{"id":"https://openalex.org/W4403791674","doi":"https://doi.org/10.1145/3664647.3680850","title":"Adaptive Selection based Referring Image Segmentation","display_name":"Adaptive Selection based Referring Image Segmentation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791674","doi":"https://doi.org/10.1145/3664647.3680850"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680850","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680850","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/A5085203949","display_name":"Pengfei Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengfei Yue","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069323421","display_name":"Jianghang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianghang Lin","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033991031","display_name":"Shengchuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchuan Zhang","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679572","display_name":"Jie Hu","orcid":"https://orcid.org/0000-0002-3187-1656"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Hu","raw_affiliation_strings":["Contemporary Amperex Technology Co., Limited, Ningde, China"],"affiliations":[{"raw_affiliation_string":"Contemporary Amperex Technology Co., Limited, Ningde, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015011504","display_name":"Yilin Lu","orcid":"https://orcid.org/0009-0000-3266-6155"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Lu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026239639","display_name":"Hongwei Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Niu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101684757","display_name":"Hui Ding","orcid":"https://orcid.org/0000-0002-7913-3871"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixin Ding","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030121180","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0003-1642-0758"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020568230","display_name":"Guannan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guannan Jiang","raw_affiliation_strings":["Contemporary Amperex Technology Co., Limited, Ningde, China"],"affiliations":[{"raw_affiliation_string":"Contemporary Amperex Technology Co., Limited, Ningde, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014628588","display_name":"Liujuan Cao","orcid":"https://orcid.org/0000-0002-7645-9606"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujuan Cao","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China","institution_ids":["https://openalex.org/I1327237609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5085203949"],"corresponding_institution_ids":["https://openalex.org/I1327237609"],"apc_list":null,"apc_paid":null,"fwci":2.8948,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92380608,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1101","last_page":"1110"},"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":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9977999925613403,"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":0.9957000017166138,"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/image-segmentation","display_name":"Image segmentation","score":0.7181199193000793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6904007196426392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6716480851173401},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5906641483306885},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5571731328964233},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.532892107963562},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.48227933049201965},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.47470441460609436},{"id":"https://openalex.org/keywords/image-texture","display_name":"Image texture","score":0.47240370512008667},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4655958116054535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46421077847480774}],"concepts":[{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.7181199193000793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6904007196426392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6716480851173401},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5906641483306885},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5571731328964233},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.532892107963562},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.48227933049201965},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47470441460609436},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.47240370512008667},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4655958116054535},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46421077847480774}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680850","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680850","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2251512949","https://openalex.org/W2302548814","https://openalex.org/W2605127024","https://openalex.org/W2798556392","https://openalex.org/W2876852810","https://openalex.org/W2894964039","https://openalex.org/W2955058313","https://openalex.org/W2963145877","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2964345792","https://openalex.org/W2964935470","https://openalex.org/W2965391153","https://openalex.org/W2980088508","https://openalex.org/W2986755220","https://openalex.org/W3004019157","https://openalex.org/W3034325957","https://openalex.org/W3034692043","https://openalex.org/W3034764937","https://openalex.org/W3035097537","https://openalex.org/W3035268124","https://openalex.org/W3083600713","https://openalex.org/W3093025045","https://openalex.org/W3108748824","https://openalex.org/W3138516171","https://openalex.org/W3169998662","https://openalex.org/W3170841864","https://openalex.org/W3172522282","https://openalex.org/W3187664142","https://openalex.org/W3201770677","https://openalex.org/W3206209177","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4285606530","https://openalex.org/W4304092062","https://openalex.org/W4312446817","https://openalex.org/W4312543911","https://openalex.org/W4312795113","https://openalex.org/W4312956471","https://openalex.org/W4382240193","https://openalex.org/W4385764483","https://openalex.org/W4386066064","https://openalex.org/W4386071535","https://openalex.org/W4386076142","https://openalex.org/W4390871886","https://openalex.org/W4390873429","https://openalex.org/W4390873528","https://openalex.org/W4393148942","https://openalex.org/W4394744354"],"related_works":["https://openalex.org/W2204605857","https://openalex.org/W3196005494","https://openalex.org/W2069318476","https://openalex.org/W2170380303","https://openalex.org/W1996489018","https://openalex.org/W2093085045","https://openalex.org/W2131637713","https://openalex.org/W1538326369","https://openalex.org/W2386159816","https://openalex.org/W29240789"],"abstract_inverted_index":{"Referring":[0],"image":[1],"segmentation":[2],"(RIS)":[3],"aims":[4],"to":[5,71,107,117,127,146],"segment":[6],"a":[7,12,138],"particular":[8],"region":[9],"based":[10],"on":[11,33,113,176],"specific":[13],"expression.":[14],"Existing":[15],"one-stage":[16],"methods":[17,31,175],"have":[18],"explored":[19],"various":[20,118],"fusion":[21,46],"strategies,":[22],"yet":[23],"they":[24],"encounter":[25],"two":[26,94],"significant":[27],"issues.":[28],"Primarily,":[29],"most":[30],"rely":[32],"manually":[34],"selected":[35],"visual":[36,40,110],"features":[37,49,53,111,131,149],"from":[38],"the":[39,44,55,84,159],"encoder":[41],"layers.":[42],"Moreover,":[43],"direct":[45],"of":[47,78,162],"word-level":[48],"into":[50],"coarse":[51,130,148],"aligned":[52],"disrupts":[54],"established":[56],"vision-language":[57,163],"alignment.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,97],"introduce":[63],"an":[64,99],"innovative":[65],"framework":[66,172],"for":[67],"RIS":[68],"that":[69,132,169],"seeks":[70],"overcome":[72],"these":[73],"challenges":[74],"with":[75,87,123,150],"adaptive":[76],"alignment":[77],"vision":[79],"and":[80,103,179],"language":[81],"features,":[82],"termed":[83],"Adaptive":[85,100],"Selection":[86,102],"Dual":[88],"Alignment":[89],"(ASDA).":[90],"ASDA":[91,171],"innovates":[92],"in":[93],"aspects.":[95],"Firstly,":[96],"design":[98],"Feature":[101],"Fusion":[104],"(AFSF)":[105],"module":[106],"dynamically":[108],"select":[109],"focusing":[112],"different":[114],"regions":[115],"related":[116],"descriptions.":[119],"AFSF":[120],"is":[121,144],"equipped":[122],"scale-wise":[124],"feature":[125],"aggregator":[126],"provide":[128],"hierarchically":[129],"preserve":[133],"crucial":[134],"low-level":[135],"details.":[136],"Secondly,":[137],"Word":[139],"Guided":[140],"Dual-Branch":[141],"Aligner":[142],"(WGDA)":[143],"leveraged":[145],"integrate":[147],"linguistic":[151],"cues":[152],"by":[153],"word-guided":[154],"attention,":[155],"which":[156],"effectively":[157],"addresses":[158],"common":[160],"issue":[161],"misalignment.":[164],"Extensive":[165],"experimental":[166],"results":[167],"demonstrate":[168],"our":[170],"surpasses":[173],"state-of-the-art":[174],"RefCOCO,":[177],"RefCOCO+":[178],"G-Ref":[180],"benchmark.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
