{"id":"https://openalex.org/W4403791997","doi":"https://doi.org/10.1145/3664647.3681012","title":"AutoGraph: Enabling Visual Context via Graph Alignment in Open Domain Multi-Modal Dialogue Generation","display_name":"AutoGraph: Enabling Visual Context via Graph Alignment in Open Domain Multi-Modal Dialogue Generation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791997","doi":"https://doi.org/10.1145/3664647.3681012"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681012","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":"article","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/A5028883563","display_name":"Deji Zhao","orcid":"https://orcid.org/0000-0002-8303-6943"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Deji Zhao","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102860580","display_name":"Donghong Han","orcid":"https://orcid.org/0000-0002-9056-1308"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghong Han","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014346487","display_name":"Ye Yuan","orcid":"https://orcid.org/0000-0002-0247-9866"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Yuan","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000941408","display_name":"Bo Ning","orcid":"https://orcid.org/0000-0001-9512-7036"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ning","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113713006","display_name":"M Li","orcid":"https://orcid.org/0009-0005-0521-7596"},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxiang Li","raw_affiliation_strings":["China Telecom Corp Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Telecom Corp Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101320954","display_name":"Zhongjiang He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjiang He","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom Corp Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom Corp Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087486098","display_name":"Shuangyong Song","orcid":"https://orcid.org/0000-0001-7465-1082"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuangyong Song","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom Corp Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom Corp Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5028883563"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.5248,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67053988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2079","last_page":"2088"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9994000196456909,"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/autograph","display_name":"Autograph","score":0.8231246471405029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7709587812423706},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6439847946166992},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5073060393333435},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47137558460235596},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4548426866531372},{"id":"https://openalex.org/keywords/open-domain","display_name":"Open domain","score":0.4169788658618927},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3840782344341278},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3653346300125122},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27599596977233887},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10067015886306763},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08282053470611572}],"concepts":[{"id":"https://openalex.org/C21639389","wikidata":"https://www.wikidata.org/wiki/Q2872572","display_name":"Autograph","level":2,"score":0.8231246471405029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709587812423706},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6439847946166992},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5073060393333435},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47137558460235596},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4548426866531372},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.4169788658618927},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3840782344341278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3653346300125122},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27599596977233887},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10067015886306763},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08282053470611572},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681012","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1933349210","https://openalex.org/W2250342921","https://openalex.org/W2945397504","https://openalex.org/W2963206148","https://openalex.org/W2963532001","https://openalex.org/W2963686995","https://openalex.org/W2963748384","https://openalex.org/W2981852735","https://openalex.org/W2985882473","https://openalex.org/W2998385486","https://openalex.org/W3015063797","https://openalex.org/W3015322406","https://openalex.org/W3114916066","https://openalex.org/W3137797626","https://openalex.org/W3173864402","https://openalex.org/W3205638321","https://openalex.org/W3206527789","https://openalex.org/W3207886649","https://openalex.org/W3207972321","https://openalex.org/W4205119860","https://openalex.org/W4212774754","https://openalex.org/W4224246420","https://openalex.org/W4226076738","https://openalex.org/W4288089799","https://openalex.org/W4384918448","https://openalex.org/W4385570522","https://openalex.org/W4385570649","https://openalex.org/W4385571451","https://openalex.org/W4385682256","https://openalex.org/W4385959364","https://openalex.org/W4389520684","https://openalex.org/W4393154896","https://openalex.org/W4400524696","https://openalex.org/W4402716330","https://openalex.org/W4402727018"],"related_works":["https://openalex.org/W2808171097","https://openalex.org/W2807839678","https://openalex.org/W2808268082","https://openalex.org/W4238483912","https://openalex.org/W2539940768","https://openalex.org/W2028065606","https://openalex.org/W2578140855","https://openalex.org/W4234387670","https://openalex.org/W3105313172","https://openalex.org/W2286186409"],"abstract_inverted_index":{"Open-domain":[0],"multi-modal":[1,17],"dialogue":[2],"system":[3],"heavily":[4],"relies":[5],"on":[6,146,163],"visual":[7,47,98],"information":[8,56,67],"to":[9,31,53,94,112,130,133],"generate":[10,139],"contextually":[11],"relevant":[12],"responses.":[13,140],"The":[14],"existing":[15],"open-domain":[16],"dialog":[18],"generation":[19],"methods":[20],"ignore":[21],"the":[22,81,109],"complementary":[23],"relationship":[24],"between":[25],"multiple":[26,69,164],"modalities,":[27],"and":[28,57,74,84,87,138,149],"are":[29],"difficult":[30],"integrate":[32,59],"with":[33,61],"LLMs.":[34,122],"To":[35],"tackle":[36],"these":[37],"challenges,":[38],"we":[39,78,102,124],"introduce":[40],"AutoGraph,":[41],"an":[42],"innovative":[43],"method":[44,145,159],"for":[45,108,121],"constructing":[46],"context":[48,99],"graphs":[49,83],"automatically.":[50],"We":[51,141],"aim":[52],"structure":[54],"complex":[55],"seamlessly":[58],"it":[60],"large":[62],"language":[63],"models":[64],"(LLMs),":[65],"aligning":[66],"from":[68],"modalities":[70],"at":[71],"both":[72],"semantic":[73],"structural":[75],"levels.":[76],"Specifically,":[77],"fully":[79],"connect":[80],"text":[82],"scene":[85],"graphs,":[86],"then":[88],"trim":[89],"unnecessary":[90],"edges":[91],"via":[92],"LLMs":[93,132],"automatically":[95],"construct":[96],"a":[97,126],"graph.":[100],"Next,":[101],"design":[103],"several":[104],"graph":[105,114,135],"sampling":[106,136],"grammar":[107,137],"first":[110],"time":[111],"convert":[113],"structures":[115],"into":[116],"sequence":[117],"which":[118],"is":[119],"suitable":[120],"Finally,":[123],"propose":[125],"two-stage":[127],"fine-tuning":[128],"strategy":[129],"allow":[131],"understand":[134],"validate":[142],"our":[143,157],"proposed":[144,158],"text-based":[147],"LLMs,":[148,151],"visual-based":[150],"respectively.":[152],"Experimental":[153],"results":[154],"show":[155],"that":[156],"achieves":[160],"state-of-the-art":[161],"performance":[162],"public":[165],"datasets.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}