{"id":"https://openalex.org/W2808413133","doi":"https://doi.org/10.24963/ijcai.2018/577","title":"Multi-modal Sentence Summarization with Modality Attention and Image Filtering","display_name":"Multi-modal Sentence Summarization with Modality Attention and Image Filtering","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2808413133","doi":"https://doi.org/10.24963/ijcai.2018/577","mag":"2808413133"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/577","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/577","pdf_url":"https://www.ijcai.org/proceedings/2018/0577.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0577.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100327720","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0002-2368-7541"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoran Li","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015809194","display_name":"Junnan Zhu","orcid":"https://orcid.org/0000-0002-9856-2946"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junnan Zhu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060038422","display_name":"Tianshang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshang Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319572","display_name":"Jiajun Zhang","orcid":"https://orcid.org/0000-0001-5293-7434"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Zhang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015785439","display_name":"Chengqing Zong","orcid":"https://orcid.org/0000-0002-9864-3818"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengqing Zong","raw_affiliation_strings":["CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China","National Laboratory of Pattern Recognition, CASIA, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100327720"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":3.1874,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.94208487,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4152","last_page":"4158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9661319255828857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8358989357948303},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7940242886543274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6237504482269287},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6217183470726013},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5778068900108337},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5543352365493774},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5432882905006409},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5280020236968994},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5026454925537109},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47211921215057373},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4568858742713928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34837836027145386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33040136098861694}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9661319255828857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8358989357948303},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7940242886543274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237504482269287},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6217183470726013},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5778068900108337},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5543352365493774},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5432882905006409},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5280020236968994},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5026454925537109},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47211921215057373},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4568858742713928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34837836027145386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33040136098861694},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/577","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/577","pdf_url":"https://www.ijcai.org/proceedings/2018/0577.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/577","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/577","pdf_url":"https://www.ijcai.org/proceedings/2018/0577.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2204133011","display_name":null,"funder_award_id":"61333018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2808413133.pdf","grobid_xml":"https://content.openalex.org/works/W2808413133.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1483155202","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1895577753","https://openalex.org/W1924770834","https://openalex.org/W2095705004","https://openalex.org/W2115322217","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2250676463","https://openalex.org/W2290013849","https://openalex.org/W2467173223","https://openalex.org/W2561360547","https://openalex.org/W2567525733","https://openalex.org/W2581101319","https://openalex.org/W2593341061","https://openalex.org/W2606974598","https://openalex.org/W2609482285","https://openalex.org/W2759570332","https://openalex.org/W2962944953","https://openalex.org/W2962965405","https://openalex.org/W2962974924","https://openalex.org/W2963407669","https://openalex.org/W2963898017","https://openalex.org/W2963929190","https://openalex.org/W2964121744","https://openalex.org/W2964165364","https://openalex.org/W2998704965","https://openalex.org/W3010232603","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W2973759123","https://openalex.org/W627697492"],"abstract_inverted_index":{"In":[0],"this":[1,53,100],"paper,":[2],"we":[3,55,72],"introduce":[4],"a":[5,12,16,57,91,130],"multi-modal":[6],"sentence":[7,19,28,93,120],"summarization":[8,42,94,121],"task":[9,23,122],"that":[10,103,119],"produces":[11],"short":[13],"summary":[14],"from":[15,125,129],"pair":[17],"of":[18,50,85,132],"and":[20,68,71,96],"image.":[21,51],"This":[22],"is":[24],"more":[25],"challenging":[26],"than":[27],"summarization.":[29],"It":[30],"not":[31],"only":[32,111],"needs":[33],"to":[34,47,61,65,76,81],"effectively":[35],"incorporate":[36],"visual":[37,79],"features":[38],"into":[39],"standard":[40],"text":[41,69,113],"framework,":[43],"but":[44],"also":[45],"requires":[46],"avoid":[48],"noise":[49],"To":[52],"end,":[54],"propose":[56],"modality-based":[58],"attention":[59,64],"mechanism":[60],"pay":[62],"different":[63],"image":[66,74],"patches":[67],"units,":[70],"design":[73],"filters":[75],"selectively":[77],"use":[78],"information":[80],"enhance":[82],"the":[83,86],"semantics":[84],"input":[87],"sentence.":[88],"We":[89],"construct":[90],"multimodal":[92],"dataset":[95,101],"extensive":[97],"experiments":[98],"on":[99],"demonstrate":[102],"our":[104],"models":[105,109],"significantly":[106],"outperform":[107],"conventional":[108],"which":[110],"employ":[112],"as":[114],"input.":[115],"Further":[116],"analyses":[117],"suggest":[118],"can":[123],"benefit":[124],"visually":[126],"grounded":[127],"representations":[128],"variety":[131],"aspects.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}