{"id":"https://openalex.org/W6888598112","doi":"https://doi.org/10.21227/q94c-c298","title":"MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image","display_name":"MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image","publication_year":2024,"publication_date":"2024-11-24","ids":{"openalex":"https://openalex.org/W6888598112","doi":"https://doi.org/10.21227/q94c-c298"},"language":"en","primary_location":{"id":"doi:10.21227/q94c-c298","is_oa":true,"landing_page_url":"https://doi.org/10.21227/q94c-c298","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/q94c-c298","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Song, Shezheng","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":true,"raw_author_name":"Song, Shezheng","raw_affiliation_strings":["National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"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":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.8281000256538391},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6560999751091003},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6413000226020813},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6305000185966492},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5809999704360962},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4794999957084656}],"concepts":[{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.8281000256538391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004999756813049},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6560999751091003},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6413000226020813},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6305000185966492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6164000034332275},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5809999704360962},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5044999718666077},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4794999957084656},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.39239999651908875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3871000111103058},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/q94c-c298","is_oa":true,"landing_page_url":"https://doi.org/10.21227/q94c-c298","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"dataset"}],"best_oa_location":{"id":"doi:10.21227/q94c-c298","is_oa":true,"landing_page_url":"https://doi.org/10.21227/q94c-c298","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"dataset"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5111141204833984}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3],"(MLLMs)":[4],"have":[5],"shown":[6],"remarkable":[7],"progress":[8],"in":[9,37,44,88,110,151,169],"high-level":[10],"semantic":[11,45],"tasks":[12,156],"such":[13],"as":[14,134,160],"visual":[15],"question":[16],"answering,":[17],"image":[18],"captioning,":[19],"and":[20,100,118,130,157],"emotion":[21],"recognition.":[22],"However,":[23],"despite":[24],"advancements,":[25],"there":[26],"remains":[27],"a":[28,41,54,161],"lack":[29],"of":[30,79],"standardized":[31],"benchmarks":[32],"for":[33,60,95,146,164],"evaluating":[34],"MLLMs":[35,73,147],"performance":[36,131],"multi-object":[38,61,153],"sentiment":[39,62,78,154,166],"analysis,":[40],"key":[42],"task":[43],"understanding.":[46],"To":[47],"address":[48],"this":[49],"gap,":[50],"we":[51],"introduce":[52],"MOSABench,":[53],"novel":[55],"evaluation":[56,96],"dataset":[57],"designed":[58],"specifically":[59],"analysis.":[63],"MOSABench":[64,89,159],"includes":[65],"approximately":[66],"1,000":[67],"images":[68],"with":[69],"multiple":[70],"objects,":[71],"requiring":[72],"to":[74,97,123,148],"independently":[75],"assess":[76],"the":[77,135,144],"each":[80],"object,":[81],"thereby":[82],"reflecting":[83],"real-world":[84],"complexities.":[85],"Key":[86],"innovations":[87],"include":[90],"distance-based":[91],"target":[92],"annotation,":[93],"post-processing":[94],"standardize":[98],"outputs,":[99],"an":[101],"improved":[102],"scoring":[103],"mechanism.":[104],"Our":[105],"experiments":[106],"reveal":[107],"notable":[108],"limitations":[109],"current":[111],"MLLMs:":[112],"while":[113],"some":[114],"models,":[115],"like":[116],"mPLUG-owl":[117],"Qwen-VL2,":[119],"demonstrate":[120],"effective":[121],"attention":[122],"sentiment-relevant":[124],"features,":[125],"others":[126],"exhibit":[127],"scattered":[128],"focus":[129],"declines,":[132],"especially":[133],"spatial":[136],"distance":[137],"between":[138],"objects":[139],"increases.":[140],"This":[141],"research":[142],"underscores":[143],"need":[145],"enhance":[149],"accuracy":[150],"complex,":[152],"analysis":[155,167],"establishes":[158],"foundational":[162],"tool":[163],"advancing":[165],"capabilities":[168],"MLLMs.":[170]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}