{"id":"https://openalex.org/W4402753283","doi":"https://doi.org/10.1109/cvpr52733.2024.01349","title":"Groundhog Grounding Large Language Models to Holistic Segmentation","display_name":"Groundhog Grounding Large Language Models to Holistic Segmentation","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402753283","doi":"https://doi.org/10.1109/cvpr52733.2024.01349"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5100444201","display_name":"Yichi Zhang","orcid":"https://orcid.org/0000-0003-3214-1070"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yichi Zhang","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036217307","display_name":"Ziqiao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziqiao Ma","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023073132","display_name":"Xiaofeng Gao","orcid":"https://orcid.org/0000-0003-3331-9846"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofeng Gao","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062889462","display_name":"Suhaila Shakiah","orcid":"https://orcid.org/0000-0002-1891-7058"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suhaila Shakiah","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077622605","display_name":"Qiaozi Gao","orcid":"https://orcid.org/0000-0002-5403-0796"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiaozi Gao","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026638047","display_name":"Joyce Chai","orcid":"https://orcid.org/0000-0002-9658-2230"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joyce Chai","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2495,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.96707834,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"14227","last_page":"14238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9991999864578247,"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":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.7410300970077515},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.46817153692245483},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.46013325452804565},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4167477488517761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3837664723396301},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11687469482421875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7410300970077515},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.46817153692245483},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.46013325452804565},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4167477488517761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3837664723396301},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11687469482421875},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.01349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":118,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1773149199","https://openalex.org/W1923115158","https://openalex.org/W1956340063","https://openalex.org/W2031489346","https://openalex.org/W2107019937","https://openalex.org/W2247513039","https://openalex.org/W2264742718","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2506483933","https://openalex.org/W2558809543","https://openalex.org/W2561196672","https://openalex.org/W2596567068","https://openalex.org/W2612560781","https://openalex.org/W2780846250","https://openalex.org/W2792937288","https://openalex.org/W2908510526","https://openalex.org/W2948672349","https://openalex.org/W2962749469","https://openalex.org/W2963109634","https://openalex.org/W2963262989","https://openalex.org/W2963518342","https://openalex.org/W2963705779","https://openalex.org/W2979382951","https://openalex.org/W2999219213","https://openalex.org/W3034764937","https://openalex.org/W3095670406","https://openalex.org/W3098232790","https://openalex.org/W3159619744","https://openalex.org/W3168597991","https://openalex.org/W3179897446","https://openalex.org/W3180169285","https://openalex.org/W3193613442","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4214530390","https://openalex.org/W4225323055","https://openalex.org/W4236965008","https://openalex.org/W4287113019","https://openalex.org/W4287586989","https://openalex.org/W4312331087","https://openalex.org/W4312563428","https://openalex.org/W4312815172","https://openalex.org/W4312956471","https://openalex.org/W4312988011","https://openalex.org/W4313068342","https://openalex.org/W4320167334","https://openalex.org/W4366208220","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4367367040","https://openalex.org/W4375869762","https://openalex.org/W4376122