{"id":"https://openalex.org/W7118753380","doi":"https://doi.org/10.1109/tmm.2026.3651062","title":"Weakly Semi-Supervised Temporal Sentence Grounding in Videos With Point Annotations","display_name":"Weakly Semi-Supervised Temporal Sentence Grounding in Videos With Point Annotations","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7118753380","doi":"https://doi.org/10.1109/tmm.2026.3651062"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651062","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-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/A5122282036","display_name":"Jianxiang Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianxiang Dong","raw_affiliation_strings":["Stony Brook University, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-3617-0875","affiliations":[{"raw_affiliation_string":"Stony Brook University, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121391000","display_name":"Zhaozheng Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaozheng Yin","raw_affiliation_strings":["Stony Brook University, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-9602-6488","affiliations":[{"raw_affiliation_string":"Stony Brook University, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5122282036"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02981511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"2268","last_page":"2278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9272000193595886,"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":0.9272000193595886,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.013199999928474426,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.008299999870359898,"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/timestamp","display_name":"Timestamp","score":0.8411999940872192},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5899999737739563},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5875999927520752},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5834000110626221},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5814999938011169},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.5620999932289124},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.4921000003814697},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.47999998927116394},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.459199994802475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8668000102043152},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.8411999940872192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5967000126838684},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5875999927520752},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5834000110626221},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5620999932289124},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4921000003814697},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32510000467300415},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C162670838","wikidata":"https://www.wikidata.org/wiki/Q6057295","display_name":"Interval temporal logic","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651062","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46168339252471924,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Temporal":[0,42],"Sentence":[1,43],"Grounding":[2,44],"(TSG)":[3],"in":[4,220],"videos":[5],"aims":[6],"to":[7,20,92,113,131,141,160,188],"localize":[8],"a":[9,21,27,38,65,72,85,98,108,162,169],"temporal":[10],"interval":[11],"from":[12],"an":[13],"untrimmed":[14],"video":[15],"that":[16,200],"is":[17],"semantically":[18],"relevant":[19],"given":[22,124],"query":[23],"sentence.":[24],"To":[25,96],"achieve":[26],"balance":[28],"between":[29,214],"tremendous":[30],"annotation":[31],"burden":[32],"and":[33,59,64,135,146,155,180,183,209,216],"grounding":[34],"performance,":[35],"we":[36,82,106,129,167],"propose":[37,107,130,168],"new":[39],"Weakly":[40],"Semi-supervised":[41],"with":[45],"Points":[46],"(WSS-TSG-P)":[47],"task,":[48],"where":[49],"the":[50,119,123,191,211],"dataset":[51],"comprises":[52],"limited":[53],"fully-annotated":[54],"video-sentence":[55],"pairs":[56,70],"by":[57,71,176],"start":[58],"end":[60],"timestamps":[61],"(full":[62],"label)":[63],"large":[66],"amount":[67],"of":[68],"weakly-annotated":[69],"single":[73],"point":[74,90,125,147,156],"timestamp":[75],"(point":[76],"label).":[77],"Based":[78],"on":[79,118,196],"this":[80],"setting,":[81],"first":[83],"introduce":[84],"point-tomoment1":[86],"regressor":[87,100,133],"which":[88],"converts":[89],"annotations":[91,145],"pseudo":[93,103,137,153,185],"moment":[94,104,186],"labels.":[95],"train":[97,161],"good":[99],"for":[101],"reliable":[102,178],"labels,":[105],"point-guided":[109,171],"feature":[110,121],"aggregation":[111],"module":[112],"aggregate":[114],"cross-modal":[115],"representations":[116],"based":[117],"prototype":[120],"at":[122],"position.":[126],"In":[127,165],"addition,":[128,166],"perform":[132],"self-training":[134],"design":[136],"label":[138],"generation":[139],"strategies":[140],"exploit":[142],"both":[143],"full":[144],"annotations.":[148],"All":[149],"heterogeneous":[150],"labels":[151,187],"(full,":[152],"moment,":[154],"labels)":[157],"are":[158],"used":[159],"TSG":[163],"backbone.":[164],"novel":[170],"group":[172],"contrastive":[173],"learning":[174,207,218],"method":[175,203],"constructing":[177],"positive":[179],"negative":[181],"sets":[182],"re-weighting":[184],"further":[189],"improve":[190],"model":[192],"performance.":[193],"Extensive":[194],"experiments":[195],"benchmark":[197],"datasets":[198],"verify":[199],"our":[201],"proposed":[202],"outperforms":[204],"other":[205],"semi-supervised":[206],"methods":[208,219],"bridges":[210],"performance":[212],"gap":[213],"weakly-supervised":[215],"fully-supervised":[217],"TSG.":[221]},"counts_by_year":[],"updated_date":"2026-03-26T06:05:38.182114","created_date":"2026-01-08T00:00:00"}