{"id":"https://openalex.org/W4403791522","doi":"https://doi.org/10.1145/3664647.3680817","title":"Tracking-forced Referring Video Object Segmentation","display_name":"Tracking-forced Referring Video Object Segmentation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791522","doi":"https://doi.org/10.1145/3664647.3680817"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5069575278","display_name":"Ruxue Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruxue Yan","raw_affiliation_strings":["VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101399958","display_name":"Wenya Guo","orcid":"https://orcid.org/0000-0001-5609-194X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenya Guo","raw_affiliation_strings":["VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037513354","display_name":"Xubo Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114416517","display_name":"Xumeng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xumeng Liu","raw_affiliation_strings":["VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386273","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0003-4906-5828"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062064974","display_name":"Xiaojie Yuan","orcid":"https://orcid.org/0000-0002-5876-6856"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Yuan","raw_affiliation_strings":["VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"VCIP, TMCC, TBI Center, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069575278"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.2493,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54531777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5356","last_page":"5364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"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/computer-vision","display_name":"Computer vision","score":0.7612588405609131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7282721996307373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6730913519859314},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6367537975311279},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.6306145191192627},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.509570837020874},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5036341547966003},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4236640930175781}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7612588405609131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7282721996307373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6730913519859314},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6367537975311279},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.6306145191192627},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.509570837020874},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5036341547966003},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4236640930175781}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2963354481","https://openalex.org/W2980088508","https://openalex.org/W2997063389","https://openalex.org/W3034777757","https://openalex.org/W3122784054","https://openalex.org/W3138516171","https://openalex.org/W3178075329","https://openalex.org/W4226024706","https://openalex.org/W4301045096","https://openalex.org/W4380993830","https://openalex.org/W4387546442","https://openalex.org/W4388048626","https://openalex.org/W4394593033"],"related_works":["https://openalex.org/W1986655823","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W3011384228","https://openalex.org/W2124969951","https://openalex.org/W2945274617","https://openalex.org/W4313052709","https://openalex.org/W4298131179","https://openalex.org/W2375430703"],"abstract_inverted_index":{"Referring":[0],"video":[1,21],"object":[2,15,174],"segmentation":[3,31,102,115],"(RVOS)":[4],"is":[5],"a":[6,42,81],"cross-modal":[7],"task":[8],"that":[9],"aims":[10],"to":[11,73,93,133,164,169],"segment":[12,47],"the":[13,34,37,91,100,117,122,126,152,161,209],"target":[14],"described":[16],"by":[17,63,67,191,216],"language":[18],"expressions.":[19],"A":[20],"typically":[22],"consists":[23],"of":[24,103],"multiple":[25],"frames":[26,62,105],"and":[27,46,89,147,203,218],"existing":[28,184],"works":[29],"conduct":[30],"at":[32,44,192],"either":[33],"clip-level":[35],"or":[36],"frame-level.":[38],"Clip-level":[39],"methods":[40,57,185,215],"process":[41],"clip":[43],"once":[45],"in":[48,116],"parallel,":[49],"lacking":[50],"explicit":[51],"inter-frame":[52,108],"interactions.":[53],"In":[54,76],"contrast,":[55],"frame-level":[56],"facilitate":[58],"direct":[59],"interactions":[60],"between":[61],"processing":[64],"videos":[65],"frame":[66,163],"frame,":[68],"but":[69],"they":[70],"are":[71],"prone":[72],"error":[74,149],"accumulation.":[75,150],"this":[77],"paper,":[78],"we":[79,98,158],"propose":[80],"novel":[82],"tracking-forced":[83,180],"framework,":[84],"introducing":[85],"high-quality":[86,111],"tracking":[87,112,142,166],"information":[88],"forcing":[90],"model":[92,132],"achieve":[94],"accurate":[95,107,171],"segmentation.":[96,175],"Concretely,":[97],"utilize":[99],"ground-truth":[101,156],"previous":[104,127,213],"as":[106],"interactions,":[109],"providing":[110],"references":[113],"for":[114],"next":[118],"frame.":[119],"This":[120],"decouples":[121],"current":[123],"input":[124],"from":[125],"output,":[128],"which":[129],"enables":[130],"our":[131,179,196],"concentrate":[134],"on":[135,140,186,208],"accurately":[136],"segmenting":[137],"just":[138],"based":[139],"given":[141],"information,":[143,167],"improving":[144],"training":[145],"efficiency":[146],"preventing":[148],"For":[151],"inference":[153],"stage":[154],"without":[155],"masks,":[157],"carefully":[159],"select":[160],"beginning":[162],"construct":[165],"aiming":[168],"ensure":[170],"tracking-based":[172],"frame-by-frame":[173],"With":[176],"these":[177],"designs,":[178],"method":[181,197],"significantly":[182],"outperforms":[183],"4":[187],"widely":[188],"used":[189],"benchmarks":[190],"least":[193],"3%.":[194],"Especially,":[195],"achieves":[198],"88.3%":[199],"[email":[200],"protected]":[201],"accuracy":[202],"87.6":[204],"overall":[205],"IoU":[206],"score":[207],"JHMDB-Sentences":[210],"dataset,":[211],"surpassing":[212],"best":[214],"5.0%":[217],"8.0,":[219],"respectively.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}