{"id":"https://openalex.org/W4391408870","doi":"https://doi.org/10.1145/3627631.3627648","title":"Dense captioning for Text-Image ReID","display_name":"Dense captioning for Text-Image ReID","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391408870","doi":"https://doi.org/10.1145/3627631.3627648"},"language":"en","primary_location":{"id":"doi:10.1145/3627631.3627648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627631.3627648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing","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/A5085785393","display_name":"A V Subramanyam","orcid":"https://orcid.org/0000-0002-8873-4644"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"A V Subramanyam","raw_affiliation_strings":["Department of Electronics & Communications Engineering, Indraprastha Institute of Information Technology Delhi (IIIT-Delhi), IN"],"affiliations":[{"raw_affiliation_string":"Department of Electronics & Communications Engineering, Indraprastha Institute of Information Technology Delhi (IIIT-Delhi), IN","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103089653","display_name":"Vibhu Dubey","orcid":"https://orcid.org/0009-0001-1599-228X"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vibhu Dubey","raw_affiliation_strings":["Department of Computer Science and Engineering, Indraprastha Institute of Information Technology Delhi (IIIT-Delhi), IN"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indraprastha Institute of Information Technology Delhi (IIIT-Delhi), IN","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008103135","display_name":"Niranjan Sundararajan","orcid":"https://orcid.org/0009-0007-3962-6261"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Niranjan Sundararajan","raw_affiliation_strings":["Department of Computer Science and Engineering, Indraprastha Institute of Information Technology Delhi (IIIT-Delhi), IN"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indraprastha Institute of Information Technology Delhi (IIIT-Delhi), IN","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066116024","display_name":"Brejesh Lall","orcid":"https://orcid.org/0000-0003-2677-3071"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Brejesh Lall","raw_affiliation_strings":["Department of Electrical Engineering, IIT Delhi, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, IIT Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085785393"],"corresponding_institution_ids":["https://openalex.org/I119939252"],"apc_list":null,"apc_paid":null,"fwci":0.6018,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70727848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9987999796867371,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9987999796867371,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9864000082015991,"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":0.9794083833694458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7317504286766052},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5997763276100159},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5458805561065674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5276844501495361}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9794083833694458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7317504286766052},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5997763276100159},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5458805561065674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5276844501495361}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627631.3627648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627631.3627648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1602182271","https://openalex.org/W2204750386","https://openalex.org/W2552579943","https://openalex.org/W2778100917","https://openalex.org/W2883311563","https://openalex.org/W2885709146","https://openalex.org/W2894786240","https://openalex.org/W3024059432","https://openalex.org/W3093025987","https://openalex.org/W3206868111","https://openalex.org/W4304087170","https://openalex.org/W4312933868"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Text-to-Image":[0],"(T2I)":[1],"ReID":[2,25,151],"has":[3,57],"attracted":[4],"a":[5,70,91,107,114,120,159,175],"lot":[6],"of":[7,31,40,53,76,97,116,162],"attention":[8],"in":[9,69,102,179],"the":[10,18,43,48,83,103,163,192],"recent":[11],"past.":[12],"CUHK-PEDES,":[13],"RSTPReid":[14,27],"and":[15,28,85,105,132,137,153,157,194],"ICFG-PEDES":[16,29],"are":[17,67],"three":[19],"available":[20],"benchmarks":[21],"to":[22,37,80,174],"evaluate":[23],"T2I":[24],"methods.":[26],"comprise":[30],"identities":[32,55,84,100],"from":[33],"MSMT17":[34],"but":[35,56],"due":[36],"limited":[38,74],"number":[39,75],"unique":[41,99],"persons,":[42],"diversity":[44],"is":[45,124],"limited.":[46],"On":[47],"other":[49],"hand,":[50],"CUHK-PEDES":[51],"comprises":[52,96],"13,003":[54],"relatively":[58],"shorter":[59],"text":[60],"description":[61],"on":[62,141],"average.":[63],"Further,":[64],"these":[65],"datasets":[66],"captured":[68,101],"restricted":[71],"environment":[72],"with":[73],"cameras.":[77],"In":[78],"order":[79],"further":[81,128],"diversify":[82],"provide":[86],"dense":[87],"captions,":[88],"we":[89],"propose":[90],"novel":[92],"dataset.":[93,143,164,195],"Our":[94,165],"dataset":[95,109,182,187],"20,000":[98],"wild":[104],"provides":[106],"rich":[108],"for":[110,119],"text-to-image":[111,150],"ReID.":[112],"With":[113],"minimum":[115],"26":[117],"words":[118],"description,":[121],"each":[122],"image":[123],"densely":[125],"captioned.":[126],"We":[127,144,189],"synthetically":[129,170],"generate":[130],"images":[131],"fine-grained":[133],"captions":[134],"using":[135,148],"Stable-diffusion":[136],"BLIP":[138],"models":[139,152,156],"trained":[140],"our":[142],"perform":[145],"elaborate":[146],"experiments":[147,166],"state-of-art":[149],"vision-language":[154],"pre-trained":[155],"present":[158],"comprehensive":[160],"analysis":[161],"also":[167],"reveal":[168],"that":[169],"generated":[171],"data":[172],"leads":[173],"substantial":[176],"performance":[177],"improvement":[178],"both":[180],"same":[181],"as":[183,185],"well":[184],"cross":[186],"settings.":[188],"will":[190],"release":[191],"code":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}