{"id":"https://openalex.org/W4312565984","doi":"https://doi.org/10.1007/978-3-031-19824-3_29","title":"D$$^3$$Net: A Unified Speaker-Listener Architecture for\u00a03D Dense Captioning and\u00a0Visual Grounding","display_name":"D$$^3$$Net: A Unified Speaker-Listener Architecture for\u00a03D Dense Captioning and\u00a0Visual Grounding","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312565984","doi":"https://doi.org/10.1007/978-3-031-19824-3_29"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-19824-3_29","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-19824-3_29","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5026731366","display_name":"Dave Zhenyu Chen","orcid":"https://orcid.org/0000-0002-3883-1905"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dave Zhenyu Chen","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101988633","display_name":"Qirui Wu","orcid":"https://orcid.org/0000-0003-3260-8224"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Qirui Wu","raw_affiliation_strings":["Simon Fraser University, Burnaby, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088583491","display_name":"Matthias Nie\u00dfner","orcid":"https://orcid.org/0000-0001-6093-5199"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Nie\u00dfner","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044978994","display_name":"Anne Lynn S. Chang","orcid":"https://orcid.org/0000-0002-2869-2147"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Angel X. Chang","raw_affiliation_strings":["Simon Fraser University, Burnaby, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"487","last_page":"505"},"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":0.9991999864578247,"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":0.9921000003814697,"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/closed-captioning","display_name":"Closed captioning","score":0.9719504117965698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8799902200698853},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7441513538360596},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7419254779815674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6312536001205444},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.57639479637146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48184287548065186},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42680612206459045},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38341468572616577},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37392091751098633},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37285661697387695},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3297659754753113},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3006722033023834}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9719504117965698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8799902200698853},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7441513538360596},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7419254779815674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6312536001205444},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.57639479637146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48184287548065186},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42680612206459045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38341468572616577},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37392091751098633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37285661697387695},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3297659754753113},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3006722033023834}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-19824-3_29","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-19824-3_29","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1923184257","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1981276685","https://openalex.org/W2119717200","https://openalex.org/W2251512949","https://openalex.org/W2302548814","https://openalex.org/W2332488709","https://openalex.org/W2552002300","https://openalex.org/W2563685048","https://openalex.org/W2571175805","https://openalex.org/W2575842049","https://openalex.org/W2583360688","https://openalex.org/W2594519801","https://openalex.org/W2745461083","https://openalex.org/W2795014656","https://openalex.org/W2805984364","https://openalex.org/W2885013662","https://openalex.org/W2904332125","https://openalex.org/W2963084599","https://openalex.org/W2963109634","https://openalex.org/W2963125977","https://openalex.org/W2963170456","https://openalex.org/W2963448089","https://openalex.org/W2963735856","https://openalex.org/W2963758027","https://openalex.org/W2964078384","https://openalex.org/W2964339842","https://openalex.org/W2964345792","https://openalex.org/W2970971581","https://openalex.org/W2976658881","https://openalex.org/W2987068636","https://openalex.org/W2988715931","https://openalex.org/W3034626012","https://openalex.org/W3034949383","https://openalex.org/W3095974555","https://openalex.org/W3106859150","https://openalex.org/W3107521863","https://openalex.org/W3133833192","https://openalex.org/W3175234951","https://openalex.org/W3182910454","https://openalex.org/W3187293622","https://openalex.org/W3203949114","https://openalex.org/W4221167937","https://openalex.org/W6630827713","https://openalex.org/W6702248584","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3009056573","https://openalex.org/W3040691452","https://openalex.org/W3161079477"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
