{"id":"https://openalex.org/W7164862325","doi":"https://doi.org/10.1145/3805622.3810843","title":"Decoupling Multimodal Perception and Reasoning for Image Reasoning Segmentation with Large Language Models","display_name":"Decoupling Multimodal Perception and Reasoning for Image Reasoning Segmentation with Large Language Models","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164862325","doi":"https://doi.org/10.1145/3805622.3810843"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810843","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810843","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810843","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072622467","display_name":"Yiqing Shen","orcid":"https://orcid.org/0000-0001-7866-3339"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiqing Shen","raw_affiliation_strings":["Johns Hopkins University, Baltimore, USA"],"raw_orcid":"https://orcid.org/0000-0001-7866-3339","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100556075","display_name":"Feng Chen","orcid":"https://orcid.org/0009-0007-9574-0691"},"institutions":[{"id":"https://openalex.org/I2802608112","display_name":"Shanghai Chest Hospital","ror":"https://ror.org/03fjc3817","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2802608112"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["JF Smartlnvest Holdings, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-9574-0691","affiliations":[{"raw_affiliation_string":"JF Smartlnvest Holdings, Shanghai, China","institution_ids":["https://openalex.org/I2802608112"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.9408894,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"977","last_page":"985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9842000007629395,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9842000007629395,"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":0.0024999999441206455,"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/T10028","display_name":"Topic Modeling","score":0.001500000013038516,"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/perception","display_name":"Perception","score":0.6122000217437744},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6086000204086304},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5945000052452087},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5051000118255615},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.44269999861717224},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.4343000054359436},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3986000120639801},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.38749998807907104},{"id":"https://openalex.org/keywords/active-appearance-model","display_name":"Active appearance model","score":0.3666999936103821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6941999793052673},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6122000217437744},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6086000204086304},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5945000052452087},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5051000118255615},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.44269999861717224},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3986999988555908},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3716000020503998},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.3666999936103821},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3490000069141388},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810843","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810843","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810843","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810843","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2046074714","https://openalex.org/W2489434015","https://openalex.org/W2767230009","https://openalex.org/W2787688993","https://openalex.org/W2801346558","https://openalex.org/W2922080824","https://openalex.org/W2962766617","https://openalex.org/W2997747012","https://openalex.org/W3204249062","https://openalex.org/W4400367117","https://openalex.org/W4402727124","https://openalex.org/W4402754134","https://openalex.org/W4402916449","https://openalex.org/W4403940533","https://openalex.org/W7133224126"],"related_works":[],"abstract_inverted_index":{"Reasoning":[0],"Segmentation":[1],"(RS)":[2],"is":[3],"a":[4,55,79,89,103,121,133],"multimodal":[5],"vision-text":[6,23],"task":[7],"that":[8,59,93,149],"requires":[9],"segmenting":[10],"objects":[11],"based":[12],"on":[13,30,156],"implicit":[14],"text":[15],"queries,":[16],"demanding":[17],"both":[18,36],"precise":[19],"visual":[20],"perception":[21,37,71],"and":[22,38,97,100,161],"reasoning":[24,111,142],"capabilities.":[25],"Current":[26],"RS":[27,57,77,159],"approaches":[28],"rely":[29],"fine-tuning":[31,123,135],"vision-language":[32],"models":[33],"(VLMs)":[34],"for":[35,126],"reasoning,":[39],"but":[40],"their":[41],"tokenization":[42],"of":[43],"images":[44],"fundamentally":[45],"disrupts":[46],"continuous":[47],"spatial":[48,95],"relationships":[49,96],"between":[50],"objects.":[51,118],"We":[52,119],"introduce":[53],"DTwinSeger,":[54],"novel":[56],"approach":[58],"leverages":[60],"Digital":[61],"Twin":[62],"(DT)":[63],"representation":[64,92,114],"as":[65,78],"an":[66],"intermediate":[67],"layer":[68],"to":[69,108,115,138],"decouple":[70],"from":[72],"reasoning.":[73],"Innovatively,":[74],"DTwinSeger":[75],"reformulates":[76],"two-stage":[80],"process,":[81],"where":[82],"the":[83,86,140],"first":[84],"transforms":[85],"image":[87,158,163],"into":[88],"structured":[90],"DT":[91,129,145],"preserves":[94],"semantic":[98],"properties":[99],"then":[101],"employs":[102],"Large":[104],"Language":[105],"Model":[106],"(LLM)":[107],"perform":[109],"explicit":[110],"over":[112],"this":[113],"identify":[116],"target":[117],"propose":[120],"supervised":[122],"method":[124,151],"specifically":[125],"LLM":[127],"with":[128,132,144],"representation,":[130],"together":[131],"corresponding":[134],"dataset":[136],"Seg-DT,":[137],"enhance":[139],"LLM\u2019s":[141],"capabilities":[143],"representations.":[146],"Experiments":[147],"show":[148],"our":[150],"can":[152],"achieve":[153],"state-of-the-art":[154],"performance":[155],"two":[157],"benchmarks":[160],"three":[162],"referring":[164],"segmentation":[165],"benchmarks.":[166]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}