{"id":"https://openalex.org/W4415137526","doi":"https://doi.org/10.1109/iccv51701.2025.02160","title":"HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model","display_name":"HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415137526","doi":"https://doi.org/10.1109/iccv51701.2025.02160"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.13026","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101494368","display_name":"Tao Wang","orcid":"https://orcid.org/0009-0006-4868-1484"},"institutions":[{"id":"https://openalex.org/I2801717407","display_name":"United Nations Human Settlements Programme","ror":"https://ror.org/020qt9g11","country_code":"KE","type":"other","lineage":["https://openalex.org/I1286959531","https://openalex.org/I2801717407"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["Uni-Ubi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uni-Ubi","institution_ids":["https://openalex.org/I2801717407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069902262","display_name":"Changxu Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I2801717407","display_name":"United Nations Human Settlements Programme","ror":"https://ror.org/020qt9g11","country_code":"KE","type":"other","lineage":["https://openalex.org/I1286959531","https://openalex.org/I2801717407"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Changxu Cheng","raw_affiliation_strings":["Uni-Ubi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uni-Ubi","institution_ids":["https://openalex.org/I2801717407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082011757","display_name":"Lingfeng Wang","orcid":null},"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":"Lingfeng Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Senda Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Senda Chen","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wuyue Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I2801717407","display_name":"United Nations Human Settlements Programme","ror":"https://ror.org/020qt9g11","country_code":"KE","type":"other","lineage":["https://openalex.org/I1286959531","https://openalex.org/I2801717407"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Wuyue Zhao","raw_affiliation_strings":["Uni-Ubi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uni-Ubi","institution_ids":["https://openalex.org/I2801717407"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30547939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23267","last_page":"23278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.847599983215332,"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":0.847599983215332,"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":0.8172000050544739,"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":0.8170999884605408,"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/segmentation","display_name":"Segmentation","score":0.8021000027656555},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.6083999872207642},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.5723000168800354},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5679000020027161},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4862000048160553},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4250999987125397},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41040000319480896},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3880000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077999949455261},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8021000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7831000089645386},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6401000022888184},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.6083999872207642},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.5723000168800354},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5679000020027161},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3880000114440918},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C42314347","wikidata":"https://www.wikidata.org/wiki/Q6865488","display_name":"Minimum spanning tree-based segmentation","level":5,"score":0.29679998755455017},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C120515352","wikidata":"https://www.wikidata.org/wiki/Q2564580","display_name":"Image plane","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.13026","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.13026","pdf_url":"https://arxiv.org/pdf/2503.13026","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.13026","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.13026","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.13026","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.13026","pdf_url":"https://arxiv.org/pdf/2503.13026","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"remarkable":[1],"performance":[2,176],"of":[3,70,122,134],"large":[4],"multimodal":[5],"models":[6],"(LMMs)":[7],"has":[8],"attracted":[9],"significant":[10],"interest":[11],"from":[12,60],"the":[13,20,50,68,77,93,96,113,119],"image":[14,52,98],"segmentation":[15,25,38,47,84,123,135,179],"community.":[16],"To":[17],"align":[18],"with":[19,86,112],"next-token-prediction":[21,115],"paradigm,":[22],"current":[23],"LMM-driven":[24],"methods":[26],"either":[27],"use":[28],"object":[29],"boundary":[30],"points":[31],"to":[32,88,162],"represent":[33],"masks":[34,85],"or":[35],"introduce":[36],"special":[37],"tokens,":[39],"whose":[40],"hidden":[41],"states":[42],"are":[43],"decoded":[44],"by":[45],"a":[46,127,140],"model":[48],"requiring":[49],"original":[51,97],"as":[53],"input.":[54],"However,":[55],"these":[56],"approaches":[57],"often":[58],"suffer":[59],"inadequate":[61],"mask":[62,100,108,142,160],"representation":[63],"and":[64,91,106,117,136,159,185],"complex":[65],"architectures,":[66],"limiting":[67],"potential":[69],"LMMs.":[71],"In":[72],"this":[73],"work,":[74],"we":[75,149],"propose":[76],"Hierarchical":[78],"Mask":[79],"Tokenizer":[80],"(HiMTok),":[81],"which":[82],"represents":[83],"up":[87],"32":[89],"tokens":[90,161],"eliminates":[92],"need":[94],"for":[95,104,131,144],"during":[99],"de-tokenization.":[101],"HiMTok":[102],"allows":[103],"compact":[105],"coarse-to-fine":[107,146],"representations,":[109],"aligning":[110],"well":[111],"LLM":[114],"paradigm":[116],"facilitating":[118],"direct":[120],"acquisition":[121],"capabilities.":[124],"We":[125],"develop":[126],"3-stage":[128],"training":[129,166],"recipe":[130],"progressive":[132],"learning":[133],"visual":[137,183,188],"capabilities,":[138],"featuring":[139],"hierarchical":[141],"loss":[143],"effective":[145],"learning.":[147],"Additionally,":[148],"enable":[150],"bidirectional":[151],"information":[152],"flow,":[153],"allowing":[154],"conversion":[155],"between":[156],"bounding":[157],"boxes":[158],"fully":[163],"leverage":[164],"multi-task":[165],"potential.":[167],"Extensive":[168],"experiments":[169],"demonstrate":[170],"that":[171],"our":[172],"method":[173],"achieves":[174],"state-of-the-art":[175],"across":[177],"various":[178],"tasks,while":[180],"also":[181],"enhancing":[182],"grounding":[184],"maintaining":[186],"overall":[187],"understanding.":[189]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-14T00:00:00"}