{"id":"https://openalex.org/W3205346281","doi":"https://doi.org/10.1145/3474085.3475366","title":"Deconfounded and Explainable Interactive Vision-Language Retrieval of Complex Scenes","display_name":"Deconfounded and Explainable Interactive Vision-Language Retrieval of Complex Scenes","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205346281","doi":"https://doi.org/10.1145/3474085.3475366","mag":"3205346281"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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":"https://openalex.org/A5035658564","display_name":"Junda Wu","orcid":"https://orcid.org/0000-0001-6464-7813"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junda Wu","raw_affiliation_strings":["New York University, New York City, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University, New York City, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767815","display_name":"Tong Yu","orcid":"https://orcid.org/0000-0001-7998-3326"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Yu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059952787","display_name":"Shuai Li","orcid":"https://orcid.org/0000-0001-8871-3272"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8593,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83037368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2103","last_page":"2111"},"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":0.9916999936103821,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/spurious-relationship","display_name":"Spurious relationship","score":0.8603272438049316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8509352207183838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5934783220291138},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5398930311203003},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4864182472229004},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4833933413028717},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.45513924956321716},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42431578040122986},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3776361644268036},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35838353633880615},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3564845025539398},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3158241808414459}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.8603272438049316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8509352207183838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5934783220291138},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5398930311203003},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4864182472229004},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4833933413028717},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.45513924956321716},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42431578040122986},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3776361644268036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35838353633880615},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3564845025539398},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3158241808414459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1487627140","https://openalex.org/W1561177922","https://openalex.org/W1980284827","https://openalex.org/W2130660124","https://openalex.org/W2150827897","https://openalex.org/W2152184085","https://openalex.org/W2166050755","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2583875861","https://openalex.org/W2745461083","https://openalex.org/W2746910012","https://openalex.org/W2798503981","https://openalex.org/W2892181857","https://openalex.org/W2896457183","https://openalex.org/W2897195437","https://openalex.org/W2944854690","https://openalex.org/W2949395487","https://openalex.org/W2949553967","https://openalex.org/W2964159778","https://openalex.org/W2969961114","https://openalex.org/W2970608575","https://openalex.org/W2970944013","https://openalex.org/W2982120135","https://openalex.org/W2997726715","https://openalex.org/W3026458074","https://openalex.org/W3034891407","https://openalex.org/W3035103424","https://openalex.org/W3035145964","https://openalex.org/W3035651653","https://openalex.org/W3036060861","https://openalex.org/W3049478012","https://openalex.org/W3094497946","https://openalex.org/W3099839483","https://openalex.org/W3102568136","https://openalex.org/W3135526844","https://openalex.org/W3171353004","https://openalex.org/W3172514680","https://openalex.org/W3177934633","https://openalex.org/W4288086191"],"related_works":["https://openalex.org/W1606474234","https://openalex.org/W2034539438","https://openalex.org/W2124645781","https://openalex.org/W2184057774","https://openalex.org/W2140331143","https://openalex.org/W2085657627","https://openalex.org/W2543381692","https://openalex.org/W3087943932","https://openalex.org/W2052401230","https://openalex.org/W2349022781"],"abstract_inverted_index":{"In":[0,45],"vision-language":[1,33],"retrieval":[2,34,47],"systems,":[3],"users":[4,21],"provide":[5,23],"natural":[6],"language":[7],"feedback":[8,24],"to":[9,22,40,119],"find":[10],"target":[11],"images.":[12],"Vision-language":[13],"explanations":[14],"in":[15,64,77,101],"the":[16,28,46,51,65,78,106],"systems":[17,35],"can":[18,36,57,94],"better":[19],"guide":[20],"and":[25,81,99,125],"thus":[26,82],"improve":[27],"retrieval.":[29],"However,":[30],"developing":[31],"explainable":[32,113],"be":[37,58,117],"challenging,":[38],"due":[39],"limited":[41,54,91],"labeled":[42,55,84,92],"multimodal":[43],"data.":[44],"of":[48,53,90],"complex":[49,66],"scenes,":[50,67],"issue":[52,89],"data":[56,93,96],"more":[59,83],"severe.":[60],"With":[61],"multiple":[62],"objects":[63,76],"each":[68],"user":[69,128],"query":[70],"may":[71,115],"not":[72,116],"exhaustively":[73],"describe":[74],"all":[75],"desired":[79],"image":[80],"queries":[85],"are":[86],"needed.":[87],"The":[88],"cause":[95],"selection":[97],"biases,":[98],"result":[100],"spurious":[102,110],"correlations":[103],"learned":[104],"by":[105],"models.":[107],"When":[108],"learning":[109],"correlations,":[111],"existing":[112],"models":[114],"able":[118],"accurately":[120],"extract":[121],"regions":[122],"from":[123,127],"images":[124],"keywords":[126],"queries.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}