{"id":"https://openalex.org/W7138000616","doi":"https://doi.org/10.1609/aaai.v40i14.38181","title":"RIS-LAD: A Benchmark and Model for Referring Image Segmentation in Low-Altitude Drone Imagery","display_name":"RIS-LAD: A Benchmark and Model for Referring Image Segmentation in Low-Altitude Drone Imagery","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138000616","doi":"https://doi.org/10.1609/aaai.v40i14.38181"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i14.38181","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38181","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38181/42143","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38181/42143","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129705830","display_name":"Kai Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Ye","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011239592","display_name":"Yijun Luan","orcid":"https://orcid.org/0000-0002-6590-9229"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"YingShi Luan","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121954445","display_name":"Zhudi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhudi Chen","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129719188","display_name":"Guangyue Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyue Meng","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032612432","display_name":"Pingyang Dai","orcid":"https://orcid.org/0000-0001-9780-271X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingyang Dai","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129656396","display_name":"Liujuan Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujuan Cao","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"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":"40","issue":"14","first_page":"11937","last_page":"11945"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7738999724388123,"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":0.7738999724388123,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.1200999990105629,"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":0.015799999237060547,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6883000135421753},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.6492000222206116},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6489999890327454},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.5644000172615051},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5537999868392944},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48910000920295715},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4074999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7028999924659729},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6883000135421753},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.6492000222206116},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6489999890327454},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47209998965263367},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4074999988079071},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.302700012922287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29030001163482666},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i14.38181","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38181","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38181/42143","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38181","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38181","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38181","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38181/42143","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1300220747","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G187639494","display_name":null,"funder_award_id":"No. 62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G2564228358","display_name":null,"funder_award_id":"No. 62025603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3568142893","display_name":null,"funder_award_id":"62272401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G363226264","display_name":null,"funder_award_id":"U23A20383","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5284885812","display_name":null,"funder_award_id":"62176222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G6727647225","display_name":null,"funder_award_id":"62176226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G717600273","display_name":null,"funder_award_id":"U22B2051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7272499820","display_name":null,"funder_award_id":"U21B2037","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"},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138000616.pdf","grobid_xml":"https://content.openalex.org/works/W7138000616.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Referring":[0],"Image":[1],"Segmentation":[2],"(RIS),":[3],"which":[4,112],"aims":[5],"to":[6,52,119,156,170],"segment":[7],"specific":[8],"objects":[9,100],"based":[10],"on":[11,96],"natural":[12],"language":[13],"descriptions,":[14],"plays":[15],"an":[16],"essential":[17],"role":[18],"in":[19,25,159,183],"vision-language":[20],"understanding.":[21],"Despite":[22],"its":[23],"progress":[24],"remote":[26],"sensing":[27],"applications,":[28],"RIS":[29,77,172],"under":[30],"Low-Altitude":[31],"Drone":[32],"(LAD)":[33],"scenarios":[34],"remains":[35],"underexplored,":[36],"as":[37,61],"existing":[38],"datasets":[39],"and":[40,47,64,101,114,174],"methods":[41],"are":[42],"typically":[43],"designed":[44],"for":[45,80],"high-altitude":[46],"static-view":[48],"imagery.":[49],"They":[50],"struggled":[51],"handle":[53],"the":[54,74,107,131,145,177],"unique":[55],"characteristics":[56],"of":[57,179],"LAD":[58,81],"views,":[59],"such":[60],"diverse":[62],"viewpoints":[63],"high":[65],"object":[66,139],"density.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,105],"propose":[72,106],"RIS-LAD,":[73],"first":[75],"fine-grained":[76],"benchmark":[78],"tailored":[79],"scenarios,":[82],"featuring":[83],"13,871":[84],"meticulously":[85],"annotated":[86],"image-text-mask":[87],"triplets":[88],"collected":[89],"from":[90],"real-world":[91],"drone":[92],"footage":[93],"with":[94,138],"emphasis":[95],"small,":[97],"densely":[98],"cluttered":[99],"multi-view":[102],"perspectives.":[103],"Additionally,":[104],"Semantic-Aware":[108],"Adaptive":[109,146],"Reasoning":[110,147],"Network,":[111],"decomposes":[113],"adaptively":[115],"routes":[116],"semantic":[117,152],"information":[118],"different":[120],"network":[121],"stages":[122],"rather":[123],"than":[124],"uniformly":[125],"injecting":[126],"all":[127],"linguistic":[128],"features.":[129],"Specifically,":[130],"Category-Dominated":[132],"Linguistic":[133],"Enhancement":[134],"aligns":[135],"visual":[136],"features":[137],"categories":[140],"during":[141],"early":[142],"encoding,":[143],"while":[144],"Fusion":[148],"Module":[149],"dynamically":[150],"selects":[151],"cues":[153],"across":[154],"scales":[155],"enhance":[157],"reasoning":[158],"complex":[160],"scenes.":[161],"Extensive":[162],"experiments":[163],"reveal":[164],"that":[165],"RIS-LAD":[166],"presents":[167],"substantial":[168],"challenges":[169],"state-of-the-art":[171],"algorithms,":[173],"also":[175],"demonstrate":[176],"effectiveness":[178],"our":[180],"proposed":[181],"model":[182],"addressing":[184],"these":[185],"challenges.":[186]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}