{"id":"https://openalex.org/W4414634784","doi":"https://doi.org/10.1109/iccv51701.2025.02021","title":"Describe Anything: Detailed Localized Image and Video Captioning","display_name":"Describe Anything: Detailed Localized Image and Video Captioning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414634784","doi":"https://doi.org/10.1109/iccv51701.2025.02021"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.16072","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114232525","display_name":"Long Lian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Lian","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101822673","display_name":"Yifan Ding","orcid":"https://orcid.org/0000-0003-1973-8374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Ding","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038696465","display_name":"Yunhao Ge","orcid":"https://orcid.org/0000-0002-8110-9280"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunhao Ge","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049815485","display_name":"Sifei Liu","orcid":"https://orcid.org/0000-0002-6011-3686"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sifei Liu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021948346","display_name":"Hanzi Mao","orcid":"https://orcid.org/0000-0002-2186-2991"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanzi Mao","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101884383","display_name":"Boyi Li","orcid":"https://orcid.org/0000-0002-8921-3808"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyi Li","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050003000","display_name":"Marco Pavone","orcid":"https://orcid.org/0000-0002-0206-4337"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Pavone","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596512","display_name":"Mingyu Liu","orcid":"https://orcid.org/0000-0001-9905-4399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming-Yu Liu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084801169","display_name":"Adam Yala","orcid":"https://orcid.org/0000-0001-9576-2590"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Yala","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100303262","display_name":"Yin Cui","orcid":"https://orcid.org/0000-0003-2882-2033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin Cui","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21766","last_page":"21777"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.991599977016449,"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":0.9911999702453613,"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/closed-captioning","display_name":"Closed captioning","score":0.8996000289916992},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7160000205039978},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6394000053405762},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6051999926567078},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.585099995136261},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5065000057220459},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5006999969482422}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8996000289916992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7994999885559082},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7160000205039978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.644599974155426},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6394000053405762},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6051999926567078},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.585099995136261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5745000243186951},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.48489999771118164},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.16072","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.16072","pdf_url":"https://arxiv.org/pdf/2504.16072","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2504.16072","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.16072","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.16072","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.16072","pdf_url":"https://arxiv.org/pdf/2504.16072","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4414634784.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"detailed":[1,30,125],"and":[2,10,39,56,92,124,129],"accurate":[3],"descriptions":[4],"for":[5,16,29],"specific":[6],"regions":[7],"in":[8],"images":[9,97],"videos":[11],"remains":[12],"a":[13,26,46,57,79,103],"fundamental":[14],"challenge":[15],"vision-language":[17],"models.":[18],"We":[19,100],"introduce":[20,101],"the":[21,71],"Describe":[22],"Anything":[23],"Model":[24],"(DAM),":[25],"model":[27],"designed":[28,105],"localized":[31,58,127],"captioning":[32],"(DLC).":[33],"DAM":[34,114],"preserves":[35],"both":[36],"local":[37],"details":[38],"global":[40],"context":[41],"through":[42],"two":[43],"key":[44],"innovations:":[45],"focal":[47],"prompt,":[48],"which":[49,61],"ensures":[50],"high-resolution":[51],"encoding":[52],"of":[53,73],"targeted":[54],"regions,":[55],"vision":[59],"backbone,":[60],"integrates":[62],"precise":[63],"localization":[64],"with":[65,88],"its":[66],"broader":[67],"context.":[68],"To":[69],"tackle":[70],"scarcity":[72],"high-quality":[74],"DLC":[75,108],"data,":[76],"we":[77],"propose":[78],"Semi-supervised":[80],"learning":[81],"(SSL)-based":[82],"Data":[83],"Pipeline":[84],"(DLC-SDP).":[85],"DLC-SDP":[86],"starts":[87],"existing":[89],"segmentation":[90],"datasets":[91],"expands":[93],"to":[94,106],"unlabeled":[95],"web":[96],"using":[98],"SSL.":[99],"DLC-Bench,":[102],"benchmark":[104],"evaluate":[107],"without":[109],"relying":[110],"on":[111,118],"reference":[112],"captions.":[113],"sets":[115],"new":[116],"state-of-the-art":[117],"7":[119],"benchmarks":[120],"spanning":[121],"keyword-level,":[122],"phrase-level,":[123],"multi-sentence":[126],"image":[128],"video":[130],"captioning.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}