{"id":"https://openalex.org/W4415538092","doi":"https://doi.org/10.1145/3746027.3755750","title":"Spatial-Aware Multi-Modal Information Fusion for Food Nutrition Estimation","display_name":"Spatial-Aware Multi-Modal Information Fusion for Food Nutrition Estimation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538092","doi":"https://doi.org/10.1145/3746027.3755750"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5070288031","display_name":"Dongjian Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongjian Yu","raw_affiliation_strings":["School of Software, Yunnan University, Kunming, Yunnan, China"],"raw_orcid":"https://orcid.org/0009-0003-0865-0489","affiliations":[{"raw_affiliation_string":"School of Software, Yunnan University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039322394","display_name":"Weiqing Min","orcid":"https://orcid.org/0000-0001-6668-9208"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqing Min","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6668-9208","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641350","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0003-2211-2006"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["School of Software, Yunnan university, Kunming, Yunnan University, China"],"raw_orcid":"https://orcid.org/0000-0003-2211-2006","affiliations":[{"raw_affiliation_string":"School of Software, Yunnan university, Kunming, Yunnan University, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039717115","display_name":"Qian Jiang","orcid":"https://orcid.org/0000-0003-3097-0721"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Jiang","raw_affiliation_strings":["School of Software, Yunnan University, Kunming, Yunnan, China"],"raw_orcid":"https://orcid.org/0000-0003-3097-0721","affiliations":[{"raw_affiliation_string":"School of Software, Yunnan University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085719285","display_name":"Shuqiang Jiang","orcid":"https://orcid.org/0000-0002-1596-4326"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqiang Jiang","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1596-4326","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8863","last_page":"8871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10866","display_name":"Nutritional Studies and Diet","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10866","display_name":"Nutritional Studies and Diet","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.9696000218391418,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12697","display_name":"Water Quality Monitoring Technologies","score":0.9176999926567078,"subfield":{"id":"https://openalex.org/subfields/2312","display_name":"Water Science and Technology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7439000010490417},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5899999737739563},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5231000185012817},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4489000141620636},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4424000084400177},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.435699999332428},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.3801000118255615}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7439000010490417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711899995803833},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5612999796867371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5514000058174133},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5231000185012817},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42160001397132874},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3801000118255615},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3614134685","display_name":null,"funder_award_id":"62261060, 62125207","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2157727960","https://openalex.org/W2972610293","https://openalex.org/W3025983928","https://openalex.org/W3046206337","https://openalex.org/W3049555908","https://openalex.org/W3138516171","https://openalex.org/W3170706004","https://openalex.org/W4213423729","https://openalex.org/W4214755140","https://openalex.org/W4291433229","https://openalex.org/W4295832202","https://openalex.org/W4309721374","https://openalex.org/W4312443924","https://openalex.org/W4376870287","https://openalex.org/W4379467021","https://openalex.org/W4386179772","https://openalex.org/W4386590722","https://openalex.org/W4389137852","https://openalex.org/W4390482913","https://openalex.org/W4403791449","https://openalex.org/W4406174872","https://openalex.org/W4407393173"],"related_works":[],"abstract_inverted_index":{"Food":[0],"nutrition":[1,19,224],"assessment":[2,20],"plays":[3],"a":[4,95,130,167],"crucial":[5],"role":[6],"in":[7,223],"maintaining":[8],"health,":[9],"preventing":[10],"diseases,":[11],"and":[12,69,73,77,109,128,140,173,190],"promoting":[13],"scientific":[14],"dietary":[15],"habits.":[16],"However,":[17],"existing":[18],"methods":[21,38],"often":[22],"fail":[23],"to":[24,32,55,66,114,153,182],"fully":[25,141,183],"consider":[26],"the":[27,75,84,122,126,150,180,185,192,205,227],"relationships":[28],"between":[29,101],"tasks,":[30,64,102,108,159],"leading":[31,54,65],"limited":[33],"overall":[34,57,161],"performance.":[35,163],"Specifically,":[36],"these":[37,91],"suffer":[39],"from":[40,125],"three":[41],"major":[42],"challenges:":[43],"(1)":[44],"task":[45,138],"conflicts,":[46],"where":[47],"different":[48],"tasks":[49],"compete":[50],"during":[51],"joint":[52],"optimization,":[53],"suboptimal":[56],"performance;":[58],"(2)":[59],"varying":[60],"training":[61],"difficulties":[62],"among":[63],"imbalanced":[67],"learning":[68,145],"subpar":[70],"model":[71,162,181],"generalization;":[72],"(3)":[74],"small-scale":[76],"complex":[78],"distribution":[79],"of":[80,86,188,229],"datasets,":[81],"which":[82],"limits":[83],"robustness":[85],"learned":[87],"representations.":[88],"To":[89],"address":[90],"issues,":[92],"we":[93,120,148,165],"propose":[94],"novel":[96],"method":[97,200,219],"that":[98,217],"reduces":[99],"interference":[100,139],"dynamically":[103],"focuses":[104],"on":[105,156,204],"more":[106,157],"challenging":[107,158],"incorporates":[110],"3D":[111],"spatial":[112,186],"awareness":[113],"enhance":[115,191],"multi-modal":[116,194],"feature":[117,195],"representation.":[118,196],"First,":[119],"decouple":[121],"prediction":[123],"network":[124],"backbone":[127],"introduce":[129],"CAMTH":[131],"(Cross-Attention-Based":[132],"Multi-Task":[133],"Head":[134],"Module),":[135,178],"effectively":[136],"mitigating":[137],"leveraging":[142],"each":[143],"task's":[144],"potential.":[146],"Second,":[147],"improve":[149],"loss":[151],"function":[152],"adaptively":[154],"focus":[155],"improving":[160],"Third,":[164],"design":[166],"3D-FEM":[168],"(3D":[169],"Feature":[170,176],"Extraction":[171],"Module)":[172],"MMFF":[174],"(Multi-Modal":[175],"Fusion":[177],"enabling":[179],"exploit":[184],"information":[187],"food":[189],"food's":[193],"We":[197],"validate":[198],"our":[199,218,230],"through":[201],"extensive":[202],"experiments":[203],"Nutrition5K":[206],"dataset,":[207],"comparing":[208],"it":[209],"with":[210],"state-of-the-art":[211],"(SOTA)":[212],"models.":[213],"The":[214],"results":[215],"show":[216],"achieves":[220],"superior":[221],"performance":[222],"estimation,":[225],"demonstrating":[226],"effectiveness":[228],"method.":[231]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}