{"id":"https://openalex.org/W4411635626","doi":"https://doi.org/10.1145/3731715.3733484","title":"Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval","display_name":"Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635626","doi":"https://doi.org/10.1145/3731715.3733484"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733484","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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":null,"display_name":"Li-Cheng Shen","orcid":"https://orcid.org/0009-0005-6575-9987"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Cheng Shen","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0005-6575-9987","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113361571","display_name":"Jih-Kang Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jih-Kang Hsieh","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0001-8298-7966","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101469985","display_name":"Wei-Hua Li","orcid":"https://orcid.org/0009-0005-8330-0491"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Hua Li","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0005-8330-0491","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072890368","display_name":"Chu\u2010Song Chen","orcid":"https://orcid.org/0000-0002-2959-2471"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chu-Song Chen","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-2959-2471","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"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":"2028","last_page":"2032"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9927999973297119,"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":0.7392400503158569},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6188955903053284},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.593518853187561},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5798820853233337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5671627521514893},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5431652665138245},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5074407458305359},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4974232017993927},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44183436036109924},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4275127351284027},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3669244050979614},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3500446081161499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392400503158569},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6188955903053284},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.593518853187561},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5798820853233337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5671627521514893},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5431652665138245},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5074407458305359},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4974232017993927},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44183436036109924},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4275127351284027},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3669244050979614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3500446081161499},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733484","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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":18,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W2963109634","https://openalex.org/W2988823324","https://openalex.org/W3035588244","https://openalex.org/W3100107515","https://openalex.org/W3201770677","https://openalex.org/W4229042118","https://openalex.org/W4385262183","https://openalex.org/W4386066126","https://openalex.org/W4386076142","https://openalex.org/W4386076397","https://openalex.org/W4390873312","https://openalex.org/W4390873528","https://openalex.org/W4390874680","https://openalex.org/W4402753581","https://openalex.org/W4402753899","https://openalex.org/W4402754134","https://openalex.org/W6600002382"],"related_works":["https://openalex.org/W2392243736","https://openalex.org/W86652014","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W4379231730","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2328518092","https://openalex.org/W4389858081","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Text-to-image":[0],"retrieval":[1,91,137,163],"(TIR)":[2],"aims":[3],"to":[4,112,118,135,146],"find":[5],"relevant":[6],"images":[7],"based":[8,18,34],"on":[9,19,35,153],"a":[10,58,81,85,93,102],"textual":[11],"query,":[12],"but":[13,39],"existing":[14],"approaches":[15],"are":[16,144],"primarily":[17],"whole-image":[20],"captions":[21],"and":[22,64,71,92,98,116,127,139,155,165],"lack":[23],"interpretability.":[24],"Meanwhile,":[25],"referring":[26],"expression":[27],"segmentation":[28,147,166],"(RES)":[29],"enables":[30],"precise":[31],"object":[32,73,99,114],"localization":[33],"natural":[36],"language":[37,105],"descriptions":[38],"is":[40,133,173],"computationally":[41],"expensive":[42],"when":[43],"applied":[44],"across":[45],"large":[46,104],"image":[47,69,90],"collections.":[48],"To":[49,75],"bridge":[50],"this":[51,77],"gap,":[52],"we":[53,79],"introduce":[54],"Mask-aware":[55],"TIR":[56,63],"(MaTIR),":[57],"new":[59],"task":[60],"that":[61],"unifies":[62],"RES,":[65],"requiring":[66],"both":[67,162],"efficient":[68],"search":[70],"accurate":[72],"segmentation.":[74],"address":[76],"task,":[78],"propose":[80],"two-stage":[82],"framework,":[83],"comprising":[84],"first":[86],"stage":[87,95],"for":[88,96],"segmentation-aware":[89],"second":[94],"reranking":[97],"grounding":[100],"with":[101],"multimodal":[103],"model":[106],"(MLLM).":[107],"We":[108,149],"leverage":[109],"SAM":[110],"2":[111],"generate":[113,140],"masks":[115],"Alpha-CLIP":[117],"extract":[119],"region-level":[120],"embeddings":[121],"offline":[122],"at":[123,175],"first,":[124],"enabling":[125],"effective":[126],"scalable":[128],"online":[129],"retrieval.":[130],"Secondly,":[131],"MLLM":[132],"used":[134],"refine":[136],"rankings":[138],"bounding":[141],"boxes,":[142],"which":[143],"matched":[145],"masks.":[148],"evaluate":[150],"our":[151],"approach":[152],"COCO":[154],"D3":[156],"datasets,":[157],"demonstrating":[158],"significant":[159],"improvements":[160],"in":[161],"accuracy":[164],"quality":[167],"over":[168],"previous":[169],"methods.":[170],"Our":[171],"code":[172],"available":[174],"https://github.com/AI-Application-and-Integration-Lab/MaTIR.":[176]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}