{"id":"https://openalex.org/W2936758701","doi":"https://doi.org/10.1109/icassp.2019.8683464","title":"Visual Relationship Recognition via Language and Position Guided Attention","display_name":"Visual Relationship Recognition via Language and Position Guided Attention","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936758701","doi":"https://doi.org/10.1109/icassp.2019.8683464","mag":"2936758701"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5022574607","display_name":"Hao Zhou","orcid":"https://orcid.org/0000-0002-0173-0393"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhou","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013484007","display_name":"Chuanping Hu","orcid":"https://orcid.org/0009-0003-7769-8005"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanping Hu","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023787090","display_name":"Chongyang Zhang","orcid":"https://orcid.org/0000-0001-7292-0445"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongyang Zhang","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003864108","display_name":"Shengyang Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyang Shen","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.5079,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68411854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2097","last_page":"2101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9988999962806702,"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":0.704585075378418},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.5607765316963196},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5006330013275146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4452624022960663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44363996386528015},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3909664750099182},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3710360527038574},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35199904441833496},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24194633960723877},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.1203850507736206},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.10307195782661438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.704585075378418},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.5607765316963196},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5006330013275146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4452624022960663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44363996386528015},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3909664750099182},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3710360527038574},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35199904441833496},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24194633960723877},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.1203850507736206},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.10307195782661438},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W2049705550","https://openalex.org/W2153579005","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2550553598","https://openalex.org/W2591644541","https://openalex.org/W2607855566","https://openalex.org/W2740962769","https://openalex.org/W2777602943","https://openalex.org/W2883170015","https://openalex.org/W2962737704","https://openalex.org/W2962749469","https://openalex.org/W2962891704","https://openalex.org/W2963150697","https://openalex.org/W2963495494","https://openalex.org/W2963656855","https://openalex.org/W4294170691","https://openalex.org/W6618372016","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6680053761","https://openalex.org/W6728925852"],"related_works":["https://openalex.org/W2385118824","https://openalex.org/W2359476137","https://openalex.org/W2362165903","https://openalex.org/W2575294667","https://openalex.org/W2378962668","https://openalex.org/W2760239433","https://openalex.org/W2358910850","https://openalex.org/W1548456315","https://openalex.org/W2758017229","https://openalex.org/W2146954092"],"abstract_inverted_index":{"Visual":[0],"relationship":[1,60],"recognition,":[2],"as":[3],"a":[4,57],"challenging":[5],"task":[6],"used":[7,84],"to":[8,85,105],"distinguish":[9],"the":[10,21,87,93,96,107],"interactions":[11],"between":[12],"object":[13],"pairs,":[14],"has":[15],"received":[16],"much":[17],"attention":[18,90,128],"recently.":[19],"Considering":[20],"fact":[22],"that":[23],"most":[24],"visual":[25,59],"relationships":[26],"are":[27,35,73,83],"semantic":[28],"concepts":[29],"defined":[30],"by":[31,49],"human":[32,37,98],"beings,":[33],"there":[34],"many":[36],"knowledge,":[38],"or":[39],"priors,":[40],"hidden":[41,97],"in":[42],"them,":[43],"which":[44],"haven't":[45],"been":[46],"fully":[47],"exploited":[48,74],"existing":[50],"methods.":[51],"In":[52],"this":[53],"work,":[54],"we":[55],"propose":[56],"novel":[58],"recognition":[61],"model":[62,132],"using":[63],"language":[64,69,124],"and":[65,70,75,78,111,118,125],"position":[66,71,126],"guided":[67,94,127],"attention:":[68],"information":[72],"vectored":[76],"firstly,":[77],"then":[79],"both":[80],"of":[81,89,109],"them":[82],"guide":[86],"generation":[88],"maps.":[91],"With":[92],"attention,":[95],"knowledge":[99],"can":[100],"be":[101],"made":[102],"better":[103],"use":[104],"enhance":[106],"selection":[108],"spatial":[110],"channel":[112],"features.":[113],"Experiments":[114],"on":[115],"VRD":[116],"[2]":[117],"VGR":[119],"[1]":[120],"show":[121],"that,":[122],"with":[123],"module,":[129],"our":[130],"proposed":[131],"achieves":[133],"state-of-the-art":[134],"performance.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
