{"id":"https://openalex.org/W4403780574","doi":"https://doi.org/10.1145/3664647.3681698","title":"MaskMentor: Unlocking the Potential of Masked Self-Teaching for Missing Modality RGB-D Semantic Segmentation","display_name":"MaskMentor: Unlocking the Potential of Masked Self-Teaching for Missing Modality RGB-D Semantic Segmentation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780574","doi":"https://doi.org/10.1145/3664647.3681698"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681698","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681698","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":"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":null,"display_name":"Zhida Zhao","orcid":"https://orcid.org/0009-0003-0773-5106"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhida Zhao","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0003-0773-5106","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jia Li","orcid":"https://orcid.org/0009-0007-5365-8198"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0007-5365-8198","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318892","display_name":"Lijun Wang","orcid":"https://orcid.org/0000-0003-2538-8358"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Wang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-2538-8358","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398548","display_name":"Yifan Wang","orcid":"https://orcid.org/0000-0002-1911-2526"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Wang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-1911-2526","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huchuan Lu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6668-9758","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.2629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56445033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1915","last_page":"1923"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9955000281333923,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9955000281333923,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9908999800682068,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7695752382278442},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6894391775131226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6212115287780762},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6045026779174805},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5755907893180847},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.48670676350593567},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44062793254852295},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4006330370903015}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7695752382278442},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894391775131226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6212115287780762},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6045026779174805},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5755907893180847},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.48670676350593567},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44062793254852295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4006330370903015}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681698","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681698","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1923184257","https://openalex.org/W2619383789","https://openalex.org/W2910281775","https://openalex.org/W2956887593","https://openalex.org/W2964111476","https://openalex.org/W2981325811","https://openalex.org/W2982157312","https://openalex.org/W2987861506","https://openalex.org/W2997006708","https://openalex.org/W3015871565","https://openalex.org/W3093327960","https://openalex.org/W3099155473","https://openalex.org/W3100676321","https://openalex.org/W3124434019","https://openalex.org/W3159481202","https://openalex.org/W3185613252","https://openalex.org/W3194841206","https://openalex.org/W4214893857","https://openalex.org/W4220849367","https://openalex.org/W4296544717","https://openalex.org/W4312336798","https://openalex.org/W4312443924","https://openalex.org/W4312815172","https://openalex.org/W4313142416","https://openalex.org/W4313164293","https://openalex.org/W4386057714","https://openalex.org/W4386065698","https://openalex.org/W4386071687","https://openalex.org/W4386075687","https://openalex.org/W4386076522","https://openalex.org/W4386179772","https://openalex.org/W4390874213","https://openalex.org/W6784910987"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W2793967660","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Existing":[0],"RGB-D":[1],"semantic":[2],"segmentation":[3,23],"methods":[4,150],"struggle":[5],"to":[6,21],"handle":[7],"modality":[8,36,62,100,110],"missing":[9,37,63,101,123],"input,":[10],"where":[11,80],"only":[12],"RGB":[13],"images":[14],"or":[15],"depth":[16],"maps":[17],"are":[18],"available,":[19],"leading":[20],"degenerated":[22],"performance.":[24],"We":[25],"tackle":[26],"this":[27],"issue":[28],"using":[29],"MaskMentor,":[30],"a":[31,85,156],"new":[32],"pre-training":[33],"framework":[34],"for":[35],"segmentation,":[38],"which":[39],"advances":[40],"its":[41],"counterparts":[42],"via":[43,55],"two":[44,152],"novel":[45],"designs:":[46],"Masked":[47],"Modality":[48],"and":[49,53,69,94,115,124,131,147],"Image":[50],"Modeling":[51],"(M2IM),":[52],"Self-Teaching":[54],"Token-Pixel":[56],"Joint":[57],"reconstruction":[58],"(STTP).":[59],"M2IM":[60,130],"simulates":[61],"scenarios":[64],"by":[65,105,155],"combining":[66],"both":[67,91,113],"modality-":[68],"patch-level":[70],"random":[71],"masking.":[72],"Meanwhile,":[73],"STTP":[74],"offers":[75],"an":[76],"effective":[77],"self-teaching":[78],"strategy,":[79],"the":[81,92,95,106,120,136,140,164,167],"trained":[82,141],"network":[83],"assumes":[84],"dual":[86],"role,":[87],"simultaneously":[88],"acting":[89],"as":[90],"teacher":[93,107],"student.":[96],"The":[97],"student":[98],"with":[99,108],"input":[102,111,126,145],"is":[103],"supervised":[104],"complete":[109,125],"through":[112],"token-":[114],"pixel-wise":[116],"masked":[117],"modeling,":[118],"closing":[119],"gap":[121],"between":[122],"modalities.":[127],"By":[128],"integrating":[129],"STTP,":[132],"MaskMentor":[133],"significantly":[134],"improves":[135],"generalization":[137],"ability":[138],"of":[139,166],"model":[142],"across":[143],"diverse":[144],"conditions":[146],"outperforms":[148],"state-of-the-art":[149],"on":[151],"popular":[153],"benchmarks":[154],"considerable":[157],"margin.":[158],"Extensive":[159],"ablation":[160],"studies":[161],"further":[162],"verify":[163],"effectiveness":[165],"above":[168],"contributions.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}