{"id":"https://openalex.org/W2946086442","doi":"https://doi.org/10.1109/tpami.2019.2911066","title":"Learning to Compose and Reason with Language Tree Structures for Visual Grounding","display_name":"Learning to Compose and Reason with Language Tree Structures for Visual Grounding","publication_year":2019,"publication_date":"2019-05-21","ids":{"openalex":"https://openalex.org/W2946086442","doi":"https://doi.org/10.1109/tpami.2019.2911066","mag":"2946086442"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2019.2911066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2019.2911066","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.01784","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Richang Hong","raw_affiliation_strings":["School of Computer & Information, Hefei University of Technology, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"School of Computer & Information, Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424059","display_name":"Daqing Liu","orcid":"https://orcid.org/0000-0002-8286-0105"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daqing Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046347854","display_name":"Xiaoyu Mo","orcid":"https://orcid.org/0000-0002-8729-5037"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaoyu Mo","raw_affiliation_strings":["School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038668215","display_name":"Xiangnan He","orcid":"https://orcid.org/0000-0001-8472-7992"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangnan He","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["School of Computer Science & Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051332325"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":5.211,"has_fulltext":false,"cited_by_count":183,"citation_normalized_percentile":{"value":0.96442969,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"44","issue":"2","first_page":"684","last_page":"696"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9966999888420105,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9962000250816345,"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":0.7413903474807739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6488232612609863},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.570877194404602},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5539118051528931},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5284604430198669},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49919581413269043},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4952026903629303},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4590339660644531},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.42742565274238586},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3571137487888336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13348764181137085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7413903474807739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6488232612609863},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.570877194404602},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5539118051528931},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5284604430198669},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49919581413269043},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4952026903629303},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4590339660644531},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.42742565274238586},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3571137487888336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13348764181137085},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2019.2911066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2019.2911066","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1906.01784","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.01784","pdf_url":"https://arxiv.org/pdf/1906.01784","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"pmh:oai:dr.ntu.edu.sg:10356/162632","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/162632","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.01784","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.01784","pdf_url":"https://arxiv.org/pdf/1906.01784","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2351125877","display_name":null,"funder_award_id":"61732007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6400325034","display_name":null,"funder_award_id":"2017YFB1002203","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8795738074","display_name":null,"funder_award_id":"61722204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1933349210","https://openalex.org/W2097117768","https://openalex.org/W2119717200","https://openalex.org/W2123442489","https://openalex.org/W2126433015","https://openalex.org/W2131774270","https://openalex.org/W2194775991","https://openalex.org/W2247513039","https://openalex.org/W2250539671","https://openalex.org/W2251939518","https://openalex.org/W2308720496","https://openalex.org/W2489434015","https://openalex.org/W2547875792","https://openalex.org/W2558535589","https://openalex.org/W2561715562","https://openalex.org/W2570343428","https://openalex.org/W2571175805","https://openalex.org/W2583360688","https://openalex.org/W2591644541","https://openalex.org/W2603266952","https://openalex.org/W2613718673","https://openalex.org/W2619818172","https://openalex.org/W2752868598","https://openalex.org/W2774005037","https://openalex.org/W2779827764","https://openalex.org/W2791751435","https://openalex.org/W2799263800","https://openalex.org/W2950697717","https://openalex.org/W2950761309","https://openalex.org/W2952644835","https://openalex.org/W2962716332","https://openalex.org/W2962764817","https://openalex.org/W2962811161","https://openalex.org/W2963042258","https://openalex.org/W2963109634","https://openalex.org/W2963224792","https://openalex.org/W2963389687","https://openalex.org/W2963451457","https://openalex.org/W2963580443","https://openalex.org/W2963735467","https://openalex.org/W2963735856","https://openalex.org/W2963921921","https://openalex.org/W2964022527","https://openalex.org/W2964121744","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W3098232790","https://openalex.org/W4230563027","https://openalex.org/W4241811150","https://openalex.org/W4246193833","https://openalex.org/W6631190155","https://openalex.org/W6679073109","https://openalex.org/W6691459498","https://openalex.org/W6725939724","https://openalex.org/W6729448088","https://openalex.org/W6730230071"],"related_works":["https://openalex.org/W2021787609","https://openalex.org/W1537063595","https://openalex.org/W2097328689","https://openalex.org/W4234899305","https://openalex.org/W2379604501","https://openalex.org/W2373854414","https://openalex.org/W2574906695","https://openalex.org/W2293063786","https://openalex.org/W2911292476","https://openalex.org/W2741631785"],"abstract_inverted_index":{"Grounding":[0,105],"natural":[1,68],"language":[2,33,46,69,83,115],"in":[3,23,59,92],"images,":[4],"such":[5],"as":[6,26],"localizing":[7],"\u201cthe":[8],"black":[9],"dog":[10],"on":[11,40,173],"the":[12,15,20,31,41,44,53,60,82,90,111,126,141,153,159,162,168,181],"left":[13],"of":[14,19,55],"tree\u201d,":[16],"is":[17,108],"one":[18],"core":[21],"problems":[22],"artificial":[24],"intelligence,":[25],"it":[27],"needs":[28],"to":[29],"comprehend":[30],"fine-grained":[32],"compositions.":[34],"However,":[35],"existing":[36],"solutions":[37],"merely":[38],"rely":[39],"association":[42],"between":[43],"holistic":[45],"features":[47],"and":[48,84,125],"visual":[49,87],"features,":[50],"while":[51],"neglect":[52],"nature":[54],"composite":[56],"reasoning":[57,88],"implied":[58],"language.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"propose":[66],"a":[67,76,93],"grounding":[70,127,137],"model":[71,99,179],"that":[72,113,157,177],"can":[73,117,130,147],"automatically":[74],"compose":[75],"binary":[77],"tree":[78,91,170],"structure":[79],"for":[80],"parsing":[81],"then":[85],"perform":[86],"along":[89],"bottom-up":[94],"fashion.":[95],"We":[96],"call":[97],"our":[98,178],"<sc":[100,144],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[101,145],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">RvG-Tree</small>":[102,146],":":[103],"Recursive":[104],"Tree,":[106],"which":[107],"inspired":[109],"by":[110,134,140,151],"intuition":[112],"any":[114],"expression":[116],"be":[118,131,148],"recursively":[119,132],"decomposed":[120],"into":[121],"two":[122,142],"constituent":[123],"parts,":[124],"confidence":[128],"score":[129,164],"accumulated":[133],"calculating":[135],"their":[136],"scores":[138],"returned":[139],"sub-trees.":[143],"trained":[149],"end-to-end":[150],"using":[152],"Straight-Through":[154],"Gumbel-Softmax":[155],"estimator":[156],"allows":[158],"gradients":[160],"from":[161],"continuous":[163],"functions":[165],"passing":[166],"through":[167],"discrete":[169],"construction.":[171],"Experiments":[172],"several":[174],"benchmarks":[175],"show":[176],"achieves":[180],"state-of-the-art":[182],"performance":[183],"with":[184],"more":[185],"explainable":[186],"reasoning.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":41},{"year":2024,"cited_by_count":49},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":27},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-05-29T00:00:00"}