{"id":"https://openalex.org/W4415276857","doi":"https://doi.org/10.1109/iccv51701.2025.02595","title":"Fusion Meets Diverse Conditions: A High-Diversity Benchmark and Baseline for UAV-Based Multimodal Object Detection with Condition Cues","display_name":"Fusion Meets Diverse Conditions: A High-Diversity Benchmark and Baseline for UAV-Based Multimodal Object Detection with Condition Cues","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415276857","doi":"https://doi.org/10.1109/iccv51701.2025.02595"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.02595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.13620","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111598130","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0002-4971-5029"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["National University of Defense Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018248885","display_name":"Kangcheng Bin","orcid":"https://orcid.org/0000-0002-3352-9854"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangcheng Bin","raw_affiliation_strings":["National University of Defense Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076522568","display_name":"Ting Hu","orcid":"https://orcid.org/0000-0002-7134-1748"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Hu","raw_affiliation_strings":["National University of Defense Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071985172","display_name":"Jiahao Qi","orcid":"https://orcid.org/0000-0002-2560-8157"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Qi","raw_affiliation_strings":["National University of Defense Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101943329","display_name":"Xingyue Liu","orcid":"https://orcid.org/0000-0001-5071-5686"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyue Liu","raw_affiliation_strings":["National University of Defense Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103078106","display_name":"Tianpeng Liu","orcid":"https://orcid.org/0000-0003-1239-1240"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianpeng Liu","raw_affiliation_strings":["National University of Defense Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412083","display_name":"Zhen Liu","orcid":"https://orcid.org/0000-0003-0917-5475"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Liu","raw_affiliation_strings":["National University of Defense Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115592234","display_name":"Yongxiang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxiang Liu","raw_affiliation_strings":["National University of Defense Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002771011","display_name":"Ping Zhong","orcid":"https://orcid.org/0000-0003-3393-8874"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Zhong","raw_affiliation_strings":["National University of Defense Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"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":0.35113067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27958","last_page":"27967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9174000024795532,"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":0.9086999893188477,"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":0.715499997138977},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6924999952316284},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5476999878883362},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5302000045776367},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4498000144958496},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4018999934196472},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.3813999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7414000034332275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7160999774932861},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.715499997138977},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6924999952316284},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5302000045776367},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5134000182151794},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.13620","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.13620","pdf_url":"https://arxiv.org/pdf/2510.13620","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.13620","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.13620","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.13620","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.13620","pdf_url":"https://arxiv.org/pdf/2510.13620","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415276857.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unmanned":[0],"aerial":[1],"vehicles":[2],"(UAV)-based":[3],"object":[4],"detection":[5],"with":[6,85],"visible":[7],"(RGB)":[8],"and":[9,24,67,75,136],"infrared":[10],"(IR)":[11],"images":[12],"facilitates":[13],"robust":[14],"around-the-clock":[15],"detection,":[16],"driven":[17],"by":[18,99,117],"advancements":[19],"in":[20,72,152],"deep":[21],"learning":[22],"techniques":[23],"the":[25,31,96,132,150,162],"availability":[26,151],"of":[27,164],"high-quality":[28],"dataset.":[29],"However,":[30],"existing":[32],"dataset":[33,51,160],"struggles":[34],"to":[35,60,65,112],"fully":[36],"capture":[37],"real-world":[38],"complexity":[39],"for":[40],"limited":[41],"imaging":[42,124],"conditions.":[43,77],"To":[44,94],"this":[45],"end,":[46],"we":[47,103],"introduce":[48],"a":[49,105,140],"high-diversity":[50],"ATR-UMOD":[52,159],"covering":[53],"varying":[54],"scenarios,":[55],"spanning":[56],"altitudes":[57],"from":[58,63],"80m":[59],"300m,":[61],"angles":[62],"0\u00b0":[64],"75\u00b0,":[66],"all-day,":[68],"all-year":[69],"time":[70],"variations":[71],"rich":[73],"weather":[74],"illumination":[76],"Moreover,":[78],"each":[79],"RGB-IR":[80],"image":[81],"pair":[82],"is":[83],"annotated":[84,119],"6":[86],"condition":[87,120,155],"attributes,":[88],"offering":[89],"valuable":[90],"high-level":[91],"contextual":[92],"information.":[93],"meet":[95],"challenge":[97],"raised":[98],"such":[100],"diverse":[101],"conditions,":[102],"propose":[104],"novel":[106],"prompt-guided":[107,145],"condition-aware":[108],"dynamic":[109],"fusion":[110],"(PCDF)":[111],"adaptively":[113],"reassign":[114],"multimodal":[115,137],"contributions":[116,138],"leveraging":[118],"cues.":[121],"By":[122],"encoding":[123],"conditions":[125,135],"as":[126],"text":[127],"prompts,":[128],"PCDF":[129],"effectively":[130],"models":[131],"relationship":[133],"between":[134],"through":[139],"task-specific":[141],"soft-gating":[142],"transformation.":[143],"A":[144],"condition-decoupling":[146],"module":[147],"further":[148],"ensures":[149],"practice":[153],"without":[154],"annotations.":[156],"Experiments":[157],"on":[158],"reveal":[161],"effectiveness":[163],"PCDF.":[165]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-17T00:00:00"}