{"id":"https://openalex.org/W7133297602","doi":"https://doi.org/10.48550/arxiv.2603.01493","title":"PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval","display_name":"PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133297602","doi":"https://doi.org/10.48550/arxiv.2603.01493"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.01493","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01493","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.01493","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127951827","display_name":"Tianyi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xu, Tianyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100963648","display_name":"Rong Shan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan, Rong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127988021","display_name":"Junjie Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Junjie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125714673","display_name":"Jiadeng Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiadeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127911405","display_name":"Teng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Teng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127981821","display_name":"Jiachen Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jiachen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125512038","display_name":"Wenteng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wenteng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127971477","display_name":"Minxin Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Minxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127891751","display_name":"Quantao Dou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dou, Quantao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128031006","display_name":"Zhaoxiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhaoxiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003963705","display_name":"Changwang Zhang","orcid":"https://orcid.org/0009-0004-4193-7833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Changwang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127932982","display_name":"Weinan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Weinan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128004073","display_name":"Jun Wang (5906)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127916978","display_name":"Jianghao Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Jianghao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5127951827"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4584999978542328,"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":0.4584999978542328,"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":0.13819999992847443,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.08420000225305557,"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/embedding","display_name":"Embedding","score":0.4702000021934509},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.46059998869895935},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4101000130176544},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.4092000126838684},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.36320000886917114},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.3479999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860999703407288},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49570000171661377},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41510000824928284},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36320000886917114},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C2776945383","wikidata":"https://www.wikidata.org/wiki/Q7170667","display_name":"Personalized search","level":3,"score":0.2623000144958496}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.01493","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01493","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.01493","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01493","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.6625638008117676,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Personal":[0],"photo":[1,27],"albums":[2],"are":[3],"not":[4],"merely":[5],"collections":[6],"of":[7,166],"static":[8],"images":[9],"but":[10],"living,":[11],"ecological":[12],"archives":[13],"defined":[14],"by":[15],"temporal":[16,99],"continuity,":[17],"social":[18,96],"entanglement,":[19],"and":[20,98,133,170],"rich":[21],"metadata,":[22,95],"which":[23,90],"makes":[24],"the":[25,43,60,73,122,134,149],"personalized":[26,79],"retrieval":[28,32,155],"non-trivial.":[29],"However,":[30],"existing":[31],"benchmarks":[33],"rely":[34],"heavily":[35],"on":[36,84,116,130],"context-isolated":[37],"web":[38],"snapshots,":[39],"failing":[40],"to":[41,47,71,78],"capture":[42],"multi-source":[44,80,87,171],"reasoning":[45,163],"required":[46],"resolve":[48],"authentic,":[49,65],"intent-driven":[50,81,107],"user":[51],"queries.":[52],"To":[53],"bridge":[54],"this":[55],"gap,":[56,124],"we":[57,104],"introduce":[58],"PhotoBench,":[59],"first":[61],"benchmark":[62],"constructed":[63],"from":[64,75],"personal":[66,153],"albums.":[67],"It":[68],"is":[69,175],"designed":[70],"shift":[72],"paradigm":[74],"visual":[76,92],"matching":[77],"reasoning.":[82],"Based":[83],"a":[85],"rigorous":[86],"profiling":[88],"framework,":[89],"integrates":[91],"semantics,":[93],"spatial-temporal":[94],"identity,":[97],"events":[100],"for":[101],"each":[102],"image,":[103],"synthesize":[105],"complex":[106],"queries":[108],"rooted":[109],"in":[110,152],"users'":[111],"life":[112],"trajectories.":[113],"Extensive":[114],"evaluation":[115],"PhotoBench":[117,174],"exposes":[118],"two":[119],"critical":[120],"limitations:":[121],"modality":[123],"where":[125,138],"unified":[126,158],"embedding":[127],"models":[128],"collapse":[129],"non-visual":[131],"constraints,":[132],"source":[135],"fusion":[136],"paradox,":[137],"agentic":[139,162],"systems":[140,164],"perform":[141],"poor":[142],"tool":[143],"orchestration.":[144],"These":[145],"findings":[146],"indicate":[147],"that":[148],"next":[150],"frontier":[151],"multimodal":[154],"lies":[156],"beyond":[157],"embeddings,":[159],"necessitating":[160],"robust":[161],"capable":[165],"precise":[167],"constraint":[168],"satisfaction":[169],"fusion.":[172],"Our":[173],"available.":[176]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}