{"id":"https://openalex.org/W4408354479","doi":"https://doi.org/10.1109/icassp49660.2025.10887841","title":"EventLens: Enhancing Visual Commonsense Reasoning by Leveraging Event-Aware Pretraining and Cross-modal Linking","display_name":"EventLens: Enhancing Visual Commonsense Reasoning by Leveraging Event-Aware Pretraining and Cross-modal Linking","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354479","doi":"https://doi.org/10.1109/icassp49660.2025.10887841"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100590007","display_name":"Mingjie Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingjie Ma","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113185525","display_name":"Zhihuan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihuan Yu","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100898886","display_name":"Yichao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichao Ma","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337866","display_name":"Guohui Li","orcid":"https://orcid.org/0000-0001-6984-1914"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohui Li","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Software Engineering,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Software Engineering,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Yang","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100590007"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03303583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9988999962806702,"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":0.9988999962806702,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9909999966621399,"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":0.9887999892234802,"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/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.8767501711845398},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.752737283706665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7120077610015869},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5972360968589783},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.5579099655151367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4055324196815491},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37081730365753174},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3641100227832794},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.12904685735702515}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.8767501711845398},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.752737283706665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7120077610015869},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5972360968589783},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.5579099655151367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4055324196815491},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37081730365753174},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3641100227832794},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.12904685735702515},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2185175083","https://openalex.org/W2560730294","https://openalex.org/W2886641317","https://openalex.org/W2914699769","https://openalex.org/W2963115613","https://openalex.org/W2970869018","https://openalex.org/W3021007069","https://openalex.org/W3090449556","https://openalex.org/W3097683561","https://openalex.org/W3173909648","https://openalex.org/W3176896951","https://openalex.org/W3194633557","https://openalex.org/W3206218097","https://openalex.org/W4226538672","https://openalex.org/W4385567175","https://openalex.org/W4386076522","https://openalex.org/W4387968123","https://openalex.org/W4390873421","https://openalex.org/W4393149524","https://openalex.org/W6639432524","https://openalex.org/W6757817989","https://openalex.org/W6766904570","https://openalex.org/W6766978945","https://openalex.org/W6767194493","https://openalex.org/W6767211374","https://openalex.org/W6767362881","https://openalex.org/W6773138695","https://openalex.org/W6778883912","https://openalex.org/W6810334672","https://openalex.org/W6811340617","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6852060543"],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W4320165839","https://openalex.org/W2151799802","https://openalex.org/W2196562041","https://openalex.org/W4385488510","https://openalex.org/W2073302931","https://openalex.org/W3206107299","https://openalex.org/W3082691151","https://openalex.org/W4287633646","https://openalex.org/W4378501473"],"abstract_inverted_index":{"Visual":[0],"Commonsense":[1],"Reasoning":[2],"(VCR)":[3],"is":[4],"a":[5,79],"cognitive":[6,86],"task,":[7,31],"challenging":[8],"models":[9],"to":[10,15,38,88,103],"answer":[11],"visual":[12,51],"questions,":[13],"and":[14,53,70,118,137],"explain":[16],"the":[17,141],"rationale":[18],"behind":[19],"their":[20,40],"answers.":[21],"While":[22],"Large":[23],"Language":[24],"Models":[25],"(LLMs)":[26],"offer":[27],"potential":[28],"for":[29],"this":[30],"VCR\u2019s":[32,50],"complex":[33,93],"scenes":[34],"require":[35],"specialized":[36],"approaches":[37],"activate":[39],"commonsense":[41,127],"reasoning":[42],"abilities,":[43],"as":[44],"existing":[45],"Multimodal":[46],"LLMs":[47],"struggle":[48],"with":[49,108,125,134],"events":[52],"unique":[54],"reference":[55,101],"tags.":[56],"To":[57],"address":[58],"these":[59],"challenges,":[60],"we":[61,77,99],"propose":[62],"EventLens,":[63],"which":[64],"enhances":[65],"VCR":[66],"through":[67],"Event-Aware":[68],"Pretraining":[69],"Cross-modal":[71],"Linking":[72],"in":[73],"Supervised":[74],"Fine-tuning.":[75],"First,":[76],"introduce":[78],"new":[80,126],"pretraining":[81],"stage":[82],"that":[83],"emulates":[84],"human":[85],"processes":[87],"improve":[89],"LLM":[90],"comprehension":[91],"of":[92,143],"scenarios.":[94],"Second,":[95],"during":[96],"supervised":[97],"fine-tuning,":[98],"leverage":[100],"tags":[102],"explicitly":[104],"bridge":[105],"RoI":[106],"features":[107],"text,":[109],"maintaining":[110],"semantic":[111],"integrity":[112],"across":[113],"modalities.":[114],"Additionally,":[115],"instruct":[116],"prompts":[117],"task-specific":[119],"adapters":[120],"help":[121],"integrate":[122],"LLMs\u2019":[123],"knowledge":[124],"reasoning.":[128],"Experimental":[129],"results":[130],"demonstrate":[131],"competitive":[132],"performance":[133],"state-of-the-art":[135],"methods":[136],"ablation":[138],"studies":[139],"verify":[140],"effectiveness":[142],"proposed":[144],"EventLens.":[145]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}