{"id":"https://openalex.org/W4396723445","doi":"https://doi.org/10.1145/3589334.3648146","title":"CapAlign: Improving Cross Modal Alignment via Informative Captioning for Harmful Meme Detection","display_name":"CapAlign: Improving Cross Modal Alignment via Informative Captioning for Harmful Meme Detection","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4396723445","doi":"https://doi.org/10.1145/3589334.3648146"},"language":"en","primary_location":{"id":"doi:10.1145/3589334.3648146","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589334.3648146","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589334.3648146?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589334.3648146?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012249481","display_name":"Junhui Ji","orcid":"https://orcid.org/0009-0009-2811-1865"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Junhui Ji","raw_affiliation_strings":["School of Computer Science, University of Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0009-2811-1865","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056294749","display_name":"Xuanrui Lin","orcid":"https://orcid.org/0009-0006-2096-0270"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanrui Lin","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-2096-0270","affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077006200","display_name":"Usman Naseem","orcid":"https://orcid.org/0000-0003-0191-7171"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Usman Naseem","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0191-7171","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012249481"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":1.6114,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84172328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4585","last_page":"4594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9907000064849854,"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":0.9907000064849854,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9904000163078308,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9782000184059143,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/closed-captioning","display_name":"Closed captioning","score":0.840256929397583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7230287790298462},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6708508729934692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47797152400016785},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07909512519836426},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.04327234625816345}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.840256929397583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230287790298462},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6708508729934692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47797152400016785},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07909512519836426},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.04327234625816345},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589334.3648146","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589334.3648146","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589334.3648146?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589334.3648146","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589334.3648146","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589334.3648146?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396723445.pdf","grobid_xml":"https://content.openalex.org/works/W4396723445.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2116873850","https://openalex.org/W2143747826","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2612690371","https://openalex.org/W2951937667","https://openalex.org/W2963446712","https://openalex.org/W2964018924","https://openalex.org/W2964121744","https://openalex.org/W3023989664","https://openalex.org/W4212774754","https://openalex.org/W4221143046","https://openalex.org/W4226278401","https://openalex.org/W4288116810","https://openalex.org/W4293518081","https://openalex.org/W4297816851","https://openalex.org/W4298092567","https://openalex.org/W4298201898","https://openalex.org/W4304098539","https://openalex.org/W4318718936","https://openalex.org/W4320561490","https://openalex.org/W4321480037","https://openalex.org/W4324321291","https://openalex.org/W4367047467","https://openalex.org/W4385573042","https://openalex.org/W4385805046","https://openalex.org/W4387969708"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403"],"abstract_inverted_index":{"Harmful":[0],"memes":[1],"detection":[2],"is":[3],"challenging":[4],"due":[5],"to":[6,22,96,100,109,116,134,155],"the":[7,31,34,38,107,118,122,139,146,149],"semantic":[8],"gap":[9,40],"between":[10],"different":[11],"modalities.":[12],"Previous":[13],"studies":[14],"mainly":[15],"focus":[16],"on":[17,163],"feature":[18],"extraction":[19],"and":[20,41,60,105,141,174],"fusion":[21],"learn":[23],"discriminative":[24],"information":[25],"from":[26,43],"memes.":[27,181],"However,":[28],"they":[29],"ignore":[30],"misalignment":[32],"of":[33,50,125,138,148,152],"modalities":[35],"caused":[36],"by":[37],"modality":[39],"suffer":[42],"data":[44],"scarcity,":[45],"resulting":[46,66],"in":[47,67,83],"insufficient":[48],"learning":[49],"fusion-based":[51],"models.":[52],"Recently,":[53],"researchers":[54],"transformed":[55],"images":[56],"into":[57],"textual":[58,123],"captions":[59,137,173],"used":[61,129],"language":[62,93],"models":[63],"for":[64,159,178],"predictions,":[65],"non-informative":[68],"image":[69,113],"captions.":[70],"To":[71],"address":[72],"these":[73],"gaps,":[74],"this":[75],"paper":[76],"proposes":[77],"an":[78,130],"instructions-based":[79],"abstracting":[80],"approach":[81,170],"CapAlign,":[82],"zero-shot":[84],"visual":[85,150],"question-answering":[86],"settings.":[87],"Precisely,":[88],"we":[89,128],"prompt":[90],"a":[91,101,111,126,153,156],"large":[92],"model":[94,104],"(LLM)":[95],"ask":[97],"informative":[98,136,172],"questions":[99],"pre-trained":[102],"vision-language":[103],"use":[106],"dialogues":[108],"generate":[110,135],"high-quality":[112],"caption.":[114],"Further,":[115],"align":[117],"generated":[119],"caption":[120],"with":[121,132,145],"content":[124,151],"meme,":[127],"LLM":[131],"instructions":[133],"meme":[140,154],"then":[142],"prepend":[143],"it":[144],"attributes":[147],"prompt-based":[157],"LM":[158],"prediction.":[160],"Experimental":[161],"findings":[162],"two":[164],"benchmark":[165],"datasets":[166],"show":[167],"that":[168],"our":[169],"produces":[171],"outperforms":[175],"state-of-the-art":[176],"methods":[177],"detecting":[179],"harmful":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}