{"id":"https://openalex.org/W4415540329","doi":"https://doi.org/10.1145/3746027.3755124","title":"Detecting Violations of Physical Common Sense in Images: A Challenge Dataset and Effective Model","display_name":"Detecting Violations of Physical Common Sense in Images: A Challenge Dataset and Effective Model","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540329","doi":"https://doi.org/10.1145/3746027.3755124"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755124","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5004605359","display_name":"Weibin Wu","orcid":"https://orcid.org/0000-0002-7262-6219"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weibin Wu","raw_affiliation_strings":["School of Software Engineering, Zhuhai Key Laboratory of Trusted Large Language Models, Sun Yat-sen University, Zhuhai, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Zhuhai Key Laboratory of Trusted Large Language Models, Sun Yat-sen University, Zhuhai, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zitong Wang","orcid":"https://orcid.org/0009-0003-8328-6197"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zitong Wang","raw_affiliation_strings":["International School of Business and Finance, Sun Yat-sen University, Zhuhai, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"International School of Business and Finance, Sun Yat-sen University, Zhuhai, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhengjie Luo","orcid":"https://orcid.org/0009-0008-1406-735X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengjie Luo","raw_affiliation_strings":["School of Software Engineering, Zhuhai Key Laboratory of Trusted Large Language Models, Sun Yat-sen University, Zhuhai, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Zhuhai Key Laboratory of Trusted Large Language Models, Sun Yat-sen University, Zhuhai, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628705","display_name":"Wenqing Chen","orcid":"https://orcid.org/0000-0002-8739-2216"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqing Chen","raw_affiliation_strings":["School of Software Engineering, Zhuhai Key Laboratory of Trusted Large Language Models, Sun Yat-sen University, Zhuhai, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Zhuhai Key Laboratory of Trusted Large Language Models, Sun Yat-sen University, Zhuhai, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000582109","display_name":"Zibin Zheng","orcid":"https://orcid.org/0000-0002-7878-4330"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zibin Zheng","raw_affiliation_strings":["School of Software Engineering, Zhuhai Key Laboratory of Trusted Large Language Models, Sun Yat-sen University, Zhuhai, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Zhuhai Key Laboratory of Trusted Large Language Models, Sun Yat-sen University, Zhuhai, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004605359"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29938757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10945","last_page":"10954"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9958999752998352,"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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9857000112533569,"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/common-sense","display_name":"Common sense","score":0.7621999979019165},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7214999794960022},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.49729999899864197},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4309000074863434},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.3993000090122223},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3319999873638153},{"id":"https://openalex.org/keywords/physical-system","display_name":"Physical system","score":0.3208000063896179}],"concepts":[{"id":"https://openalex.org/C2779814899","wikidata":"https://www.wikidata.org/wiki/Q332880","display_name":"Common sense","level":2,"score":0.7621999979019165},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7214999794960022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6158000230789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5759999752044678},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42149999737739563},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C31084985","wikidata":"https://www.wikidata.org/wiki/Q372650","display_name":"Common knowledge (logic)","level":5,"score":0.28529998660087585},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C14396502","wikidata":"https://www.wikidata.org/wiki/Q280951","display_name":"Common cause and special cause","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755124","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6124034781","display_name":null,"funder_award_id":"62206318, 62306344","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2185175083","https://openalex.org/W4220717841","https://openalex.org/W4392172801","https://openalex.org/W4405595839","https://openalex.org/W4411450064","https://openalex.org/W4411450306"],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1,21],"(VLMs)":[2],"have":[3],"achieved":[4],"remarkable":[5],"success":[6],"in":[7,56,96,188],"various":[8],"vision-language":[9],"tasks,":[10],"such":[11],"as":[12],"image":[13],"captioning":[14],"and":[15],"visual":[16,152],"question":[17],"answering.":[18],"However,":[19],"these":[20],"often":[22],"lack":[23],"physical":[24,36,44,93,134,153,171,189],"common":[25,35,45,94,135,190],"sense,":[26],"frequently":[27],"failing":[28],"to":[29,83,89,125,130,151,163],"identify":[30],"visually":[31],"evident":[32],"violations":[33,91,132],"of":[34,43,76,92,133],"principles.":[37],"Therefore,":[38],"evaluating":[39],"the":[40,86,103,127,145,165,177,185],"VLMs'":[41,87,128],"understanding":[42],"sense":[46,95,191],"is":[47],"essential,":[48],"which":[49,143],"has":[50],"not":[51],"yet":[52],"been":[53],"systematically":[54,84],"explored":[55],"existing":[57],"research.":[58],"To":[59],"fill":[60],"this":[61],"gap,":[62],"we":[63,118],"introduce":[64],"PhyVIB":[65],"(Physical":[66],"Common":[67],"Sense":[68],"Violation":[69],"Image":[70],"Benchmark).":[71],"This":[72],"novel":[73],"benchmark":[74],"consists":[75],"16,000":[77],"images":[78],"across":[79],"eight":[80],"categories,":[81],"aiming":[82],"assess":[85],"capability":[88,129,169],"detect":[90,131],"images.":[97],"Our":[98,193],"evaluations":[99],"show":[100,175],"that":[101,176],"even":[102],"state-of-the-art":[104,186],"VLMs":[105,187],"perform":[106],"poorly":[107],"on":[108,170],"PhyVIB,":[109],"highlighting":[110],"a":[111,121],"significant":[112],"area":[113],"for":[114],"improvement.":[115],"In":[116],"response,":[117],"propose":[119],"PhyDetector,":[120],"two-stage":[122],"fine-tuning":[123],"framework":[124],"enhance":[126,164],"sense.":[136],"The":[137,155],"first":[138],"stage":[139,157],"involves":[140],"supervised":[141],"fine-tuning,":[142],"equips":[144],"VLM":[146],"with":[147,180],"essential":[148],"concepts":[149],"related":[150],"anomalies.":[154],"second":[156],"utilizes":[158],"group":[159],"relative":[160],"policy":[161],"optimization":[162],"VLM's":[166],"multimodal":[167],"reasoning":[168],"plausibility.":[172],"Experimental":[173],"results":[174],"model":[178],"fine-tuned":[179],"PhyDetector":[181],"can":[182],"significantly":[183],"outperform":[184],"understanding.":[192],"artifacts":[194],"are":[195],"available":[196],"at":[197],"https://github.com/ZitongWang018/PhyVIB.":[198]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}