{"id":"https://openalex.org/W4414360005","doi":"https://doi.org/10.24963/ijcai.2025/228","title":"Few-Shot Incremental Multi-modal Learning via Touch Guidance and Imaginary Vision Synthesis","display_name":"Few-Shot Incremental Multi-modal Learning via Touch Guidance and Imaginary Vision Synthesis","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360005","doi":"https://doi.org/10.24963/ijcai.2025/228"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/228","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5102380578","display_name":"Lina Wei","orcid":"https://orcid.org/0000-0002-6994-1170"},"institutions":[{"id":"https://openalex.org/I4210096345","display_name":"City University","ror":"https://ror.org/00r1j9q42","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210096345"]},{"id":"https://openalex.org/I4210114441","display_name":"Zhejiang Provincial Public Security Department","ror":"https://ror.org/01z3tch16","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210114441"]},{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]}],"countries":["BD","CN"],"is_corresponding":true,"raw_author_name":"Lina Wei","raw_affiliation_strings":["Hangzhou City University","Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou City University","institution_ids":["https://openalex.org/I4210096345","https://openalex.org/I4400573310"]},{"raw_affiliation_string":"Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security","institution_ids":["https://openalex.org/I4210114441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054182752","display_name":"Yan Ma","orcid":"https://orcid.org/0000-0003-4626-1401"},"institutions":[{"id":"https://openalex.org/I4210096345","display_name":"City University","ror":"https://ror.org/00r1j9q42","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210096345"]},{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Yuhang Ma","raw_affiliation_strings":["Hangzhou City University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou City University","institution_ids":["https://openalex.org/I4210096345","https://openalex.org/I4400573310"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109455252","display_name":"Zhongsheng Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096345","display_name":"City University","ror":"https://ror.org/00r1j9q42","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210096345"]},{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Zhongsheng Lin","raw_affiliation_strings":["Hangzhou City University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou City University","institution_ids":["https://openalex.org/I4210096345","https://openalex.org/I4400573310"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391379","display_name":"Fangfang Wang","orcid":"https://orcid.org/0000-0002-5441-4490"},"institutions":[{"id":"https://openalex.org/I163151501","display_name":"Hangzhou Normal University","ror":"https://ror.org/014v1mr15","country_code":"CN","type":"education","lineage":["https://openalex.org/I163151501"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangfang Wang","raw_affiliation_strings":["Hangzhou Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Normal University","institution_ids":["https://openalex.org/I163151501"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037349726","display_name":"Canghong Jin","orcid":"https://orcid.org/0000-0002-9774-9688"},"institutions":[{"id":"https://openalex.org/I4210096345","display_name":"City University","ror":"https://ror.org/00r1j9q42","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210096345"]},{"id":"https://openalex.org/I4210114441","display_name":"Zhejiang Provincial Public Security Department","ror":"https://ror.org/01z3tch16","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210114441"]},{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]}],"countries":["BD","CN"],"is_corresponding":false,"raw_author_name":"Canghong Jin","raw_affiliation_strings":["Hangzhou City University","Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou City University","institution_ids":["https://openalex.org/I4210096345","https://openalex.org/I4400573310"]},{"raw_affiliation_string":"Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security","institution_ids":["https://openalex.org/I4210114441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007599551","display_name":"Hanbin Zhao","orcid":"https://orcid.org/0000-0001-8906-4534"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanbin Zhao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100723407","display_name":"Dapeng Chen","orcid":"https://orcid.org/0000-0002-1930-419X"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Chen","raw_affiliation_strings":["Nanjing University of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology","institution_ids":["https://openalex.org/I200845125"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102380578"],"corresponding_institution_ids":["https://openalex.org/I4210096345","https://openalex.org/I4210114441","https://openalex.org/I4400573310"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21814177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2045","last_page":"2053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9789000153541565,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9613000154495239,"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/forgetting","display_name":"Forgetting","score":0.6978999972343445},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5296000242233276},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"Incremental learning","score":0.510200023651123},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4578000009059906},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4366999864578247},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.42340001463890076},{"id":"https://openalex.org/keywords/mirroring","display_name":"Mirroring","score":0.42179998755455017},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4154999852180481}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.6978999972343445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6917999982833862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6273000240325928},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5296000242233276},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.510200023651123},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4366999864578247},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4174000024795532},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3174999952316284},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C200220432","wikidata":"https://www.wikidata.org/wiki/Q7936208","display_name":"Vision science","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/228","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"perception,":[1],"which":[2],"integrates":[3,83],"vision":[4,74,86,103],"and":[5,18,34,66,82,85,126,142,144,157],"touch,":[6],"is":[7,169],"increasingly":[8],"demonstrating":[9],"its":[10],"significance":[11],"in":[12,22,47,161],"domains":[13],"such":[14],"as":[15],"embodied":[16],"intelligence":[17],"human-computer":[19],"interaction.":[20],"However,":[21],"open-world":[23],"scenarios,":[24],"multimodal":[25],"data":[26],"streams":[27],"face":[28],"significant":[29],"challenges,":[30],"including":[31,122],"catastrophic":[32,131],"forgetting":[33,132],"overfitting,":[35],"during":[36,133],"few-shot":[37,114,163],"class":[38],"incremental":[39,164],"learning":[40,108,120,155,165],"(FSCIL),":[41],"leading":[42],"to":[43,77,88,109,129],"a":[44,55,98],"severe":[45],"degradation":[46],"model":[48],"performance.":[49],"In":[50],"this":[51],"work,":[52],"we":[53,96,117],"propose":[54],"novel":[56],"approach":[57],"named":[58],"Few-Shot":[59],"Incremental":[60],"Multi-modal":[61],"Learning":[62],"via":[63],"Touch":[64,141],"Guidance":[65],"Imaginary":[67],"Vision":[68],"Synthesis":[69],"(TIFS).":[70],"Our":[71,167],"method":[72],"leverages":[73],"imagination":[75],"synthesis":[76],"enhance":[78],"the":[79,90,111,140,149],"semantic":[80],"understanding":[81],"touch":[84],"fusion":[87],"improve":[89],"problem":[91],"of":[92,113],"modal":[93],"imbalance.":[94],"Specifically,":[95],"introduce":[97],"framework":[99,151],"that":[100,148],"employs":[101],"touch-guided":[102],"information":[104],"for":[105],"cross-modal":[106],"contrastive":[107],"address":[110],"challenges":[112],"learning.":[115,136],"Additionally,":[116],"incorporate":[118],"multiple":[119],"mechanisms,":[121,125,128],"regularization,":[123],"memory":[124],"attention":[127],"mitigate":[130],"multi-incremental":[134],"step":[135],"Experimental":[137],"results":[138],"on":[139],"Go":[143],"VisGel":[145],"datasets":[146],"demonstrate":[147],"TIFS":[150],"exhibits":[152],"robust":[153],"continuous":[154],"capabilities":[156],"strong":[158],"generalization":[159],"performance":[160],"touch-vision":[162],"tasks.":[166],"code":[168],"available":[170],"at":[171],"https://github.com/Vision-Multimodal-Lab-HZCU/TIFS.":[172]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
