{"id":"https://openalex.org/W4402593859","doi":"https://doi.org/10.1109/avss61716.2024.10672595","title":"RefMOS: A Robust Referred Moving Object Segmentation framework based on text query","display_name":"RefMOS: A Robust Referred Moving Object Segmentation framework based on text query","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402593859","doi":"https://doi.org/10.1109/avss61716.2024.10672595"},"language":"en","primary_location":{"id":"doi:10.1109/avss61716.2024.10672595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss61716.2024.10672595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","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/A5036792164","display_name":"Prafulla Saxena","orcid":"https://orcid.org/0000-0002-4997-6544"},"institutions":[{"id":"https://openalex.org/I83205935","display_name":"Malaviya National Institute of Technology Jaipur","ror":"https://ror.org/0077k1j32","country_code":"IN","type":"education","lineage":["https://openalex.org/I83205935"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Prafulla Saxena","raw_affiliation_strings":["MNIT Jaipur"],"affiliations":[{"raw_affiliation_string":"MNIT Jaipur","institution_ids":["https://openalex.org/I83205935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109783614","display_name":"Susim Mukul Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Susim Mukul Roy","raw_affiliation_strings":["IIT Jodhpur"],"affiliations":[{"raw_affiliation_string":"IIT Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071699662","display_name":"Dinesh Kumar Tyagi","orcid":"https://orcid.org/0000-0003-1104-7456"},"institutions":[{"id":"https://openalex.org/I83205935","display_name":"Malaviya National Institute of Technology Jaipur","ror":"https://ror.org/0077k1j32","country_code":"IN","type":"education","lineage":["https://openalex.org/I83205935"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dinesh Kumar Tyagi","raw_affiliation_strings":["MNIT Jaipur"],"affiliations":[{"raw_affiliation_string":"MNIT Jaipur","institution_ids":["https://openalex.org/I83205935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015414891","display_name":"Santosh Kumar Vipparthi","orcid":"https://orcid.org/0000-0002-5672-3537"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Santosh Kumar Vipparthi","raw_affiliation_strings":["IIT Ropar"],"affiliations":[{"raw_affiliation_string":"IIT Ropar","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032409915","display_name":"Subrahmanyam Murala","orcid":"https://orcid.org/0000-0003-3384-4368"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Subrahmanyam Murala","raw_affiliation_strings":["IIT Ropar"],"affiliations":[{"raw_affiliation_string":"IIT Ropar","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066817859","display_name":"Ravi Balasubramanian","orcid":"https://orcid.org/0000-0001-7472-6603"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R. Balasubramanian","raw_affiliation_strings":["IIT Roorkee"],"affiliations":[{"raw_affiliation_string":"IIT Roorkee","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036792164"],"corresponding_institution_ids":["https://openalex.org/I83205935"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53612267,"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":"1","last_page":"7"},"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":0.9979000091552734,"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":0.9979000091552734,"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/T11106","display_name":"Data Management and Algorithms","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9800999760627747,"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-science","display_name":"Computer science","score":0.7888265252113342},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6215314865112305},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6069298982620239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5120049118995667},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46012070775032043},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.43308889865875244},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42718270421028137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888265252113342},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6215314865112305},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6069298982620239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120049118995667},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46012070775032043},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.43308889865875244},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42718270421028137}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/avss61716.2024.10672595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss61716.2024.10672595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2470139095","https://openalex.org/W2787091153","https://openalex.org/W2799239273","https://openalex.org/W2903118147","https://openalex.org/W2916797271","https://openalex.org/W2925327970","https://openalex.org/W2962884594","https://openalex.org/W2962942822","https://openalex.org/W2980088508","https://openalex.org/W2990205821","https://openalex.org/W3009499989","https://openalex.org/W3034731255","https://openalex.org/W3094664776","https://openalex.org/W3104844437","https://openalex.org/W3215899623","https://openalex.org/W4226024706","https://openalex.org/W4283796148","https://openalex.org/W4288052482","https://openalex.org/W4308233893","https://openalex.org/W6754033419","https://openalex.org/W6755207826","https://openalex.org/W6759534164","https://openalex.org/W6796280812","https://openalex.org/W6796524941"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2737719445","https://openalex.org/W4239098401","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W2898210368","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Referred":[0],"Moving":[1],"object":[2,22,79],"segmentation":[3,80],"is":[4,46,147],"a":[5,36,47,75,98,165],"very":[6],"challenging":[7],"task":[8],"in":[9,157],"automated":[10],"video":[11,105],"surveillance":[12],"applications":[13],"as":[14,41,43,107],"it":[15],"requires":[16],"additional":[17],"information":[18,112,131,140,152],"to":[19,54,64,83,149,180],"learn":[20],"about":[21],"representation":[23],"referred":[24,77,87,154],"by":[25,35,88,103,160],"natural":[26],"language":[27,167],"expression.":[28],"In":[29,69,115],"segmenting":[30],"specific":[31],"moving":[32,40,78,85,155],"objects":[33,45,86,156],"targeted":[34],"text,":[37],"suppressing":[38],"other":[39],"well":[42],"stationary":[44],"crucial":[48],"task.":[49],"A":[50],"better":[51],"context":[52],"needs":[53],"be":[55,65],"learned":[56],"where":[57],"linguistic,":[58],"spatial,":[59],"and":[60,136,175,192],"temporal":[61,111,139],"features":[62,163],"need":[63],"taken":[66],"into":[67],"account.":[68],"this":[70,116],"work,":[71,117],"we":[72,118],"have":[73,119],"proposed":[74,120],"robust":[76],"(RefMOS)":[81],"framework":[82,186],"capture":[84,150],"text":[89,159],"query.":[90],"Most":[91],"of":[92,101,153],"the":[93,129,133,151,158,172,182,189,198],"earlier":[94],"state-of-the-art":[95,190],"methods":[96],"exploit":[97],"different":[99],"type":[100],"supervision":[102],"treating":[104],"frames":[106,135],"images":[108],"but":[109],"lack":[110],"during":[113],"processing.":[114],"an":[121],"inter-frame":[122],"movement":[123,130],"detector":[124],"(IFCD)":[125],"module,":[126],"which":[127],"extracts":[128],"between":[132],"consecutive":[134],"helps":[137],"integrate":[138],"with":[141,188],"spatial":[142],"visual":[143],"features.":[144],"Language":[145],"embedding":[146],"utilized":[148],"extracting":[161],"linguistic":[162],"from":[164],"pre-trained":[166],"model,":[168],"i.e.,":[169],"BERT.":[170],"Furthermore,":[171],"cross-entropy":[173],"loss":[174],"SGD":[176],"optimizer":[177],"are":[178],"used":[179],"train":[181],"network.":[183],"Our":[184],"RefMOS":[185],"competes":[187],"approaches":[191],"achieves":[193],"48.6":[194],"mean":[195],"IOU":[196],"on":[197],"ref-DAVIS":[199],"17":[200],"dataset.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}