{"id":"https://openalex.org/W4416654759","doi":"https://doi.org/10.1145/3805712.3809532","title":"Attention Grounded Enhancement for Visual Document Retrieval","display_name":"Attention Grounded Enhancement for Visual Document Retrieval","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W4416654759","doi":"https://doi.org/10.1145/3805712.3809532"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809532","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809532","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809532","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084278260","display_name":"Wanqing Cui","orcid":"https://orcid.org/0000-0001-5015-5252"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanqing Cui","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5015-5252","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072873702","display_name":"Wei Huang","orcid":"https://orcid.org/0000-0001-8324-8877"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-1556-8198","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009270055","display_name":"Yazhi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yazhi Guo","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-7148-411X","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081891813","display_name":"Yibo Hu","orcid":"https://orcid.org/0000-0002-9647-9647"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Hu","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-7762-6986","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Meiguang Jin","orcid":"https://orcid.org/0000-0003-3796-2310"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiguang Jin","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3796-2310","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052717498","display_name":"Junfeng Ma","orcid":"https://orcid.org/0000-0002-8914-3125"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Ma","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-8589-1006","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040708820","display_name":"Keping Bi","orcid":"https://orcid.org/0000-0001-5123-4999"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keping Bi","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-4999","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"223","last_page":"233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8424999713897705,"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":0.8424999713897705,"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":0.07599999755620956,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.01209999993443489,"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/relevance","display_name":"Relevance (law)","score":0.5985999703407288},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5476999878883362},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5019000172615051},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49300000071525574},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.41260001063346863},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.38449999690055847},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.3749000132083893},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.36079999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046000003814697},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5985999703407288},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5724999904632568},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5019000172615051},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49300000071525574},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41110000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40880000591278076},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38449999690055847},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.36079999804496765},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.3375999927520752},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.2660999894142151},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3805712.3809532","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809532","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.13415","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.13415","pdf_url":"https://arxiv.org/pdf/2511.13415","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.2511.13415","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.13415","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":"doi:10.1145/3805712.3809532","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809532","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G229693334","display_name":null,"funder_award_id":"62302486","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"document":[1,18,110,123,182,221],"retrieval":[2,34,183],"requires":[3],"understanding":[4],"heterogeneous":[5],"and":[6,28,63,197,204,207,220,230],"multi-modal":[7],"content":[8,174],"to":[9,24,58,65,73,103,127,153,164],"satisfy":[10],"implicit":[11,67],"information":[12,27],"needs.":[13],"Recent":[14],"advances":[15],"use":[16],"screenshot-based":[17],"encoding":[19],"with":[20,41,147],"fine-grained":[21,79],"late":[22],"interaction":[23],"encode":[25],"holistic":[26],"capture":[29,66],"nuanced":[30],"alignments,":[31],"significantly":[32,190],"improving":[33],"performance.":[35],"However,":[36],"retrievers":[37,56],"are":[38,125],"still":[39],"trained":[40],"coarse":[42],"global":[43,149],"relevance":[44,80,139,151],"labels,":[45],"without":[46],"revealing":[47],"which":[48,122,173],"regions":[49,124],"support":[50],"the":[51,105,118,130,148,156,162,179,192],"match.":[52],"As":[53],"a":[54,84],"result,":[55],"tend":[57],"rely":[59],"on":[60,129,178],"surface-level":[61,225],"cues":[62],"struggle":[64],"semantic":[68],"connections,":[69],"hindering":[70],"their":[71],"ability":[72],"handle":[74],"non-extractive":[75],"queries.":[76],"To":[77],"improve":[78],"modeling,":[81],"we":[82],"propose":[83],"Attention-Grounded":[85],"REtriever":[86],"Enhancement":[87],"(AGREE)":[88],"framework.":[89],"AGREE":[90,113,143,189,213],"leverages":[91],"cross-modal":[92],"attention":[93,115,133],"from":[94,117],"multimodal":[95],"large":[96],"language":[97],"models":[98],"(MLLMs)":[99],"as":[100,136],"proxy":[101],"supervision":[102,160],"guide":[104],"retriever":[106],"in":[107,199],"identifying":[108],"relevant":[109],"regions.":[111],"Specifically,":[112],"extracts":[114],"maps":[116],"MLLM":[119],"that":[120,188,212],"highlight":[121],"attended":[126],"based":[128],"query.":[131],"These":[132],"scores":[134],"serve":[135],"local,":[137],"region-level":[138],"signals.":[140],"During":[141],"training,":[142],"combines":[144],"local":[145],"signals":[146],"document-level":[150],"label":[152],"jointly":[154],"optimize":[155],"retriever.":[157],"This":[158],"dual-level":[159],"enables":[161],"model":[163],"learn":[165],"not":[166],"only":[167],"whether":[168],"documents":[169],"match,":[170],"but":[171],"also":[172],"drives":[175],"relevance.":[176],"Experiments":[177],"challenging":[180],"visual":[181],"benchmark,":[184],"ViDoRe":[185],"V2,":[186],"show":[187],"outperforms":[191],"global-supervision-only":[193],"baseline":[194],"by":[195],"12.82%":[196],"5.03%":[198],"terms":[200,219],"of":[201],"average":[202],"nDCG@1":[203],"nDCG@5.":[205],"Quantitative":[206],"qualitative":[208],"analyses":[209],"further":[210],"demonstrate":[211],"promotes":[214],"deeper":[215],"alignment":[216],"between":[217],"query":[218],"regions,":[222],"moving":[223],"beyond":[224],"matching":[226],"toward":[227],"more":[228],"accurate":[229],"interpretable":[231],"retrieval.":[232],"Our":[233],"code":[234],"is":[235],"available":[236],"at:":[237],"https://github.com/VickiCui/AGREE.":[238]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2025-11-19T00:00:00"}