{"id":"https://openalex.org/W4401307166","doi":"https://doi.org/10.1145/3664647.3681677","title":"Leveraging Weak Cross-Modal Guidance for Coherence Modelling via Iterative Learning","display_name":"Leveraging Weak Cross-Modal Guidance for Coherence Modelling via Iterative Learning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4401307166","doi":"https://doi.org/10.1145/3664647.3681677"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681677","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.00305","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Yi Bin","raw_affiliation_strings":["Tongji University & National University of Singapore, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9714-8738","affiliations":[{"raw_affiliation_string":"Tongji University & National University of Singapore, Shanghai, China","institution_ids":["https://openalex.org/I116953780","https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051272861","display_name":"Junrong Liao","orcid":"https://orcid.org/0009-0006-9180-1867"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junrong Liao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0006-9180-1867","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091807843","display_name":"Yujuan Ding","orcid":"https://orcid.org/0000-0003-2945-1107"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yujuan Ding","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong SAR, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-2945-1107","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong SAR, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100629473","display_name":"Haoxuan Li","orcid":"https://orcid.org/0009-0005-1355-6256"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"HaoXuan Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0005-1355-6256","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5070-4511","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090171111","display_name":"See-Kiong Ng","orcid":"https://orcid.org/0000-0001-6565-7511"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"See-Kiong Ng","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6565-7511","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Tongji University & University of Electronic Science and Technology of China, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Tongji University & University of Electronic Science and Technology of China, Shanghai, China","institution_ids":["https://openalex.org/I116953780","https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4630","last_page":"4639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9957000017166138,"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":0.9957000017166138,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9567999839782715,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9458000063896179,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7805478572845459},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7698819041252136},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6751821637153625},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6411860585212708},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5798277258872986},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.46634265780448914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4472987949848175},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.44417884945869446},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.41522231698036194},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.41491204500198364},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4053427577018738},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0741477906703949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805478572845459},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7698819041252136},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6751821637153625},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6411860585212708},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5798277258872986},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.46634265780448914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4472987949848175},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44417884945869446},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.41522231698036194},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41491204500198364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4053427577018738},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0741477906703949},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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":2,"locations":[{"id":"doi:10.1145/3664647.3681677","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.00305","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.00305","pdf_url":"https://arxiv.org/pdf/2408.00305","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.00305","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.00305","pdf_url":"https://arxiv.org/pdf/2408.00305","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1294623083","display_name":null,"funder_award_id":"62220106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6574276969","display_name":null,"funder_award_id":"I21001E0002","funder_id":"https://openalex.org/F4320307791","funder_display_name":"Cisco Systems"},{"id":"https://openalex.org/G700280992","display_name":null,"funder_award_id":"I21001E0002","funder_id":"https://openalex.org/F4320320698","funder_display_name":"National University of Singapore"},{"id":"https://openalex.org/G8836073055","display_name":null,"funder_award_id":"62102070","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401307166.pdf","grobid_xml":"https://content.openalex.org/works/W4401307166.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W262945579","https://openalex.org/W1503071992","https://openalex.org/W1607035479","https://openalex.org/W1933349210","https://openalex.org/W2140676672","https://openalex.org/W2736142580","https://openalex.org/W2759083144","https://openalex.org/W2776762669","https://openalex.org/W2899197626","https://openalex.org/W2970880694","https://openalex.org/W2990408345","https://openalex.org/W2996876695","https://openalex.org/W2998259434","https://openalex.org/W2998303222","https://openalex.org/W3021868432","https://openalex.org/W3087871082","https://openalex.org/W3098817461","https://openalex.org/W3128339783","https://openalex.org/W3134272453","https://openalex.org/W3176313262","https://openalex.org/W3176616156","https://openalex.org/W3206675006","https://openalex.org/W3206723373","https://openalex.org/W3209229003","https://openalex.org/W3214184275","https://openalex.org/W4281930370","https://openalex.org/W4294653840","https://openalex.org/W4295036294","https://openalex.org/W4304099166","https://openalex.org/W4313855701","https://openalex.org/W4379984087","https://openalex.org/W4380479516","https://openalex.org/W4381804476","https://openalex.org/W4385570540","https://openalex.org/W4385895960","https://openalex.org/W4385934203","https://openalex.org/W4386076265","https://openalex.org/W4386076681","https://openalex.org/W4387967944","https://openalex.org/W4387967980","https://openalex.org/W4389520011","https://openalex.org/W4389520163","https://openalex.org/W4391494845","https://openalex.org/W4393158799","https://openalex.org/W7000408738"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Cross-modal":[0],"coherence":[1,31,45,123,138,160,182],"modeling":[2,32,124,139,183],"is":[3,59,131],"essential":[4],"for":[5,180],"intelligent":[6],"systems":[7],"to":[8,34,42,67,74,86,120,134,157],"help":[9],"them":[10],"organize":[11],"and":[12,17,63,97],"structure":[13],"information,":[14],"thereby":[15],"understanding":[16],"creating":[18],"content":[19],"of":[20,47,52,89],"the":[21,36,44,48,53,70,99,122,137,174],"physical":[22],"world":[23],"coherently":[24],"like":[25],"human-beings.":[26],"Previous":[27],"work":[28],"on":[29,95,167],"cross-modal":[30,71,90,151,181],"attempted":[33],"leverage":[35],"order":[37,113],"information":[38,58,119],"from":[39,146],"another":[40],"modality":[41,116],"assist":[43],"recovering":[46],"target":[49],"modality.":[50,164],"Despite":[51],"effectiveness,":[54],"labeled":[55],"associated":[56],"coherency":[57],"not":[60],"always":[61],"available":[62,197],"might":[64],"be":[65],"costly":[66],"acquire,":[68],"making":[69],"guidance":[72,91,145],"hard":[73],"leverage.":[75],"To":[76],"tackle":[77],"this":[78,80],"challenge,":[79],"paper":[81],"explores":[82],"a":[83],"new":[84],"way":[85],"take":[87],"advantage":[88],"without":[92],"gold":[93],"labels":[94],"coherency,":[96],"proposes":[98],"Weak":[100],"Cross-Modal":[101],"Guided":[102],"Ordering":[103],"(WeGO)":[104],"model.":[105],"More":[106],"specifically,":[107],"it":[108],"leverages":[109],"high-confidence":[110],"predicted":[111],"pairwise":[112],"in":[114,125,140,155,162],"one":[115],"as":[117],"reference":[118],"guide":[121],"another.":[126],"An":[127],"iterative":[128,150],"learning":[129],"paradigm":[130],"further":[132,158],"designed":[133],"jointly":[135],"optimize":[136],"two":[141,168],"modalities":[142],"with":[143],"selected":[144],"each":[147,163],"other.":[148],"The":[149],"boosting":[152],"also":[153],"functions":[154],"inference":[156],"enhance":[159],"prediction":[161],"Experimental":[165],"results":[166],"public":[169],"datasets":[170],"have":[171,188],"demonstrated":[172],"that":[173],"proposed":[175],"method":[176],"outperforms":[177],"existing":[178],"methods":[179],"tasks.":[184],"Major":[185],"technical":[186],"modules":[187],"been":[189],"evaluated":[190],"effective":[191],"through":[192],"ablation":[193],"studies.":[194],"Codes":[195],"are":[196],"at:":[198],"\\url{https://github.com/scvready123/IterWeGO}.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}