{"id":"https://openalex.org/W4224920290","doi":"https://doi.org/10.1109/icassp43922.2022.9746751","title":"Informative Attention Supervision for Grounded Video Description","display_name":"Informative Attention Supervision for Grounded Video Description","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920290","doi":"https://doi.org/10.1109/icassp43922.2022.9746751"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746751","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5103081907","display_name":"Boyang Wan","orcid":"https://orcid.org/0000-0001-8889-0287"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Boyang Wan","raw_affiliation_strings":["Jiangxi University of Finance and Economics,School of Information Management,Nanchang,China","School of Information Management, Jiangxi University of Finance and Economics, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,School of Information Management,Nanchang,China","institution_ids":["https://openalex.org/I59649739"]},{"raw_affiliation_string":"School of Information Management, Jiangxi University of Finance and Economics, Nanchang, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030344445","display_name":"Wenhui Jiang","orcid":"https://orcid.org/0000-0002-4144-6725"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhui Jiang","raw_affiliation_strings":["Jiangxi University of Finance and Economics,School of Information Management,Nanchang,China","School of Information Management, Jiangxi University of Finance and Economics, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,School of Information Management,Nanchang,China","institution_ids":["https://openalex.org/I59649739"]},{"raw_affiliation_string":"School of Information Management, Jiangxi University of Finance and Economics, Nanchang, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063013411","display_name":"Yuming Fang","orcid":"https://orcid.org/0000-0002-6946-3586"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Fang","raw_affiliation_strings":["Jiangxi University of Finance and Economics,School of Information Management,Nanchang,China","School of Information Management, Jiangxi University of Finance and Economics, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,School of Information Management,Nanchang,China","institution_ids":["https://openalex.org/I59649739"]},{"raw_affiliation_string":"School of Information Management, Jiangxi University of Finance and Economics, Nanchang, China","institution_ids":["https://openalex.org/I59649739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103081907"],"corresponding_institution_ids":["https://openalex.org/I59649739"],"apc_list":null,"apc_paid":null,"fwci":0.3595,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66018453,"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":"1955","last_page":"1959"},"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":0.9965000152587891,"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":0.9891999959945679,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.8240600824356079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7932748794555664},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.739791214466095},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.7133592367172241},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5968111157417297},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5906161665916443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5163675546646118},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.512633740901947},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38915157318115234},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32436037063598633},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1588057577610016},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.06148889660835266}],"concepts":[{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.8240600824356079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932748794555664},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.739791214466095},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.7133592367172241},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5968111157417297},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5906161665916443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5163675546646118},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.512633740901947},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38915157318115234},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32436037063598633},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1588057577610016},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.06148889660835266},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746751","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322956","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29"},{"id":"https://openalex.org/F4320327780","display_name":"Key Research and Development Program of Jiangxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1889081078","https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2463955103","https://openalex.org/W2486996822","https://openalex.org/W2795151422","https://openalex.org/W2884293275","https://openalex.org/W2962735233","https://openalex.org/W2963349562","https://openalex.org/W2963351113","https://openalex.org/W2963630207","https://openalex.org/W2963916161","https://openalex.org/W2968101724","https://openalex.org/W2969557970","https://openalex.org/W3035021504","https://openalex.org/W3035763695","https://openalex.org/W3092659741","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6722654596","https://openalex.org/W6753013641","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2348909947","https://openalex.org/W4292672442","https://openalex.org/W2362101859","https://openalex.org/W2791431590","https://openalex.org/W1978900583","https://openalex.org/W2350688482","https://openalex.org/W2053575972","https://openalex.org/W4323256314","https://openalex.org/W2042102171","https://openalex.org/W4251223544"],"abstract_inverted_index":{"Attention":[0],"supervision":[1,108,142],"encourages":[2],"grounded":[3],"video":[4],"description":[5,22],"models":[6],"(GVDMs)":[7],"to":[8,31,64,84,86,146],"focus":[9,32,65,148],"on":[10,33,67,149,167],"the":[11,21,47,56,62,72,82,92,95,100,136,144,152,168],"related":[12],"visual":[13],"content":[14],"when":[15,71],"generating":[16],"words.":[17],"Thus,":[18],"it":[19,79],"improves":[20],"performance":[23],"of":[24,94,151,158,160],"GVDMs.":[25],"However,":[26],"existing":[27],"GVDMs":[28,63,73,145],"often":[29],"fail":[30],"small":[34,130],"but":[35],"informative":[36,87,106,154],"regions":[37,40,70,88,132,156],"because":[38],"these":[39],"are":[41],"considered":[42],"as":[43],"negative":[44],"by":[45],"using":[46],"intersection-over-union":[48],"(IoU)":[49],"based":[50],"attention":[51,58,107,113,125,155],"groundtruth":[52,114,126],"sampling":[53,115],"method.":[54],"Moreover,":[55],"prevailing":[57],"loss":[59],"functions":[60],"enforce":[61],"equally":[66],"all":[68,159],"sampled":[69],"generate":[74],"words,":[75],"which":[76],"may":[77],"make":[78],"difficult":[80],"for":[81],"model":[83],"attend":[85],"and":[89,117,174],"thus":[90],"degrade":[91],"quality":[93],"generated":[96],"sentences.":[97],"To":[98],"alleviate":[99],"above":[101],"problems,":[102],"we":[103],"propose":[104],"an":[105],"method":[109,116,128],"including":[110],"a":[111,118],"novel":[112],"group-based":[119],"weak":[120],"grounding":[121,141],"supervision.":[122],"Specifically,":[123],"our":[124],"sample":[127],"captures":[129],"proposal":[131],"that":[133],"overlap":[134],"with":[135],"entity":[137],"boxes.":[138],"The":[139],"proposed":[140],"allows":[143],"dynamically":[147],"some":[150],"most":[153],"instead":[157],"them.":[161],"Our":[162],"approach":[163],"yields":[164],"competitive":[165],"results":[166],"ActivityNet":[169],"Entities":[170],"dataset":[171],"without":[172,179],"bells":[173],"whistles,":[175],"surpassing":[176],"previous":[177],"methods":[178],"increasing":[180],"inference":[181],"costs.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}