{"id":"https://openalex.org/W4413377329","doi":"https://doi.org/10.3390/bdcc9080209","title":"SplitGround: Long-Chain Reasoning Split via Modular Multi-Expert Collaboration for Training-Free Scene Knowledge-Guided Visual Grounding","display_name":"SplitGround: Long-Chain Reasoning Split via Modular Multi-Expert Collaboration for Training-Free Scene Knowledge-Guided Visual Grounding","publication_year":2025,"publication_date":"2025-08-14","ids":{"openalex":"https://openalex.org/W4413377329","doi":"https://doi.org/10.3390/bdcc9080209"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc9080209","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9080209","pdf_url":"https://www.mdpi.com/2504-2289/9/8/209/pdf?version=1755248311","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/9/8/209/pdf?version=1755248311","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xilong Qin","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":"Xilong Qin","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053458494","display_name":"Yue Hu","orcid":"https://orcid.org/0000-0002-8115-7020"},"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":true,"raw_author_name":"Yue Hu","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017356141","display_name":"Wansen Wu","orcid":"https://orcid.org/0000-0002-0467-3830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wansen Wu","raw_affiliation_strings":["Navy Submarine Academy, Qingdao 266000, China"],"affiliations":[{"raw_affiliation_string":"Navy Submarine Academy, Qingdao 266000, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025349009","display_name":"Xinmeng Li","orcid":"https://orcid.org/0000-0002-6863-6078"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinmeng Li","raw_affiliation_strings":["Hunan Institute of Advanced Technology, Changsha 410205, China"],"affiliations":[{"raw_affiliation_string":"Hunan Institute of Advanced Technology, Changsha 410205, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100610160","display_name":"Quanjun Yin","orcid":"https://orcid.org/0000-0002-1207-8660"},"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":"Quanjun Yin","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053458494"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19441157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"8","first_page":"209","last_page":"209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.998199999332428,"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/modular-design","display_name":"Modular design","score":0.7846782207489014},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6307550668716431},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5444821119308472},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4666929841041565},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.464805006980896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40334630012512207},{"id":"https://openalex.org/keywords/engineering-drawing","display_name":"Engineering drawing","score":0.35812199115753174},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20607200264930725},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11971241235733032}],"concepts":[{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7846782207489014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6307550668716431},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5444821119308472},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4666929841041565},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.464805006980896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40334630012512207},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.35812199115753174},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20607200264930725},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11971241235733032},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/bdcc9080209","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9080209","pdf_url":"https://www.mdpi.com/2504-2289/9/8/209/pdf?version=1755248311","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7028807a57b94faead871057e2f39b64","is_oa":true,"landing_page_url":"https://doaj.org/article/7028807a57b94faead871057e2f39b64","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 9, Iss 8, p 209 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/bdcc9080209","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9080209","pdf_url":"https://www.mdpi.com/2504-2289/9/8/209/pdf?version=1755248311","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8026757606","display_name":null,"funder_award_id":"2024-JCJQ-QT-034","funder_id":"https://openalex.org/F4320311778","funder_display_name":"China Association for Science and Technology"},{"id":"https://openalex.org/G8043730865","display_name":null,"funder_award_id":"2023JJ40676","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G8092987286","display_name":null,"funder_award_id":"62306329","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320311778","display_name":"China Association for Science and