{"id":"https://openalex.org/W7164813448","doi":"https://doi.org/10.1145/3805622.3810821","title":"GjPest4CMR: LLMs-Assisted Morphology-Aware Fine-grained Goji Pest Image-Text Retrieval","display_name":"GjPest4CMR: LLMs-Assisted Morphology-Aware Fine-grained Goji Pest Image-Text Retrieval","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164813448","doi":"https://doi.org/10.1145/3805622.3810821"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810821","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810821","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064103203","display_name":"Wenkai Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I140221134","display_name":"Anhui Agricultural University","ror":"https://ror.org/0327f3359","country_code":"CN","type":"education","lineage":["https://openalex.org/I140221134"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenkai Ma","raw_affiliation_strings":["Anhui Agricultural University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-1996-5066","affiliations":[{"raw_affiliation_string":"Anhui Agricultural University, Hefei, China","institution_ids":["https://openalex.org/I140221134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031638251","display_name":"Wentao Ma","orcid":"https://orcid.org/0000-0003-3059-6629"},"institutions":[{"id":"https://openalex.org/I140221134","display_name":"Anhui Agricultural University","ror":"https://ror.org/0327f3359","country_code":"CN","type":"education","lineage":["https://openalex.org/I140221134"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Ma","raw_affiliation_strings":["Anhui Agricultural University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3059-6629","affiliations":[{"raw_affiliation_string":"Anhui Agricultural University, Hefei, China","institution_ids":["https://openalex.org/I140221134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410960","display_name":"Tan Wang","orcid":"https://orcid.org/0000-0002-0578-2078"},"institutions":[{"id":"https://openalex.org/I140221134","display_name":"Anhui Agricultural University","ror":"https://ror.org/0327f3359","country_code":"CN","type":"education","lineage":["https://openalex.org/I140221134"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan Wang","raw_affiliation_strings":["Anhui Agricultural University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0578-2078","affiliations":[{"raw_affiliation_string":"Anhui Agricultural University, Hefei, China","institution_ids":["https://openalex.org/I140221134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138628473","display_name":"Yuwei Wang","orcid":"https://orcid.org/0009-0007-7040-0527"},"institutions":[{"id":"https://openalex.org/I140221134","display_name":"Anhui Agricultural University","ror":"https://ror.org/0327f3359","country_code":"CN","type":"education","lineage":["https://openalex.org/I140221134"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Wang","raw_affiliation_strings":["Anhui Agricultural University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-7040-0527","affiliations":[{"raw_affiliation_string":"Anhui Agricultural University, Hefei, China","institution_ids":["https://openalex.org/I140221134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396485","display_name":"Lu Liu","orcid":"https://orcid.org/0000-0002-3170-9376"},"institutions":[{"id":"https://openalex.org/I140221134","display_name":"Anhui Agricultural University","ror":"https://ror.org/0327f3359","country_code":"CN","type":"education","lineage":["https://openalex.org/I140221134"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Liu","raw_affiliation_strings":["Anhui Agricultural University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0004-2055-2619","affiliations":[{"raw_affiliation_string":"Anhui Agricultural University, Hefei, China","institution_ids":["https://openalex.org/I140221134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404947","display_name":"Jie Yang","orcid":"https://orcid.org/0000-0003-4801-7162"},"institutions":[{"id":"https://openalex.org/I140221134","display_name":"Anhui Agricultural University","ror":"https://ror.org/0327f3359","country_code":"CN","type":"education","lineage":["https://openalex.org/I140221134"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfei Yang","raw_affiliation_strings":["Anhui Agricultural University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0008-4944-4231","affiliations":[{"raw_affiliation_string":"Anhui Agricultural University, Hefei, China","institution_ids":["https://openalex.org/I140221134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138646169","display_name":"Xianbao Xu","orcid":"https://orcid.org/0009-0002-6607-3942"},"institutions":[{"id":"https://openalex.org/I140221134","display_name":"Anhui Agricultural University","ror":"https://ror.org/0327f3359","country_code":"CN","type":"education","lineage":["https://openalex.org/I140221134"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianbao Xu","raw_affiliation_strings":["Anhui Agricultural University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-6607-3942","affiliations":[{"raw_affiliation_string":"Anhui Agricultural University, Hefei, China","institution_ids":["https://openalex.org/I140221134"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003835661","display_name":"Yuan Rao","orcid":"https://orcid.org/0000-0002-4386-2490"},"institutions":[{"id":"https://openalex.org/I140221134","display_name":"Anhui Agricultural University","ror":"https://ror.org/0327f3359","country_code":"CN","type":"education","lineage":["https://openalex.org/I140221134"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Rao","raw_affiliation_strings":["Anhui Agricultural University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4386-2490","affiliations":[{"raw_affiliation_string":"Anhui Agricultural University, Hefei, China","institution_ids":["https://openalex.org/I140221134"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93443925,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"138","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.19359999895095825,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.19359999895095825,"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":0.15559999644756317,"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/T10028","display_name":"Topic