449","https://openalex.org/W4376312115","https://openalex.org/W4377164404","https://openalex.org/W4381415952","https://openalex.org/W4382132560","https://openalex.org/W4382490555","https://openalex.org/W4382491206","https://openalex.org/W4383987918","https://openalex.org/W4384648427","https://openalex.org/W4384918448","https://openalex.org/W4385571695","https://openalex.org/W4385958573","https://openalex.org/W4386065815","https://openalex.org/W4386071509","https://openalex.org/W4386240819","https://openalex.org/W4387225729","https://openalex.org/W4387596621","https://openalex.org/W4389519620","https://openalex.org/W4389523832","https://openalex.org/W4390873847","https://openalex.org/W4390874575","https://openalex.org/W4390874594","https://openalex.org/W4390874680","https://openalex.org/W4396681775","https://openalex.org/W4401770219","https://openalex.org/W4402727764","https://openalex.org/W6678262379","https://openalex.org/W6691231616","https://openalex.org/W6749224410","https://openalex.org/W6757081750","https://openalex.org/W6757817989","https://openalex.org/W6786556762","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6797716411","https://openalex.org/W6801512601","https://openalex.org/W6810334672","https://openalex.org/W6839015040","https://openalex.org/W6839091850","https://openalex.org/W6846500931","https://openalex.org/W6848935878","https://openalex.org/W6850147914","https://openalex.org/W6851592950","https://openalex.org/W6851800889","https://openalex.org/W6851813333","https://openalex.org/W6851950068","https://openalex.org/W6852060543","https://openalex.org/W6852667213","https://openalex.org/W6852989508","https://openalex.org/W6852999659","https://openalex.org/W6853105247","https://openalex.org/W6853116092","https://openalex.org/W6854093740","https://openalex.org/W6854222408","https://openalex.org/W6854262950","https://openalex.org/W6854596735","https://openalex.org/W6854866820","https://openalex.org/W6854915240","https://openalex.org/W6856093385","https://openalex.org/W6856224812","https://openalex.org/W6856857450","https://openalex.org/W6857109777","https://openalex.org/W6857162426","https://openalex.org/W6857569170","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2021787609","https://openalex.org/W2390279801","https://openalex.org/W2097328689","https://openalex.org/W2358668433","https://openalex.org/W4234899305","https://openalex.org/W4396701345","https://openalex.org/W1537063595","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Most":[0],"multimodal":[1],"large":[2],"language":[3,11,129],"models":[4],"(MLLMs)":[5],"learn":[6],"language-to-object":[7],"grounding":[8,50,82,130,144],"through":[9],"causal":[10],"modeling":[12],"where":[13],"grounded":[14,99],"objects":[15],"are":[16,32],"captured":[17],"by":[18,49,84,108],"bounding":[19],"boxes":[20],"as":[21],"sequences":[22],"of":[23,112,148],"location":[24],"tokens.":[25],"This":[26],"paradigm":[27],"lacks":[28],"pixel-level":[29],"representations":[30],"that":[31,122],"important":[33],"for":[34,71],"fine-grained":[35],"visual":[36,68,100,149],"understanding":[37],"and":[38,63,86,135,151],"diagnosis.":[39],"In":[40],"this":[41],"work,":[42],"we":[43,94],"introduce":[44],"Groundhog,":[45],"an":[46],"MLLM":[47,73],"developed":[48],"Large":[51],"Language":[52],"Models":[53],"to":[54,80],"holistic":[55],"segmentation.":[56],"GROUNDHOG":[57,123,140],"incorporates":[58],"a":[59,98,110],"masked":[60],"feature":[61],"extractor":[62],"converts":[64],"extracted":[65],"features":[66],"into":[67],"entity":[69,89],"tokens":[70],"the":[72,88],"backbone,":[74],"which":[75],"then":[76],"connects":[77],"groundable":[78],"phrases":[79],"unified":[81],"masks":[83],"retrieving":[85],"merging":[87],"masks.":[90],"To":[91],"train":[92],"GROUNDHOG,":[93],"carefully":[95],"curated":[96],"M3G2,":[97],"instruction":[101],"tuning":[102],"dataset":[103],"with":[104,115],"Multi-Modal":[105],"Multi-Grained":[106],"Grounding,":[107],"harvesting":[109],"collection":[111],"segmentation-grounded":[113],"datasets":[114],"rich":[116],"annotations.":[117],"Our":[118],"experimental":[119],"results":[120],"show":[121],"achieves":[124],"superior":[125],"performance":[126],"on":[127],"various":[128],"tasks":[131],"without":[132],"task-specific":[133],"fine-tuning,":[134],"significantly":[136],"reduces":[137],"object":[138],"hallucination.":[139],"also":[141],"demonstrates":[142],"better":[143],"towards":[145],"complex":[146],"forms":[147],"input":[150],"provides":[152],"easy-to-understand":[153],"diagnosis":[154],"in":[155],"failure":[156],"cases.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}