{"id":"https://openalex.org/W7213529201","doi":"https://doi.org/10.48550/arxiv.2609.18206","title":"CapMap-MS-TTA: 3rd Place Solution for the MUMU Track of the 8th LSVOS Challenge at ECCV 2026","display_name":"CapMap-MS-TTA: 3rd Place Solution for the MUMU Track of the 8th LSVOS Challenge at ECCV 2026","publication_year":2026,"publication_date":"2026-09-16","ids":{"openalex":"https://openalex.org/W7213529201","doi":"https://doi.org/10.48550/arxiv.2609.18206"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.18206","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.18206","pdf_url":"https://arxiv.org/pdf/2609.18206","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/2609.18206","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152028543","display_name":"Chengfeng Qiu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Chengfeng","raw_affiliation_strings":["Netease YiDun AI Lab , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netease YiDun AI Lab , Hangzhou , China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081007409","display_name":"Kaifeng Wei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Kaifeng","raw_affiliation_strings":["Netease YiDun AI Lab , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netease YiDun AI Lab , Hangzhou , China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6952999830245972,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6952999830245972,"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":0.2874000072479248,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004399999976158142,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image-tagging","display_name":"image tagging","score":0.8050000071525574},{"id":"https://openalex.org/keywords/open-vocabulary-object-detection","display_name":"open-vocabulary object detection","score":0.9890000224113464},{"id":"https://openalex.org/keywords/test-time-augmentation","display_name":"test-time augmentation","score":0.7149999737739563},{"id":"https://openalex.org/keywords/training-free-inference","display_name":"training-free inference","score":0.6200000047683716},{"id":"https://openalex.org/keywords/non-maximum-suppression","display_name":"non-maximum suppression","score":0.722000002861023},{"id":"https://openalex.org/keywords/florence-2","display_name":"Florence-2","score":0.7020000219345093}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8729000091552734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8070999979972839},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7419000267982483},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.6243000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5910999774932861},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5672000050544739},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5371999740600586},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4377000033855438},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4221999943256378},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3903000056743622},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.35190001130104065},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.25949999690055847}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.18206","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.18206","pdf_url":"https://arxiv.org/pdf/2609.18206","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.2609.18206","doi":"https://doi.org/10.48550/arxiv.2609.18206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.18206","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.18206","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.18206","pdf_url":"https://arxiv.org/pdf/2609.18206","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/W7213529201.pdf","grobid_xml":"https://content.openalex.org/works/W7213529201.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4414315814","https://openalex.org/W4415250007","https://openalex.org/W7090727754"],"related_works":["https://openalex.org/W7213598709","https://openalex.org/W7212028458","https://openalex.org/W4414745512","https://openalex.org/W4402698545","https://openalex.org/W4403007094","https://openalex.org/W4413144929","https://openalex.org/W4410622346","https://openalex.org/W4416146766","https://openalex.org/W7128682324","https://openalex.org/W4402961760"],"abstract_inverted_index":{"The":[0],"MUMU":[1,146],"track":[2],"of":[3,138],"the":[4,71,80,85,124,144],"8th":[5],"Large-scale":[6],"Video":[7],"Object":[8],"Segmentation":[9],"(LSVOS)":[10],"Challenge":[11],"requires":[12],"a":[13,50,98,134],"single":[14],"unified":[15],"multimodal":[16],"model":[17],"to":[18,133],"jointly":[19],"solve":[20],"image":[21],"tagging":[22],"(Task":[23,28,33],"A),":[24],"open-vocabulary":[25],"object":[26],"detection":[27,107],"B),":[29],"and":[30,41,97,111,140],"English":[31],"captioning":[32],"C)":[34],"under":[35],"strict":[36],"resource":[37],"constraints":[38],"(<=0.5B":[39],"parameters":[40],"<=8":[42],"GB":[43],"peak":[44],"GPU":[45],"memory).":[46],"We":[47],"present":[48],"CapMap-MS-TTA,":[49],"training-free":[51],"submission":[52],"built":[53],"on":[54,143],"Microsoft":[55],"Florence-2-base":[56],"(~231M":[57],"parameters),":[58],"combining":[59],"caption":[60,83],"keyword":[61,92],"mapping":[62],"with":[63,74,94,109],"multi-scale":[64,110],"flip":[65],"test-time":[66,113],"augmentation.":[67],"Task":[68,77,102],"C":[69],"uses":[70],"native":[72],"pathway":[73],"length/token":[75],"sanitization.":[76],"A":[78],"maps":[79],"same":[81],"detailed":[82],"into":[84],"official":[86],"quality/scene/event":[87],"vocabularies":[88],"via":[89],"an":[90],"expanded":[91],"lexicon":[93],"whole-word":[95],"matching":[96],"lightweight":[99],"expand-hints":[100],"stage.":[101],"B":[103],"runs":[104],"Florence-2":[105,129],"open":[106],"()":[108],"horizontal-flip":[112],"augmentation":[114],"(TTA),":[115],"followed":[116],"by":[117],"label-aware":[118],"non-maximum":[119],"suppression":[120],"(NMS).":[121],"Without":[122],"fine-tuning,":[123],"system":[125],"improves":[126],"our":[127],"reproduced":[128],"baseline":[130],"from":[131],"15.16":[132],"best":[135],"public":[136],"score":[137],"16.4815,":[139],"ranks":[141],"3rd":[142],"final":[145],"leaderboard.":[147]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-18T00:00:00"}