{"id":"https://openalex.org/W4398161262","doi":"https://doi.org/10.1145/3605098.3636192","title":"Open-Vocabulary And Multitask Image Segmentation","display_name":"Open-Vocabulary And Multitask Image Segmentation","publication_year":2024,"publication_date":"2024-04-08","ids":{"openalex":"https://openalex.org/W4398161262","doi":"https://doi.org/10.1145/3605098.3636192"},"language":"en","primary_location":{"id":"doi:10.1145/3605098.3636192","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605098.3636192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing","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/A5089770514","display_name":"Lihu Pan","orcid":"https://orcid.org/0000-0001-9530-694X"},"institutions":[{"id":"https://openalex.org/I46305995","display_name":"Taiyuan University of Science and Technology","ror":"https://ror.org/01wcbdc92","country_code":"CN","type":"education","lineage":["https://openalex.org/I46305995"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihu Pan","raw_affiliation_strings":["School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0001-9530-694X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, China","institution_ids":["https://openalex.org/I46305995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062109496","display_name":"Yunting Yang","orcid":"https://orcid.org/0009-0007-2195-622X"},"institutions":[{"id":"https://openalex.org/I46305995","display_name":"Taiyuan University of Science and Technology","ror":"https://ror.org/01wcbdc92","country_code":"CN","type":"education","lineage":["https://openalex.org/I46305995"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunting Yang","raw_affiliation_strings":["School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, China"],"raw_orcid":"https://orcid.org/0009-0007-2195-622X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, China","institution_ids":["https://openalex.org/I46305995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020485549","display_name":"Zhengkui Wang","orcid":"https://orcid.org/0000-0003-4554-0791"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhengkui Wang","raw_affiliation_strings":["InfoComm Technology Cluster, Singapore Institute of Technology, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-4554-0791","affiliations":[{"raw_affiliation_string":"InfoComm Technology Cluster, Singapore Institute of Technology, Singapore, Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101576537","display_name":"Wen Shan","orcid":"https://orcid.org/0000-0002-7377-8943"},"institutions":[{"id":"https://openalex.org/I8696757","display_name":"Singapore University of Social Sciences","ror":"https://ror.org/01s57k749","country_code":"SG","type":"education","lineage":["https://openalex.org/I8696757"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wen Shan","raw_affiliation_strings":["Singapore University of Social Sciences, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7377-8943","affiliations":[{"raw_affiliation_string":"Singapore University of Social Sciences, Singapore, Singapore","institution_ids":["https://openalex.org/I8696757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103164549","display_name":"Jiali Yin","orcid":"https://orcid.org/0009-0006-1037-3494"},"institutions":[{"id":"https://openalex.org/I46305995","display_name":"Taiyuan University of Science and Technology","ror":"https://ror.org/01wcbdc92","country_code":"CN","type":"education","lineage":["https://openalex.org/I46305995"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiali Yin","raw_affiliation_strings":["School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, China"],"raw_orcid":"https://orcid.org/0009-0006-1037-3494","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, China","institution_ids":["https://openalex.org/I46305995"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.05653805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1048","last_page":"1049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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":0.9980999827384949,"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":0.7721667885780334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.656938374042511},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6468312740325928},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6389214992523193},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.552842915058136},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4983832836151123},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.49386483430862427},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4630342721939087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.333059698343277},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15082284808158875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721667885780334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.656938374042511},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6468312740325928},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6389214992523193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.552842915058136},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4983832836151123},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.49386483430862427},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4630342721939087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.333059698343277},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15082284808158875},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605098.3636192","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605098.3636192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2879390606","https://openalex.org/W4312420092"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W3167549738","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Open-vocabulary":[0],"learning":[1],"has":[2],"revolutionized":[3],"image":[4,66],"segmentation,":[5,91,106],"enabling":[6],"the":[7],"delineation":[8],"of":[9,65],"arbitrary":[10],"categories":[11],"from":[12],"textual":[13],"descriptions.":[14],"While":[15],"current":[16],"methods":[17],"often":[18],"employ":[19],"specialized":[20],"architectures,":[21],"OVAMTSeg":[22,37],"presents":[23],"a":[24,73,85],"unified":[25],"framework":[26,71],"for":[27,76,117],"Open-Vocabulary":[28],"and":[29,54,59,67,111],"Multitask":[30],"Image":[31],"Segmentation.":[32],"Leveraging":[33],"adaptive":[34],"prompt":[35],"learning,":[36],"excels":[38],"in":[39,88,104],"capturing":[40],"category-sensitive":[41],"concepts,":[42],"ensuring":[43],"robustness":[44],"across":[45],"diverse":[46],"multi-task":[47],"scenarios.":[48],"Text":[49],"prompts":[50],"effectively":[51],"capture":[52],"semantic":[53],"contextual":[55],"features,":[56],"while":[57],"cross-attention":[58],"cross-modal":[60],"interactions":[61],"facilitate":[62],"seamless":[63],"fusion":[64],"text":[68],"features.":[69],"The":[70],"incorporates":[72],"transformer-based":[74],"decoder":[75],"dense":[77],"prediction.":[78],"Experimental":[79],"results":[80],"demonstrate":[81],"OVAMTSeg's":[82],"effectiveness,":[83],"achieving":[84],"47.5":[86],"mIoU":[87,93,101,108,113],"referring":[89],"expression":[90],"51.6":[92],"on":[94,102,109,114],"Pascal-VOC":[95],"with":[96],"four":[97],"unseen":[98],"classes,":[99],"46.6":[100],"Pascal-Context":[103],"zero-shot":[105],"65.9":[107],"Pascal-5i,":[110],"35.7":[112],"COCO-20i":[115],"datasets":[116],"one-shot":[118],"segmentation.":[119]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}