{"id":"https://openalex.org/W4402715892","doi":"https://doi.org/10.1109/cvpr52733.2024.01740","title":"HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding","display_name":"HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402715892","doi":"https://doi.org/10.1109/cvpr52733.2024.01740"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5047520818","display_name":"Trong-Thuan Nguyen","orcid":"https://orcid.org/0000-0001-7729-2927"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trong-Thuan Nguyen","raw_affiliation_strings":["University of Arkansas,CVIU Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arkansas,CVIU Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002689322","display_name":"Pha Nguyen","orcid":"https://orcid.org/0000-0003-1517-1382"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pha Nguyen","raw_affiliation_strings":["University of Arkansas,CVIU Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arkansas,CVIU Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056226189","display_name":"Khoa Luu","orcid":"https://orcid.org/0000-0003-2104-0901"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khoa Luu","raw_affiliation_strings":["University of Arkansas,CVIU Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arkansas,CVIU Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18384","last_page":"18394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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":0.9983999729156494,"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":0.775759220123291},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5505620241165161},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.48389753699302673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3471270203590393},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.282338410615921},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08630046248435974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.775759220123291},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5505620241165161},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.48389753699302673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3471270203590393},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.282338410615921},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08630046248435974},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.01740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2277195237","https://openalex.org/W2337252826","https://openalex.org/W2579549467","https://openalex.org/W2618799552","https://openalex.org/W2891033863","https://openalex.org/W2951323451","https://openalex.org/W2955189650","https://openalex.org/W2963351448","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W2994508843","https://openalex.org/W3034538190","https://openalex.org/W3034679267","https://openalex.org/W3035503132","https://openalex.org/W3035564946","https://openalex.org/W3035590142","https://openalex.org/W3096609285","https://openalex.org/W3167258964","https://openalex.org/W3181951703","https://openalex.org/W3194397797","https://openalex.org/W3205786327","https://openalex.org/W3207758636","https://openalex.org/W3215287157","https://openalex.org/W3216659302","https://openalex.org/W4200631219","https://openalex.org/W4214601882","https://openalex.org/W4221166385","https://openalex.org/W4224301911","https://openalex.org/W4307074043","https://openalex.org/W4312259618","https://openalex.org/W4312509322","https://openalex.org/W4312682661","https://openalex.org/W4312738368","https://openalex.org/W4312936847","https://openalex.org/W4313046672","https://openalex.org/W4366457972","https://openalex.org/W4378170107","https://openalex.org/W4386047751","https://openalex.org/W4386047823","https://openalex.org/W4386066129","https://openalex.org/W4386066385","https://openalex.org/W4386066401","https://openalex.org/W4386071841","https://openalex.org/W4386075638","https://openalex.org/W4386075707","https://openalex.org/W4386075801","https://openalex.org/W4386075932","https://openalex.org/W4386076413","https://openalex.org/W4386083094","https://openalex.org/W4388067728","https://openalex.org/W4390872437","https://openalex.org/W4390873659","https://openalex.org/W6760045743","https://openalex.org/W6809959322","https://openalex.org/W6846257375","https://openalex.org/W6867072984"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Visual":[0],"interactivity":[1],"understanding":[2,65],"within":[3,51,66,127],"visual":[4,54,67],"scenes":[5],"presents":[6],"a":[7,21,30,88,104,112,122,128],"significant":[8],"challenge":[9],"in":[10,39,154],"computer":[11],"vision.":[12],"Existing":[13],"methods":[14,149],"focus":[15],"on":[16],"complex":[17,53],"interactivities":[18,64,76],"while":[19],"leveraging":[20],"simple":[22],"relationship":[23],"model.":[24],"These":[25],"methods,":[26],"however,":[27],"struggle":[28],"with":[29],"diversity":[31],"of":[32,56,100,107],"appearance,":[33],"situation,":[34],"position,":[35],"interaction,":[36],"and":[37,79,125],"relation":[38],"videos.":[40],"This":[41],"limitation":[42],"hinders":[43],"the":[44,49,52],"ability":[45],"to":[46,131,147],"fully":[47],"comprehend":[48],"interplay":[50],"dynamics":[55],"subjects.":[57],"In":[58],"this":[59,83],"paper,":[60],"we":[61,85,110],"delve":[62],"into":[63,135],"content":[68],"by":[69,103],"deriving":[70],"scene":[71,136],"graph":[72,126],"representations":[73],"from":[74],"dense":[75],"among":[77],"humans":[78],"objects.":[80],"To":[81],"achieve":[82],"goal,":[84],"first":[86],"present":[87],"new":[89,113],"dataset":[90],"containing":[91],"Appearance-Situation-Position-Interaction-Relation":[92],"predicates,":[93],"named":[94,115],"ASPIRe,":[95],"offering":[96],"an":[97],"extensive":[98,151],"collection":[99],"videos":[101],"marked":[102],"wide":[105],"range":[106],"interactivities.":[108],"Then,":[109],"propose":[111],"approach":[114,143],"Hierarchical":[116],"Interlacement":[117],"Graph":[118],"(HIG),":[119],"which":[120],"leverages":[121],"unified":[123],"layer":[124],"hierarchical":[129],"structure":[130],"provide":[132],"deep":[133],"insights":[134],"changes":[137],"across":[138],"five":[139],"distinct":[140],"tasks.":[141],"Our":[142],"demonstrates":[144],"superior":[145],"performance":[146],"other":[148],"through":[150],"experiments":[152],"conducted":[153],"various":[155],"scenarios.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}