Technology","ror":"https://ror.org/035vmht26"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413377329.pdf"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2064675550","https://openalex.org/W2925509384","https://openalex.org/W2946086442","https://openalex.org/W2952524542","https://openalex.org/W2983358816","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W3035097537","https://openalex.org/W3035268124","https://openalex.org/W3110435696","https://openalex.org/W3135367836","https://openalex.org/W3159619744","https://openalex.org/W3166396011","https://openalex.org/W3173364567","https://openalex.org/W3174004334","https://openalex.org/W3174965650","https://openalex.org/W3216551675","https://openalex.org/W4214490042","https://openalex.org/W4221146106","https://openalex.org/W4251712421","https://openalex.org/W4288725058","https://openalex.org/W4288747841","https://openalex.org/W4312351586","https://openalex.org/W4312845548","https://openalex.org/W4312956471","https://openalex.org/W4313026212","https://openalex.org/W4313068342","https://openalex.org/W4313145013","https://openalex.org/W4320165837","https://openalex.org/W4324128075","https://openalex.org/W4361866031","https://openalex.org/W4384820618","https://openalex.org/W4386065815","https://openalex.org/W4386071469","https://openalex.org/W4386071652","https://openalex.org/W4386071755","https://openalex.org/W4386523254","https://openalex.org/W4387272106","https://openalex.org/W4395064954","https://openalex.org/W4400009090","https://openalex.org/W4401043311","https://openalex.org/W4401416853","https://openalex.org/W4402660140","https://openalex.org/W4402727018","https://openalex.org/W4402753283","https://openalex.org/W4402753874","https://openalex.org/W4402774238","https://openalex.org/W4402952458","https://openalex.org/W4403795789","https://openalex.org/W4404534210","https://openalex.org/W4404612908","https://openalex.org/W4406077510","https://openalex.org/W4407706848","https://openalex.org/W4408393837","https://openalex.org/W4410589610","https://openalex.org/W4413144643","https://openalex.org/W6857162426","https://openalex.org/W6858268588","https://openalex.org/W6873617260"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W2378076731","https://openalex.org/W4412817058","https://openalex.org/W3216976533","https://openalex.org/W4286888643","https://openalex.org/W100620283"],"abstract_inverted_index":{"Scene":[0],"Knowledge-guided":[1],"Visual":[2],"Grounding":[3],"(SK-VG)":[4],"is":[5],"a":[6,66,81,94,186,261],"multi-modal":[7],"detection":[8],"task":[9,61],"built":[10],"upon":[11],"conventional":[12],"visual":[13,105,273],"grounding":[14,274],"(VG)":[15],"for":[16,36,181,191,271],"human\u2013computer":[17],"interaction":[18],"scenarios.":[19],"It":[20],"utilizes":[21],"an":[22,176,241],"additional":[23],"passage":[24],"of":[25,87,96,103,235,244,250],"scene":[26,58],"knowledge":[27,68,97,139,168],"apart":[28],"from":[29],"the":[30,42,50,54,85,91,104,146,162,228,232,247,251,255],"image":[31,55,166,183],"and":[32,53,93,141,165,185],"context-dependent":[33],"textual":[34],"query":[35,52,92,164,193],"referred":[37],"object":[38,142],"localization.":[39,143],"Due":[40],"to":[41,71,84,125,135,200,211],"inherent":[43],"difficulty":[44],"in":[45,90,121,138],"directly":[46],"establishing":[47],"correlations":[48],"between":[49],"given":[51],"without":[56,265],"leveraging":[57],"knowledge,":[59],"this":[60],"imposes":[62],"significant":[63,233],"demands":[64],"on":[65,100,202,227,246],"multi-step":[67],"reasoning":[69,114,128,158,204,217],"process":[70],"achieve":[72],"accurate":[73],"grounding.":[74],"Off-the-shelf":[75],"VG":[76],"models":[77],"underperform":[78],"under":[79],"such":[80],"setting":[82],"due":[83],"requirement":[86],"detailed":[88],"description":[89],"lack":[95],"inference":[98],"based":[99],"implicit":[101],"narratives":[102],"scene.":[106],"Recent":[107],"Vision\u2013Language":[108],"Models":[109],"(VLMs)":[110],"exhibit":[111],"improved":[112],"cross-modal":[113],"capabilities.":[115],"However,":[116],"their":[117],"monolithic":[118],"architectures,":[119],"particularly":[120],"lightweight":[122],"implementations,":[123],"struggle":[124],"maintain":[126],"coherent":[127],"chains":[129,218],"across":[130],"sequential":[131],"logical":[132],"deductions,":[133],"leading":[134],"error":[136],"accumulation":[137],"integration":[140],"To":[144],"address":[145],"above-mentioned":[147],"challenges,":[148],"we":[149],"propose":[150],"SplitGround\u2014a":[151],"collaborative":[152],"framework":[153],"that":[154],"strategically":[155],"decomposes":[156],"complex":[157],"processes":[159],"by":[160],"fusing":[161],"input":[163],"with":[167,222],"through":[169],"two":[170],"auxiliary":[171,208],"modules.":[172],"Specifically,":[173],"it":[174],"implements":[175],"Agentic":[177],"Annotation":[178],"Workflow":[179],"(AAW)":[180],"explicit":[182],"annotation":[184],"Synonymous":[187],"Conversion":[188],"Mechanism":[189],"(SCM)":[190],"semantic":[192],"transformation.":[194],"This":[195],"hierarchical":[196],"decomposition":[197],"enables":[198],"VLMs":[199],"focus":[201],"essential":[203],"steps":[205],"while":[206],"offloading":[207],"cognitive":[209],"tasks":[210],"specialized":[212],"modules,":[213],"effectively":[214],"splitting":[215],"long":[216],"into":[219],"manageable":[220],"subtasks":[221],"reduced":[223],"complexity.":[224],"Comprehensive":[225],"evaluations":[226],"SK-VG":[229],"benchmark":[230],"demonstrate":[231],"advancements":[234],"our":[236],"method.":[237],"Remarkably,":[238],"SplitGround":[239],"attains":[240],"accuracy":[242],"improvement":[243],"15.71%":[245],"hard":[248],"split":[249],"test":[252],"set":[253],"over":[254],"previous":[256],"training-required":[257],"SOTA,":[258],"using":[259],"only":[260],"compact":[262],"VLM":[263],"backbone":[264],"fine-tuning,":[266],"which":[267],"provides":[268],"new":[269],"insights":[270],"knowledge-intensive":[272],"tasks.":[275]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}