{"id":"https://openalex.org/W4415540140","doi":"https://doi.org/10.1145/3746027.3755222","title":"WaveCL: Wavelet Calibration Learning for Referring Video Object Segmentation","display_name":"WaveCL: Wavelet Calibration Learning for Referring Video Object Segmentation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540140","doi":"https://doi.org/10.1145/3746027.3755222"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110522039","display_name":"Chen Ran","orcid":"https://orcid.org/0000-0002-8610-8172"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Chen","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8610-8172","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061219010","display_name":"Taiyi Su","orcid":"https://orcid.org/0000-0002-4357-1095"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taiyi Su","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4357-1095","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9999-4871","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3856","last_page":"3864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991999864578247,"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":0.9991999864578247,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9983999729156494,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9980999827384949,"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/segmentation","display_name":"Segmentation","score":0.7067000269889832},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.6241999864578247},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5726000070571899},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4472000002861023},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4318000078201294},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.4174000024795532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4099999964237213},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3952000141143799},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.3562000095844269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7415000200271606},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7067000269889832},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.6241999864578247},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5916000008583069},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5726000070571899},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.4174000024795532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3052999973297119},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C2777885455","wikidata":"https://www.wikidata.org/wiki/Q5156615","display_name":"Complex wavelet transform","level":5,"score":0.26109999418258667},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2125127483","display_name":null,"funder_award_id":"62371343","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3038806383","display_name":null,"funder_award_id":"2024-1-ZD-02","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1996938738","https://openalex.org/W4225495512","https://openalex.org/W4283029876","https://openalex.org/W4389347891","https://openalex.org/W4395703093"],"related_works":[],"abstract_inverted_index":{"Referring":[0],"video":[1,12,30,116],"object":[2,140],"segmentation":[3,62,173],"(RVOS)":[4],"focuses":[5],"on":[6,14,23,97,126,183],"segmenting":[7],"target":[8,34,65,90,139],"objects":[9],"in":[10,39,58,209],"a":[11,71,142],"based":[13],"natural":[15],"language":[16],"descriptions.":[17],"However,":[18],"existing":[19,197],"methods":[20],"typically":[21],"rely":[22],"text":[24,154],"cues":[25],"that":[26,194],"are":[27],"unrelated":[28],"to":[29,46,80,133],"content,":[31,117],"and":[32,50,55,84,105,121,167,177,191],"the":[33,40,64,89,112,127,138,151,158,163],"entity":[35,102],"is":[36,78,95],"only":[37],"recognized":[38],"pixel":[41],"space.":[42],"This":[43],"often":[44],"leads":[45],"ambiguous":[47],"cross-modal":[48,82,123],"understanding":[49,83],"fragmented":[51],"perception":[52,103,108],"across":[53],"space":[54],"time,":[56],"resulting":[57],"inaccurate":[59],"or":[60],"incomplete":[61],"of":[63,88,137,153,160,165,187,203],"objects.":[66],"To":[67],"address":[68],"these":[69],"challenges,":[70],"novel":[72],"wavelet":[73,131,148],"calibration":[74],"learning":[75],"(WaveCL)":[76],"framework":[77,94],"proposed":[79],"unify":[81],"preserve":[85],"spatial-temporal":[86,144,179],"integrity":[87,107,159],"object.":[91],"The":[92,200],"WaveCL":[93,169,195],"built":[96],"two":[98],"core":[99],"components:":[100],"semantic-calibrated":[101],"(SEP)":[104],"wavelet-guided":[106],"(WIP).":[109],"SEP":[110,166],"aligns":[111],"textual":[113],"semantics":[114],"with":[115,150,174],"enabling":[118],"more":[119],"accurate":[120],"context-aware":[122],"understanding.":[124],"WIP,":[125,168],"other":[128],"hand,":[129],"leverages":[130],"representations":[132],"capture":[134],"fine-grained":[135],"details":[136],"from":[141],"global":[143],"perspective.":[145],"By":[146],"refining":[147],"clues":[149],"guidance":[152],"queries,":[155],"WIP":[156],"enhances":[157],"segmentation.":[161],"Through":[162],"collaboration":[164],"enables":[170],"precise,":[171],"target-specific":[172],"detailed":[175],"boundaries":[176],"consistent":[178],"perception.":[180],"Extensive":[181],"experiments":[182],"four":[184],"benchmark":[185],"datasets":[186],"Ref-YouTube-VOS,":[188],"Ref-DAVIS17,":[189],"A2D-Sentences,":[190],"JHMDB-Sentences":[192],"show":[193],"outperforms":[196],"state-of-the-art":[198],"methods.":[199],"source":[201],"code":[202],"this":[204],"work":[205],"can":[206],"be":[207],"found":[208],"https://mic.tongji.edu.cn.":[210]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}