{"id":"https://openalex.org/W4401416473","doi":"https://doi.org/10.1109/icra57147.2024.10611354","title":"Towards Unified Interactive Visual Grounding in The Wild","display_name":"Towards Unified Interactive Visual Grounding in The Wild","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416473","doi":"https://doi.org/10.1109/icra57147.2024.10611354"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":"https://openalex.org/A5085531312","display_name":"Jie Xu","orcid":"https://orcid.org/0000-0001-5291-5198"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Xu","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074050672","display_name":"Hanbo Zhang","orcid":"https://orcid.org/0000-0002-2235-6855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanbo Zhang","raw_affiliation_strings":["ByteDance Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013535642","display_name":"Qingyi Si","orcid":"https://orcid.org/0000-0001-8433-0215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyi Si","raw_affiliation_strings":["ByteDance Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033510515","display_name":"Yifeng Li","orcid":"https://orcid.org/0000-0002-4873-6928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifeng Li","raw_affiliation_strings":["ByteDance Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006277484","display_name":"Xuguang Lan","orcid":"https://orcid.org/0000-0002-3422-944X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuguang Lan","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065667064","display_name":"Tao Kong","orcid":"https://orcid.org/0000-0002-9412-1457"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Kong","raw_affiliation_strings":["ByteDance Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3288","last_page":"3295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9983999729156494,"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":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.6791026592254639},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5455233454704285},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3893272578716278},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3735213875770569},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12994864583015442},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10395008325576782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791026592254639},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5455233454704285},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3893272578716278},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3735213875770569},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12994864583015442},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10395008325576782}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":78,"referenced_works":["https://openalex.org/W1485735559","https://openalex.org/W1583837637","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W1980043766","https://openalex.org/W2097476943","https://openalex.org/W2109586012","https://openalex.org/W2199571216","https://openalex.org/W2293700449","https://openalex.org/W2489434015","https://openalex.org/W2552002300","https://openalex.org/W2558809543","https://openalex.org/W2599940792","https://openalex.org/W2779827764","https://openalex.org/W2963010567","https://openalex.org/W2963758027","https://openalex.org/W2964345792","https://openalex.org/W2966715458","https://openalex.org/W2983943451","https://openalex.org/W2997117909","https://openalex.org/W2998012869","https://openalex.org/W3034727271","https://openalex.org/W3090449556","https://openalex.org/W3096415518","https://openalex.org/W3173220247","https://openalex.org/W3174510143","https://openalex.org/W3179845435","https://openalex.org/W3207187156","https://openalex.org/W3214685499","https://openalex.org/W4224308101","https://openalex.org/W4225323055","https://openalex.org/W4225591000","https://openalex.org/W4283208789","https://openalex.org/W4285102324","https://openalex.org/W4285294723","https://openalex.org/W4288089799","https://openalex.org/W4289548744","https://openalex.org/W4292779060","https://openalex.org/W4311642023","https://openalex.org/W4322718191","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4367367040","https://openalex.org/W4376312115","https://openalex.org/W4383109104","https://openalex.org/W4384918448","https://openalex.org/W4387804152","https://openalex.org/W4390874575","https://openalex.org/W4401043272","https://openalex.org/W6629041193","https://openalex.org/W6639432524","https://openalex.org/W6676497082","https://openalex.org/W6697165031","https://openalex.org/W6735343109","https://openalex.org/W6753048945","https://openalex.org/W6766111395","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6769627184","https://openalex.org/W6770039263","https://openalex.org/W6778883912","https://openalex.org/W6789909235","https://openalex.org/W6791353385","https://openalex.org/W6804095316","https://openalex.org/W6810081322","https://openalex.org/W6810220367","https://openalex.org/W6810334672","https://openalex.org/W6839091850","https://openalex.org/W6847118041","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6852060543","https://openalex.org/W6852800892","https://openalex.org/W6853116092","https://openalex.org/W6854324007","https://openalex.org/W6854866820","https://openalex.org/W6857715090"],"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/W2379604501"],"abstract_inverted_index":{"Interactive":[0],"visual":[1,61,72,144],"grounding":[2,62],"in":[3,16,43,46,63],"Human-Robot":[4],"Interaction":[5],"(HRI)":[6],"is":[7],"challenging":[8,95,127],"yet":[9],"practical":[10],"due":[11],"to":[12,22,38,92,142],"the":[13,24,99,123],"inevitable":[14],"ambiguity":[15],"natural":[17],"languages.":[18],"It":[19],"requires":[20],"robots":[21],"disambiguate":[23],"user\u2019s":[25],"input":[26],"by":[27,113],"active":[28],"information":[29],"gathering.":[30],"Previous":[31],"approaches":[32],"often":[33],"rely":[34],"on":[35,81,104,122,158],"predefined":[36],"templates":[37],"ask":[39],"disambiguation":[40],"questions,":[41],"resulting":[42],"performance":[44,112],"reduction":[45],"realistic":[47],"interactive":[48,60],"scenarios.":[49,97],"In":[50,98],"this":[51],"paper,":[52],"we":[53,101,118],"propose":[54],"TiO,":[55],"an":[56],"end-to-end":[57],"system":[58],"for":[59],"human-robot":[64],"interaction.":[65],"Benefiting":[66],"from":[67],"a":[68,82,114,149],"unified":[69],"formulation":[70],"of":[71,84],"dialog":[73],"and":[74,88,94,106,145,154],"grounding,":[75],"our":[76,137],"method":[77,138],"can":[78],"be":[79],"trained":[80],"joint":[83],"extensive":[85],"public":[86],"data,":[87],"show":[89,135],"superior":[90,140],"generality":[91,141],"diversified":[93,143],"open-world":[96],"experiments,":[100],"validate":[102],"TiO":[103],"GuessWhat?!":[105],"InViG":[107],"benchmarks,":[108],"setting":[109],"new":[110],"state-of-the-art":[111],"clear":[115],"margin.":[116],"Moreover,":[117],"conduct":[119],"HRI":[120],"experiments":[121],"carefully":[124],"selected":[125],"150":[126],"scenes":[128],"as":[129,131],"well":[130],"real-robot":[132],"platforms.":[133],"Results":[134],"that":[136],"demonstrates":[139],"language":[146],"inputs":[147],"with":[148],"high":[150],"success":[151],"rate.":[152],"Codes":[153],"demos":[155],"are":[156],"available":[157],"https://jxu124.github.io/TiO/.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}