{"id":"https://openalex.org/W7165018024","doi":"https://doi.org/10.1007/s11263-026-02903-2","title":"Reasoning Segmentation for Images and Videos: A Survey","display_name":"Reasoning Segmentation for Images and Videos: A Survey","publication_year":2026,"publication_date":"2026-06-17","ids":{"openalex":"https://openalex.org/W7165018024","doi":"https://doi.org/10.1007/s11263-026-02903-2"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-026-02903-2","doi":"https://doi.org/10.1007/s11263-026-02903-2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-026-02903-2","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-3","ki-jl-1","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.18816","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072622467","display_name":"Yiqing Shen","orcid":"https://orcid.org/0000-0001-7866-3339","observed_orcids":["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":true,"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":"middle","author":{"id":"https://openalex.org/A5082289162","display_name":"Chenjia Li","orcid":null,"observed_orcids":[]},"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":"Chenjia Li","raw_affiliation_strings":["Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138798573","display_name":"Fei Xiong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Xiong","raw_affiliation_strings":["Amazon Web Services, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Seattle, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138764278","display_name":"Jeong-O Jeong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeong-O Jeong","raw_affiliation_strings":["Amazon Web Services, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Seattle, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121970539","display_name":"Tianpeng Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianpeng Wang","raw_affiliation_strings":["Amazon Web Services, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Seattle, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138783552","display_name":"Michael Latman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Latman","raw_affiliation_strings":["Amazon Web Services, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Seattle, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087095414","display_name":"Mathias Unberath","orcid":"https://orcid.org/0000-0002-0055-9950","observed_orcids":["https://orcid.org/0000-0002-0055-9950"]},"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":"Mathias Unberath","raw_affiliation_strings":["Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072622467"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":{"value":4090,"currency":"USD","value_usd":4090},"apc_paid":null,"fwci":14.0693,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.99045873,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"134","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8769999742507935,"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":0.8769999742507935,"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":0.10189999639987946,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.00559999980032444,"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/text-guided-segmentation","display_name":"text-guided segmentation","score":0.6259999871253967},{"id":"https://openalex.org/keywords/object-delineation","display_name":"object delineation","score":0.6959999799728394},{"id":"https://openalex.org/keywords/natural-language-prompts","display_name":"natural language prompts","score":0.5379999876022339},{"id":"https://openalex.org/keywords/human-ai-interaction","display_name":"human-AI interaction","score":0.8610000014305115},{"id":"https://openalex.org/keywords/video-segmentation","display_name":"video segmentation","score":0.718999981880188},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"image segmentation","score":0.7160000205039978},{"id":"https://openalex.org/keywords/evaluation-indicators","display_name":"evaluation metrics","score":0.7829999923706055},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.7609999775886536}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.753600001335144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6804999709129333},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5109000205993652},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.387800008058548},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3425000011920929},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.29670000076293945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.25609999895095825}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11263-026-02903-2","doi":"https://doi.org/10.1007/s11263-026-02903-2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-026-02903-2","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-3","ki-jl-1","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2505.18816","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.18816","pdf_url":"https://arxiv.org/pdf/2505.18816","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.18816","doi":"https://doi.org/10.48550/arxiv.2505.18816","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.18816","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.18816","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.18816","pdf_url":"https://arxiv.org/pdf/2505.18816","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7165018024.pdf","grobid_xml":"https://content.openalex.org/works/W7165018024.grobid-xml"},"referenced_works_count":100,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2104408738","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2561196672","https://openalex.org/W2594519801","https://openalex.org/W2737258237","https://openalex.org/W2752101582","https://openalex.org/W2793407941","https://openalex.org/W2889986507","https://openalex.org/W2892087592","https://openalex.org/W2948672349","https://openalex.org/W2963109634","https://openalex.org/W2963341956","https://openalex.org/W2970641574","https://openalex.org/W2982723417","https://openalex.org/W2990616379","https://openalex.org/W3013137071","https://openalex.org/W3016889634","https://openalex.org/W3028351217","https://openalex.org/W3030520226","https://openalex.org/W3034764937","https://openalex.org/W3039368862","https://openalex.org/W3095175122","https://openalex.org/W3104844437","https://openalex.org/W3119997354","https://openalex.org/W3138516171","https://openalex.org/W3158120491","https://openalex.org/W3165896978","https://openalex.org/W3168867926","https://openalex.org/W3212555189","https://openalex.org/W3216610038","https://openalex.org/W4200631575","https://openalex.org/W4225832925","https://openalex.org/W4226069476","https://openalex.org/W4288083516","https://openalex.org/W4312396403","https://openalex.org/W4312868348","https://openalex.org/W4312936847","https://openalex.org/W4319300361","https://openalex.org/W4361194507","https://openalex.org/W4366208220","https://openalex.org/W4386071509","https://openalex.org/W4386076142","https://openalex.org/W4386185600","https://openalex.org/W4390489648","https://openalex.org/W4390872515","https://openalex.org/W4390872914","https://openalex.org/W4390873736","https://openalex.org/W4390873799","https://openalex.org/W4390874025","https://openalex.org/W4390874575","https://openalex.org/W4390874578","https://openalex.org/W4392172801","https://openalex.org/W4393118471","https://openalex.org/W4394839031","https://openalex.org/W4399213100","https://openalex.org/W4401200977","https://openalex.org/W4401307635","https://openalex.org/W4402671548","https://openalex.org/W4402716107","https://openalex.org/W4402727018","https://openalex.org/W4402727124","https://openalex.org/W4402727851","https://openalex.org/W4402754134","https://openalex.org/W4402774343","https://openalex.org/W4402916449","https://openalex.org/W4402952371","https://openalex.org/W4403002096","https://openalex.org/W4403570162","https://openalex.org/W4403938790","https://openalex.org/W4403940533","https://openalex.org/W4404344134","https://openalex.org/W4404601423","https://openalex.org/W4405626818","https://openalex.org/W4405655802","https://openalex.org/W4406415774","https://openalex.org/W4409224394","https://openalex.org/W4409314121","https://openalex.org/W4412945059","https://openalex.org/W4413144596","https://openalex.org/W4413144730","https://openalex.org/W4413146469","https://openalex.org/W4413155278","https://openalex.org/W4413155334","https://openalex.org/W4413157975","https://openalex.org/W4414379518","https://openalex.org/W4415061873","https://openalex.org/W4415158162","https://openalex.org/W4415249249","https://openalex.org/W4415798746","https://openalex.org/W4415798953","https://openalex.org/W4417471306","https://openalex.org/W6948186439","https://openalex.org/W6967068517","https://openalex.org/W6979267127","https://openalex.org/W7133246916","https://openalex.org/W7223749645"],"related_works":["https://openalex.org/W4415816116","https://openalex.org/W7138455615","https://openalex.org/W7087559764","https://openalex.org/W7223052312","https://openalex.org/W4404601423","https://openalex.org/W7133925853","https://openalex.org/W7164862325","https://openalex.org/W4401200977","https://openalex.org/W4402754134","https://openalex.org/W7127952675"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-06-18T00:00:00"}
