{"id":"https://openalex.org/W4405785362","doi":"https://doi.org/10.1109/iros58592.2024.10802712","title":"Learning Temporally Composable Task Segmentations with Language","display_name":"Learning Temporally Composable Task Segmentations with Language","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785362","doi":"https://doi.org/10.1109/iros58592.2024.10802712"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5114080361","display_name":"Divyanshu Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Divyanshu Raj","raw_affiliation_strings":["Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002806266","display_name":"Omkar Patil","orcid":"https://orcid.org/0000-0002-7933-9837"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omkar Patil","raw_affiliation_strings":["Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100847729","display_name":"Weiwei Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiwei Gu","raw_affiliation_strings":["Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083735830","display_name":"Chitta Baral","orcid":"https://orcid.org/0000-0002-7549-723X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chitta Baral","raw_affiliation_strings":["Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089421543","display_name":"Nakul Gopalan","orcid":"https://orcid.org/0000-0002-6947-5501"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nakul Gopalan","raw_affiliation_strings":["Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114080361"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21495568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5195","last_page":"5202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9758999943733215,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9758999943733215,"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":0.9466000199317932,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9412000179290771,"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":0.830693244934082},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6617141366004944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4220949411392212},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40626490116119385},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3480048179626465},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06675645709037781}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.830693244934082},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6617141366004944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4220949411392212},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40626490116119385},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3480048179626465},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06675645709037781},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1963873191","https://openalex.org/W2011760672","https://openalex.org/W2022760091","https://openalex.org/W2056262371","https://openalex.org/W2063471043","https://openalex.org/W2211996086","https://openalex.org/W2277684984","https://openalex.org/W2636355936","https://openalex.org/W2962736495","https://openalex.org/W2963017553","https://openalex.org/W2963393391","https://openalex.org/W2964089981","https://openalex.org/W2967186499","https://openalex.org/W2981750465","https://openalex.org/W2994446013","https://openalex.org/W3007769740","https://openalex.org/W3025323587","https://openalex.org/W3034758614","https://openalex.org/W3040621713","https://openalex.org/W3104862079","https://openalex.org/W3105232955","https://openalex.org/W3211772574","https://openalex.org/W4214773477","https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4387764390","https://openalex.org/W4401416041","https://openalex.org/W6636408305","https://openalex.org/W6646884813","https://openalex.org/W6684863604","https://openalex.org/W6687461575","https://openalex.org/W6739847781","https://openalex.org/W6778883912","https://openalex.org/W6799428148","https://openalex.org/W6849861922","https://openalex.org/W6854738657"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W3204019825","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"In":[0,112,183],"this":[1,84],"work,":[2],"we":[3,115,187,196],"present":[4],"an":[5,209],"approach":[6,114,140],"to":[7,50,87,128,160,167,231],"identify":[8],"sub-tasks":[9,155],"within":[10],"a":[11,130,142,192,199,221],"demonstrated":[12],"robot":[13,69,125],"trajectory":[14,70,126,154,228],"with":[15,28,66,74,156,191],"the":[16,119,169,203,226],"supervision":[17],"provided":[18],"by":[19,52,93,229],"language":[20,157],"instructions.":[21],"Learning":[22],"longer":[23,89],"horizon":[24,90,97],"tasks":[25,43,46,98],"is":[26,86],"challenging":[27],"techniques":[29,117],"such":[30,78,208],"as":[31,79],"reinforcement":[32],"learning":[33],"and":[34,72,177],"behavior":[35,105,212],"cloning.":[36],"Previous":[37],"approaches":[38,107],"have":[39],"split":[40,88],"these":[41],"long":[42],"into":[44,95],"shorter":[45,96],"that":[47,99,161,189],"are":[48],"easier":[49],"learn":[51],"using":[53,103,108,207],"statistical":[54],"change":[55],"point":[56],"detection":[57,62,134],"methods.":[58],"However,":[59],"classical":[60],"changepoint":[61],"methods":[63],"function":[64],"only":[65],"low":[67],"dimensional":[68,76],"data":[71,127,185],"not":[73],"high":[75],"inputs":[77],"vision.":[80],"Our":[81,136],"goal":[82],"in":[83,147],"work":[85],"tasks,":[91],"represented":[92],"trajectories":[94,195,219],"can":[100,197],"be":[101],"learned":[102],"conventional":[104],"cloning":[106,213],"guidance":[109,158],"from":[110,118],"language.":[111,163],"our":[113,181,184,217],"use":[116],"video":[120],"moment":[121,138],"retrieval":[122],"problem":[123],"on":[124,216,225],"demonstrate":[129],"high-dimensional":[131],"generalizable":[132],"change-point":[133],"approach.":[135,210],"proposed":[137],"retrieval-based":[139],"shows":[141],"more":[143],"than":[144],"30%":[145],"improvement":[146],"mean":[148],"average":[149],"precision":[150],"(mAP)":[151],"for":[152],"identifying":[153],"compared":[159],"without":[162],"We":[164],"perform":[165],"ablations":[166],"understand":[168],"effects":[170],"of":[171,180,206],"domain":[172],"randomization,":[173],"sample":[174,204],"complexity,":[175],"views,":[176],"sim-to-real":[178],"transfer":[179],"method.":[182],"ablation":[186],"find":[188],"just":[190],"100":[193],"labelled":[194],"achieve":[198],"61.41":[200],"mAP,":[201],"demonstrating":[202],"efficiency":[205],"Further,":[211],"models":[214],"trained":[215,224],"segmented":[218],"outperform":[220],"single":[222],"model":[223],"whole":[227],"up":[230],"20%.":[232]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}