{"id":"https://openalex.org/W4392903163","doi":"https://doi.org/10.1109/icassp48485.2024.10448385","title":"Exploiting Modality-Specific Features for Multi-Modal Manipulation Detection and Grounding","display_name":"Exploiting Modality-Specific Features for Multi-Modal Manipulation Detection and Grounding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903163","doi":"https://doi.org/10.1109/icassp48485.2024.10448385"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103275853","display_name":"Jiazhen Wang","orcid":"https://orcid.org/0000-0003-3226-349X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazhen Wang","raw_affiliation_strings":["University of Science and Technology of China,School of Cyber Science and Technology","School of Cyber Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Cyber Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395493","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0002-3977-8800"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["University of Science and Technology of China,School of Cyber Science and Technology","School of Cyber Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Cyber Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077867418","display_name":"Changtao Miao","orcid":"https://orcid.org/0000-0002-7634-9992"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changtao Miao","raw_affiliation_strings":["University of Science and Technology of China,School of Cyber Science and Technology","School of Cyber Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Cyber Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101816996","display_name":"Zhiwei Zhao","orcid":"https://orcid.org/0000-0003-1850-3098"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Zhao","raw_affiliation_strings":["University of Science and Technology of China,School of Cyber Science and Technology","School of Cyber Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Cyber Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088627439","display_name":"Wanyi Zhuang","orcid":"https://orcid.org/0000-0001-9305-1189"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanyi Zhuang","raw_affiliation_strings":["University of Science and Technology of China,School of Cyber Science and Technology","School of Cyber Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Cyber Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045938154","display_name":"Qi Chu","orcid":"https://orcid.org/0000-0003-3028-0755"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chu","raw_affiliation_strings":["University of Science and Technology of China,School of Cyber Science and Technology","School of Cyber Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Cyber Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064573190","display_name":"Nenghai Yu","orcid":"https://orcid.org/0000-0003-4417-9316"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenghai Yu","raw_affiliation_strings":["University of Science and Technology of China,School of Cyber Science and Technology","School of Cyber Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Cyber Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.6294,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.9238704,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4935","last_page":"4939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9914000034332275,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9588000178337097,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8136712312698364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7783371806144714},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6536560654640198},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5407180786132812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5398615598678589},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49747565388679504},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.423062264919281},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3559170067310333},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32489752769470215},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.086841881275177}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8136712312698364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783371806144714},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6536560654640198},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5407180786132812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5398615598678589},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49747565388679504},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.423062264919281},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3559170067310333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32489752769470215},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.086841881275177},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"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:10.1109/icassp48485.2024.10448385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/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":26,"referenced_works":["https://openalex.org/W2908510526","https://openalex.org/W2951080837","https://openalex.org/W2962766617","https://openalex.org/W3096609285","https://openalex.org/W3207353304","https://openalex.org/W3213165621","https://openalex.org/W4206742848","https://openalex.org/W4224925583","https://openalex.org/W4285044753","https://openalex.org/W4287758545","https://openalex.org/W4290994941","https://openalex.org/W4299567010","https://openalex.org/W4312732149","https://openalex.org/W4312784228","https://openalex.org/W4312967678","https://openalex.org/W4375869278","https://openalex.org/W4382239959","https://openalex.org/W4386071472","https://openalex.org/W6757817989","https://openalex.org/W6763240421","https://openalex.org/W6784810453","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6798837711","https://openalex.org/W6803621926","https://openalex.org/W6809497388"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W4390516098","https://openalex.org/W2374013449","https://openalex.org/W2181948922","https://openalex.org/W73545470","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W2364381299","https://openalex.org/W627697492"],"abstract_inverted_index":{"AI-synthesized":[0],"text":[1],"and":[2,35,64,72,96,102,118],"images":[3],"have":[4],"gained":[5],"significant":[6],"attention,":[7],"particularly":[8],"due":[9],"to":[10,43,54,100,113,163],"the":[11,18,48,83,144,152,155],"widespread":[12],"dissemination":[13],"of":[14,50,146,158],"multi-modal":[15,32,69,86],"manipulations":[16],"on":[17,27,39,151],"internet,":[19],"which":[20],"has":[21],"resulted":[22],"in":[23],"numerous":[24],"negative":[25],"impacts":[26],"society.":[28],"Existing":[29],"methods":[30],"for":[31,68,85],"manipulation":[33,70,127],"detection":[34,71],"grounding":[36,73],"primarily":[37],"focus":[38],"fusing":[40],"vision-language":[41],"features":[42,80],"make":[44],"predictions,":[45],"while":[46,81],"overlooking":[47],"importance":[49],"modality-specific":[51,79,115],"features,":[52],"leading":[53],"sub-optimal":[55],"results.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,91,107,123],"construct":[61],"a":[62],"simple":[63],"novel":[65],"transformer-based":[66],"framework":[67,76],"tasks.":[74],"Our":[75],"simultaneously":[77],"explores":[78],"preserving":[82],"capability":[84],"alignment.":[87],"To":[88],"achieve":[89],"this,":[90],"introduce":[92],"visual/language":[93],"pre-trained":[94],"encoders":[95],"dual-branch":[97],"cross-attention":[98],"(DCA)":[99],"extract":[101],"fuse":[103],"modality-unique":[104],"features.":[105],"Furthermore,":[106],"design":[108],"decoupled":[109],"fine-grained":[110],"classifiers":[111],"(DFC)":[112],"enhance":[114],"feature":[116],"mining":[117],"mitigate":[119],"modality":[120,138],"competition.":[121],"Moreover,":[122],"propose":[124],"an":[125],"implicit":[126],"query":[128],"(IMQ)":[129],"that":[130],"adaptively":[131],"aggregates":[132],"global":[133],"contextual":[134],"cues":[135],"within":[136],"each":[137],"using":[139],"learnable":[140],"queries,":[141],"thereby":[142],"improving":[143],"discovery":[145],"forged":[147],"details.":[148],"Extensive":[149],"experiments":[150],"DGM4dataset":[153],"demonstrate":[154],"superior":[156],"performance":[157],"our":[159],"proposed":[160],"model":[161],"compared":[162],"state-of-the-art":[164],"approaches.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}