"alignment,":[39],"which":[40,114],"typically":[41],"requires":[42],"multiple":[43,169],"exchanges,":[45],"especially":[46],"in":[47,76,247],"sequential":[49],"decision-making":[50],"process":[51],"VLT.":[53],"However,":[54],"current":[55],"VLT":[56,94,120,140,155,191,202,228],"benchmarks":[57,141,203],"do":[58],"not":[59],"account":[60],"for":[61,122,132,226],"multi-round":[62,116,160],"interactions":[63],"during":[64],"tracking.":[65],"They":[66],"provide":[67,174],"only":[68],"an":[69],"initial":[70],"text":[71,163],"and":[72,104,165,181,204,207,211,224,253],"bounding":[73],"box":[74],"(bbox)":[75],"first":[78,124],"frame,":[79],"with":[80,111,177],"no":[81],"further":[82],"as":[84],"progresses,":[86],"deviating":[87],"from":[88],"original":[90],"motivation":[91],"task.":[95],"To":[96],"address":[97],"these":[98],"limitations,":[99],"we":[100,173],"propose":[101,152],"a":[102,153,231],"novel":[103],"robust":[105],"benchmark,":[106],"VLT-MI":[107],"(Visual":[108],"Multi-modal":[112],"Interaction),":[113],"introduces":[115],"into":[118],"task":[121],"time.":[125],"(1)":[126],"We":[127,151,195,237],"generate":[128],"diverse,":[129],"multi-granularity":[130],"texts":[131,180],"multi-round,":[133],"multi-modal":[134,235],"based":[136],"existing":[138],"mainstream":[139],"using":[142],"DTLLM-VLT,":[143],"leveraging":[144],"world":[146],"knowledge":[147],"LLMs.":[149],"(2)":[150],"new":[154,222],"paradigm":[157],"that":[158],"achieves":[159],"updates":[164],"object":[166],"recovery.":[167],"When":[168],"failures":[171],"occur,":[172],"tracker":[176],"aligned":[179],"corrected":[182],"bboxes":[183],"interaction,":[185],"thereby":[186],"expanding":[187],"scope":[189],"downstream":[192],"tasks.":[193],"(3)":[194],"conduct":[196],"comparative":[197],"experiments":[198],"both":[200],"traditional":[201],"VLT-MI,":[205],"evaluating":[206],"analyzing":[208],"accuracy":[210],"robustness":[212],"trackers":[214],"under":[215],"interactive":[217],"paradigm.":[218],"work":[220],"offers":[221],"insights":[223],"paradigms":[225],"task,":[229],"enabling":[230],"fine-grained":[232],"evaluation":[233],"trackers.":[236],"believe":[238],"this":[239],"approach":[240],"can":[241],"be":[242],"extended":[243],"to":[244],"additional":[245],"datasets":[246],"future,":[249],"supporting":[250],"broader":[251],"evaluations":[252],"comparisons":[254],"video-language":[256],"model":[257],"capabilities.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-10-23T00:00:00"}