Modeling","score":0.08879999816417694,"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/pest-analysis","display_name":"PEST analysis","score":0.6805999875068665},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5889000296592712},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5616999864578247},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4316999912261963},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.384799987077713},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3720000088214874},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.34220001101493835}],"concepts":[{"id":"https://openalex.org/C22508944","wikidata":"https://www.wikidata.org/wiki/Q568174","display_name":"PEST analysis","level":2,"score":0.6805999875068665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5902000069618225},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5889000296592712},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5616999864578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43619999289512634},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38370001316070557},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.34220001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C2993762632","wikidata":"https://www.wikidata.org/wiki/Q219174","display_name":"Agricultural pest","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810821","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810821","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.48714184761047363,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2938719104","https://openalex.org/W2962964995","https://openalex.org/W2966002724","https://openalex.org/W3035605030","https://openalex.org/W3090449556","https://openalex.org/W3130281122","https://openalex.org/W3165084071","https://openalex.org/W3206956589","https://openalex.org/W4307372257","https://openalex.org/W4324291273","https://openalex.org/W4385748583","https://openalex.org/W4387968696","https://openalex.org/W4387969154","https://openalex.org/W4388430673","https://openalex.org/W4392158420","https://openalex.org/W4393154025","https://openalex.org/W4399423396","https://openalex.org/W4402778073","https://openalex.org/W4403780697","https://openalex.org/W4408803975","https://openalex.org/W4412431050","https://openalex.org/W4413144897","https://openalex.org/W4413156709","https://openalex.org/W4413263514","https://openalex.org/W4416684237","https://openalex.org/W7126170422","https://openalex.org/W7129078221","https://openalex.org/W7130388922"],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"agricultural":[1],"pest":[2,60,109,119],"image-text":[3,110,120],"retrieval":[4,68,121],"demands":[5],"robust":[6],"cross-modal":[7,176],"matching":[8],"capable":[9],"of":[10,216,233],"handling":[11],"subtle":[12,51],"appearance":[13],"differences":[14],"and":[15,29,50,89,149,162,193,199,218,220,226],"structured":[16,132,147],"multi-sentence":[17,131],"descriptions.":[18,133],"Yet,":[19],"small-scale":[20],"domain":[21],"data":[22],"introduces":[23],"two":[24],"key":[25],"challenges":[26],"in":[27],"supervision":[28,45,148],"representation.":[30],"First,":[31],"existing":[32],"corpora":[33],"typically":[34],"pair":[35],"each":[36],"image":[37],"with":[38,127,169,196],"a":[39,102],"single":[40],"coarse":[41],"paragraph,":[42],"providing":[43,130],"incomplete":[44],"that":[46],"omits":[47],"life-stage":[48],"appearances":[49],"morphological":[52],"traits,":[53],"while":[54],"high-frequency":[55],"redundant":[56],"fields":[57],"shared":[58],"across":[59],"categories":[61],"further":[62,229],"cause":[63],"semantic":[64],"confounding.":[65],"Second,":[66],"prevailing":[67],"models":[69],"rely":[70],"on":[71,154],"global":[72],"pooled":[73],"alignment,":[74,177],"which":[75],"averages":[76],"out":[77],"low-occupancy":[78],"but":[79],"discriminative":[80],"local":[81,156],"cues":[82],"such":[83],"as":[84],"stripe":[85],"layouts,":[86],"body":[87],"segmentation,":[88],"wing":[90],"venation,":[91],"entangling":[92],"near-neighbor":[93],"categories.":[94],"To":[95],"address":[96],"these":[97],"issues,":[98],"we":[99,138],"propose":[100],"StruMorAlign,":[101],"parameter-efficient":[103],"cross-attention":[104],"CLIP":[105],"framework":[106],"for":[107,173,190],"fine-grained":[108],"retrieval.":[111],"We":[112],"first":[113,160],"construct":[114],"GjPest4CMR,":[115],"an":[116],"English":[117],"goji":[118],"dataset":[122],"created":[123],"via":[124],"LLMs-assisted":[125],"re-writing":[126],"expert-in-the-loop":[128],"verification,":[129],"On":[134,182],"the":[135,159,179,183,203,213,231],"modeling":[136],"side,":[137],"design":[139],"StruPD":[140,217],"(Structured":[141],"Semantic":[142],"Deconfounding)":[143],"to":[144],"provide":[145],"multi-granularity":[146],"strengthen":[150],"coarse-to-fine":[151],"consistency":[152],"learning":[153],"morphology-relevant":[155],"regions,":[157],"addressing":[158,178],"challenge;":[161],"introduce":[163],"GateA2":[164],"(Gated":[165],"Adaptive":[166],"Alignment)":[167],"self-distillation":[168],"high-momentum":[170],"EMA":[171],"teacher":[172],"parameter-efficient,":[174],"morphology-aware":[175],"second":[180],"challenge.":[181],"GjPest4CMR":[184],"dataset,":[185],"StruMorAlign":[186],"achieves":[187],"mR":[188],"78.72%":[189],"both":[191],"image-to-text":[192],"text-to-image":[194],"retrieval,":[195],"I2T":[197],"R@1=53.11%":[198],"T2I":[200],"R@1=51.53%,":[201],"outperforming":[202],"strongest":[204],"baseline":[205],"HarMA":[206],"by":[207],"+9.72":[208],"mR.":[209],"Ablation":[210],"studies":[211],"confirm":[212],"complementary":[214],"benefits":[215],"GateA2,":[219],"qualitative":[221],"analyses":[222],"including":[223],"t-SNE":[224],"visualizations":[225],"attention":[227],"heatmaps":[228],"validate":[230],"effectiveness":[232],"our":[234],"approach.":[235]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}