{"id":"https://openalex.org/W4417066038","doi":"https://doi.org/10.1109/iccv51701.2025.00245","title":"VisRL: Intention-Driven Visual Perception via Reinforced Reasoning","display_name":"VisRL: Intention-Driven Visual Perception via Reinforced Reasoning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417066038","doi":"https://doi.org/10.1109/iccv51701.2025.00245"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00245","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.07523","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102796839","display_name":"Zhangquan Chen","orcid":"https://orcid.org/0000-0003-4531-2430"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangquan Chen","raw_affiliation_strings":["Tsinghua University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035359374","display_name":"Xufang Luo","orcid":"https://orcid.org/0000-0002-3405-554X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xufang Luo","raw_affiliation_strings":["Microsoft Research Asia,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440920","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0003-3103-8442"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["Microsoft Research Asia,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,China","institution_ids":["https://openalex.org/I4210113369"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2545","last_page":"2555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8428000211715698,"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":0.8428000211715698,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.05689999833703041,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.013700000010430813,"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/visual-reasoning","display_name":"Visual reasoning","score":0.6661999821662903},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.595300018787384},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4999000132083893},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4932999908924103},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4733000099658966},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.47290000319480896},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4440000057220459},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4138999879360199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7340999841690063},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6661999821662903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6464999914169312},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.595300018787384},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4932999908924103},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4717999994754791},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.39570000767707825},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.32120001316070557},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00245","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:2503.07523","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.07523","pdf_url":"https://arxiv.org/pdf/2503.07523","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.07523","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.07523","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":"pmh:oai:arXiv.org:2503.07523","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.07523","pdf_url":"https://arxiv.org/pdf/2503.07523","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":"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":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0,44],"understanding":[1],"is":[2,182],"inherently":[3],"intention-driven":[4,110],"-":[5],"humans":[6,151],"selectively":[7],"focus":[8,60,127],"on":[9,16,71],"different":[10,178],"regions":[11],"of":[12,29,50,88,109],"a":[13,59,64],"scene":[14],"based":[15],"their":[17],"goals.":[18],"Recent":[19],"advances":[20],"in":[21],"large":[22],"multimodal":[23],"models":[24],"(LMMs)":[25],"enable":[26],"flexible":[27],"expression":[28],"such":[30],"intentions":[31],"through":[32,134],"natural":[33],"language,":[34],"allowing":[35],"queries":[36],"to":[37,84,106,153],"guide":[38],"visual":[39,111,117],"reasoning":[40,53,118],"processes.":[41],"Frameworks":[42],"like":[43],"Chain-of-Thought":[45],"have":[46],"demonstrated":[47],"the":[48,56,85,98,107,115,139,155],"benefit":[49],"incorporating":[51],"explicit":[52],"steps,":[54],"where":[55],"model":[57],"predicts":[58],"region":[61,143],"before":[62],"answering":[63],"query.":[65],"However,":[66],"existing":[67],"approaches":[68],"rely":[69],"heavily":[70],"supervised":[72],"training":[73],"with":[74,149],"annotated":[75],"intermediate":[76,126],"bounding":[77],"boxes,":[78],"which":[79],"severely":[80],"limits":[81],"scalability":[82],"due":[83],"combinatorial":[86],"explosion":[87],"intention-region":[89],"pairs.":[90],"To":[91],"overcome":[92],"this":[93],"limitation,":[94],"we":[95],"propose":[96],"VisRL,":[97],"first":[99],"framework":[100],"that":[101,163],"applies":[102],"reinforcement":[103],"learning":[104],"(RL)":[105],"problem":[108],"perception.":[112],"VisRL":[113,164],"optimizes":[114],"entire":[116],"process":[119],"using":[120],"only":[121],"reward":[122],"signals.":[123],"By":[124],"treating":[125],"selection":[128],"as":[129],"an":[130],"internal":[131],"decision":[132],"optimized":[133],"trial-and-error,":[135],"our":[136],"method":[137],"eliminates":[138],"need":[140],"for":[141],"costly":[142],"annotations":[144],"while":[145],"aligning":[146],"more":[147],"closely":[148],"how":[150],"learn":[152],"perceive":[154],"world.":[156],"Extensive":[157],"experiments":[158],"across":[159,177],"multiple":[160],"benchmarks":[161],"show":[162],"consistently":[165],"outperforms":[166],"strong":[167,175],"baselines,":[168],"demonstrating":[169],"both":[170],"its":[171,174],"effectiveness":[172],"and":[173],"generalization":[176],"LMMs.":[179],"Our":[180],"code":[181],"available":[183],"at":[184],"https://github.com/zhangquanchen/VisRL.":[185]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}