{"id":"https://openalex.org/W4304099166","doi":"https://doi.org/10.1145/3503161.3548184","title":"Non-Autoregressive Cross-Modal Coherence Modelling","display_name":"Non-Autoregressive Cross-Modal Coherence Modelling","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304099166","doi":"https://doi.org/10.1145/3503161.3548184"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548184","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548184","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"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":"Yi Bin","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"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/A5101916735","display_name":"Wenhao Shi","orcid":"https://orcid.org/0000-0001-5651-8608"},"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":"Wenhao Shi","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"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/A5100622779","display_name":"Jipeng Zhang","orcid":"https://orcid.org/0000-0002-3269-6992"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jipeng Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"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, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"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 & Institute of Electronic and Information Engineering of UESTC in Guangdong, Chengdu, Dongguan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China & Institute of Electronic and Information Engineering of UESTC in Guangdong, Chengdu, Dongguan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"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/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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China & Peng Cheng Laboratory, Chengdu, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China & Peng Cheng Laboratory, Chengdu, Shenzhen, China","institution_ids":["https://openalex.org/I150229711","https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3253","last_page":"3261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9144999980926514,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9144999980926514,"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/computer-science","display_name":"Computer science","score":0.7860522270202637},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7659522294998169},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7585026025772095},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6936444044113159},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6290258169174194},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.585839033126831},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5060507655143738},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.41824156045913696},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4118626117706299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3729167878627777},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37255626916885376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11439913511276245},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.0796053409576416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860522270202637},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7659522294998169},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7585026025772095},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6936444044113159},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6290258169174194},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.585839033126831},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5060507655143738},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41824156045913696},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4118626117706299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3729167878627777},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37255626916885376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11439913511276245},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0796053409576416},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548184","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548184","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-126480","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-126480","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G2450289543","display_name":null,"funder_award_id":"BX2021055,2021M690027","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G2529474818","display_name":null,"funder_award_id":"62102070,U20B2063","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"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W753847829","https://openalex.org/W1596841185","https://openalex.org/W1964073652","https://openalex.org/W2042452379","https://openalex.org/W2140676672","https://openalex.org/W2169546346","https://openalex.org/W2251356693","https://openalex.org/W2388114291","https://openalex.org/W2546190447","https://openalex.org/W2765440071","https://openalex.org/W2766237723","https://openalex.org/W2886300652","https://openalex.org/W2887712318","https://openalex.org/W2905032972","https://openalex.org/W2964972381","https://openalex.org/W2969362383","https://openalex.org/W2987869401","https://openalex.org/W2996876695","https://openalex.org/W2998259434","https://openalex.org/W3003735286","https://openalex.org/W3010705931","https://openalex.org/W3021868432","https://openalex.org/W3111984153","https://openalex.org/W3134272453","https://openalex.org/W3169472988","https://openalex.org/W3205604798","https://openalex.org/W3206675006","https://openalex.org/W4214931354","https://openalex.org/W4285602612","https://openalex.org/W6754000420","https://openalex.org/W6791103873"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W2150410159","https://openalex.org/W1972271943","https://openalex.org/W4306353150","https://openalex.org/W3150905897","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W2026860389","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"Modelling":[0],"the":[1,13,28,40,47,52,63,76,108,135,141,155,181,191,195],"coherence":[2,19,49,64],"of":[3,30,134,144,194],"information":[4,31,65,73],"is":[5,99,198],"important":[6],"for":[7],"human":[8],"to":[9,59,74,106,116,131,153,170],"perceive":[10],"and":[11,33,112,160,175,189],"prehend":[12],"physical":[14],"world.":[15],"Existing":[16],"works":[17],"on":[18,23,166],"modelling":[20],"mainly":[21],"focus":[22],"single":[24,67],"modality,":[25,68],"which":[26],"overlook":[27],"effect":[29],"integration":[32],"semantic":[34,77],"consistency":[35,78],"across":[36],"modalities.":[37,80],"To":[38,81,139],"fill":[39],"research":[41],"gap,":[42],"this":[43,82],"paper":[44],"targets":[45],"at":[46,200],"cross-modal":[48,53,72,125,136,187],"modelling,":[50],"specifically,":[51],"ordering":[54,156],"task.":[55],"The":[56],"task":[57],"requires":[58],"not":[60],"only":[61],"explore":[62],"in":[66,120,129],"but":[69],"also":[70],"leverage":[71,186],"model":[75,107],"between":[79,158],"end,":[83],"we":[84,147],"propose":[85],"a":[86,93,113,124],"Non-Autoregressive":[87],"Cross-modal":[88],"Ordering":[89],"Net":[90],"(NACON)":[91],"adopting":[92],"basic":[94],"encoder-decoder":[95],"architecture.":[96],"Specifically,":[97],"NACON":[98,130,183],"equipped":[100],"with":[101],"an":[102,149],"order-invariant":[103],"context":[104],"encoder":[105],"unordered":[109],"input":[110],"set":[111],"non-autoregressive":[114,145],"decoder":[115],"generate":[117],"ordered":[118],"sequences":[119],"parallel.":[121],"We":[122,162],"devise":[123],"positional":[126],"attention":[127],"module":[128],"take":[132],"advantage":[133],"order":[137,193],"guidance.":[138],"alleviate":[140],"repetition":[142],"problem":[143],"models,":[146],"introduce":[148],"elegant":[150],"exclusive":[151],"loss":[152],"constrain":[154],"exclusiveness":[157],"positions":[159],"elements.":[161],"conduct":[163],"extensive":[164],"experiments":[165],"two":[167],"assembled":[168],"datasets":[169],"support":[171],"our":[172],"task,":[173],"SIND":[174],"TACoS-Ordering.":[176],"Experimental":[177],"results":[178],"show":[179],"that":[180],"proposed":[182],"can":[184],"effectively":[185],"guidance":[188],"recover":[190],"correct":[192],"elements.The":[196],"code":[197],"available":[199],"https://github.com/YiBin-CHN/CMCM.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}