{"id":"https://openalex.org/W4383097625","doi":"https://doi.org/10.1109/icra48891.2023.10161478","title":"Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs","display_name":"Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383097625","doi":"https://doi.org/10.1109/icra48891.2023.10161478"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5100736344","display_name":"Jingyi Wang","orcid":"https://orcid.org/0000-0002-7649-3011"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Wang","raw_affiliation_strings":["Tsinghua University,Department of Computer Science,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947034","display_name":"Jinfa Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfa Huang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University,China","School of Electronic and Computer Engineering, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440826","display_name":"Can Zhang","orcid":"https://orcid.org/0000-0001-9530-5218"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Zhang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University,China","School of Electronic and Computer Engineering, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102011846","display_name":"Zhidong Deng","orcid":"https://orcid.org/0000-0001-9970-1023"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhidong Deng","raw_affiliation_strings":["Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist), THUAI, State Key Laboratory of Intelligent Technology and Systems,Department of Computer Science,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist), THUAI, State Key Laboratory of Intelligent Technology and Systems,Department of Computer Science,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8231","last_page":"8238"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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":0.9944999814033508,"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":0.7353384494781494},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6916964650154114},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5686368942260742},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5662925839424133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5369863510131836},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.466610848903656},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42480459809303284},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3491278290748596},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33534130454063416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353384494781494},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6916964650154114},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5686368942260742},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5662925839424133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5369863510131836},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.466610848903656},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42480459809303284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3491278290748596},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33534130454063416},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G5541826327","display_name":null,"funder_award_id":"62176134","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2077069816","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2337252826","https://openalex.org/W2561238782","https://openalex.org/W2605736949","https://openalex.org/W2731516819","https://openalex.org/W2807697862","https://openalex.org/W2883170015","https://openalex.org/W2887783173","https://openalex.org/W2890783894","https://openalex.org/W2908510526","https://openalex.org/W2953106684","https://openalex.org/W2962716332","https://openalex.org/W2963101956","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2963541336","https://openalex.org/W2989506311","https://openalex.org/W2997006708","https://openalex.org/W3007063652","https://openalex.org/W3034679267","https://openalex.org/W3035517717","https://openalex.org/W3089532322","https://openalex.org/W3090132503","https://openalex.org/W3104862079","https://openalex.org/W3108124733","https://openalex.org/W3110290422","https://openalex.org/W3113025168","https://openalex.org/W3157307310","https://openalex.org/W3173364567","https://openalex.org/W3186621246","https://openalex.org/W3193902142","https://openalex.org/W3205264932","https://openalex.org/W3206376852","https://openalex.org/W3207057769","https://openalex.org/W3208423679","https://openalex.org/W3212977909","https://openalex.org/W3215287157","https://openalex.org/W4200630194","https://openalex.org/W4226054716","https://openalex.org/W4226373110","https://openalex.org/W4285077803","https://openalex.org/W4285102229","https://openalex.org/W4295750171","https://openalex.org/W4312317310","https://openalex.org/W4312732547","https://openalex.org/W6620707391","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6730179637","https://openalex.org/W6740493225","https://openalex.org/W6753775626","https://openalex.org/W6754554023","https://openalex.org/W6757817989","https://openalex.org/W6804931167","https://openalex.org/W6811168474"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W2997152889","https://openalex.org/W4385572700","https://openalex.org/W4307309205","https://openalex.org/W4288261899","https://openalex.org/W4385009901","https://openalex.org/W2768698792","https://openalex.org/W3016124757"],"abstract_inverted_index":{"Dynamic":[0],"scene":[1,46,59,88],"graphs":[2,60],"generated":[3],"from":[4],"video":[5],"clips":[6],"could":[7],"help":[8],"enhance":[9],"the":[10,37,81,93,105,119,142,150,161],"semantic":[11],"visual":[12],"understanding":[13],"in":[14,57,86],"a":[15,68,127,133],"wide":[16],"range":[17],"of":[18,30,39,84,95,98,121],"challenging":[19],"tasks":[20],"such":[21],"as":[22,104],"environmental":[23],"perception,":[24],"autonomous":[25],"navigation,":[26],"and":[27,33,41,135,177],"task":[28],"planning":[29],"self-driving":[31],"vehicles":[32],"mobile":[34],"robots.":[35],"In":[36,63,110],"process":[38],"temporal":[40,82],"spatial":[42],"modeling":[43],"during":[44],"dynamic":[45,58,87],"graph":[47],"generation,":[48],"it":[49],"is":[50,116],"particularly":[51],"intractable":[52],"to":[53,79],"learn":[54],"time-variant":[55,122,162],"relations":[56,85],"among":[61],"frames.":[62,146],"this":[64,111],"paper,":[65],"we":[66,91,125],"propose":[67],"Time-variant":[69],"Relation-aware":[70],"TRansformer":[71],"(TR":[72],"<sup":[73],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[74],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[75],"),":[76],"which":[77],"aims":[78],"model":[80,160],"change":[83],"graphs.":[89],"Explicitly,":[90],"leverage":[92],"difference":[94,143],"text":[96],"embeddings":[97],"prompted":[99],"sentences":[100],"about":[101],"relation":[102,128],"labels":[103],"supervision":[106],"signal":[107],"for":[108,118],"relations.":[109,123,163],"way,":[112],"cross-modality":[113],"feature":[114,129],"guidance":[115],"realized":[117],"learning":[120],"Implicitly,":[124],"design":[126],"fusion":[130],"module":[131],"with":[132],"transformer":[134],"an":[136],"additional":[137],"message":[138],"token":[139],"that":[140,155],"describes":[141],"between":[144],"adjacent":[145],"Extensive":[147],"experiments":[148],"on":[149],"Action":[151],"Genome":[152],"dataset":[153],"prove":[154],"our":[156],"TR2":[157,164],"can":[158],"effectively":[159],"significantly":[165],"outperforms":[166],"previous":[167],"state-of-the-art":[168],"methods":[169],"under":[170],"two":[171],"different":[172],"settings":[173],"by":[174],"2.1":[175],"%":[176],"2.6%":[178],"respectively.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}