{"id":"https://openalex.org/W4409360981","doi":"https://doi.org/10.1609/aaai.v39i28.35248","title":"Leveraging Textual Memory and Key Frame Reasoning for Full Video Understanding Using Off-the-Shelf LLMs and VLMs (Student Abstract)","display_name":"Leveraging Textual Memory and Key Frame Reasoning for Full Video Understanding Using Off-the-Shelf LLMs and VLMs (Student Abstract)","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409360981","doi":"https://doi.org/10.1609/aaai.v39i28.35248"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i28.35248","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i28.35248","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/35248/37403","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/35248/37403","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112390894","display_name":"H. Dubey","orcid":null},"institutions":[{"id":"https://openalex.org/I177156846","display_name":"South Dakota State University","ror":"https://ror.org/015jmes13","country_code":"US","type":"education","lineage":["https://openalex.org/I177156846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harsh Dubey","raw_affiliation_strings":["South Dakota State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South Dakota State University","institution_ids":["https://openalex.org/I177156846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061711551","display_name":"Chulwoo Pack","orcid":"https://orcid.org/0000-0002-9876-4388"},"institutions":[{"id":"https://openalex.org/I177156846","display_name":"South Dakota State University","ror":"https://ror.org/015jmes13","country_code":"US","type":"education","lineage":["https://openalex.org/I177156846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chulwoo Pack","raw_affiliation_strings":["South Dakota State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South Dakota State University","institution_ids":["https://openalex.org/I177156846"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177156846"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05128205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"28","first_page":"29351","last_page":"29352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9811999797821045,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9811999797821045,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9710000157356262,"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/T10028","display_name":"Topic Modeling","score":0.9652000069618225,"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/key","display_name":"Key (lock)","score":0.8041024804115295},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6767442226409912},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5209535360336304},{"id":"https://openalex.org/keywords/off-the-shelf","display_name":"Off the shelf","score":0.5006332397460938},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.46957844495773315},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3721666634082794},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08778861165046692},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07385051250457764},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.06689238548278809}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.8041024804115295},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6767442226409912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5209535360336304},{"id":"https://openalex.org/C2982819384","wikidata":"https://www.wikidata.org/wiki/Q7078910","display_name":"Off the shelf","level":2,"score":0.5006332397460938},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.46957844495773315},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3721666634082794},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08778861165046692},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07385051250457764},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.06689238548278809}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v39i28.35248","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i28.35248","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/35248/37403","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i28.35248","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i28.35248","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/35248/37403","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409360981.pdf","grobid_xml":"https://content.openalex.org/works/W4409360981.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2810201907","https://openalex.org/W1614340030","https://openalex.org/W2386640596","https://openalex.org/W2103803681","https://openalex.org/W2356908413","https://openalex.org/W2036745083","https://openalex.org/W2394559091","https://openalex.org/W2557342721","https://openalex.org/W855007925","https://openalex.org/W2349938628"],"abstract_inverted_index":{"To":[0],"address":[1],"the":[2,85],"limitations":[3],"of":[4,82],"current":[5],"Large-scale":[6],"Video-Language":[7],"Models":[8],"(LVLMs)":[9],"in":[10],"fine-grained":[11,102],"understanding":[12,22],"and":[13,31,45,65,71,96],"long-term":[14],"temporal":[15],"memory,":[16],"we":[17,50],"propose":[18],"a":[19,26,32,38,52,79,99],"novel":[20,53],"video":[21],"approach":[23,74],"that":[24],"integrates":[25],"Vision":[27],"Language":[28,34],"Model":[29,35],"(VLM)":[30],"Large":[33],"(LLM)":[36],"with":[37,98],"textual":[39],"memory":[40],"mechanism":[41],"to":[42,61],"ensure":[43],"continuity":[44],"contextual":[46],"coherence.":[47],"In":[48],"addition,":[49],"introduce":[51],"evaluation":[54],"metric,":[55],"VAD-Score":[56],"(Video":[57],"Automated":[58],"Description":[59],"Score),":[60],"assess":[62],"precision,":[63],"recall,":[64],"F1":[66],"scores":[67],"for":[68],"events,":[69],"subjects,":[70],"objects.":[72],"Our":[73],"delivers":[75],"competitive":[76],"results":[77],"on":[78,101],"diverse":[80],"set":[81],"videos":[83],"from":[84],"DREAM-1K":[86],"dataset,":[87],"spanning":[88],"categories":[89],"such":[90],"as":[91],"live-action,":[92],"animation,":[93],"shorts,":[94],"stock,":[95],"YouTube,":[97],"focus":[100],"comprehension.":[103]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}