{"id":"https://openalex.org/W4417073151","doi":"https://doi.org/10.1145/3743093.3771066","title":"Time-IC: Empowering MLLM with Interleaved Context for Temporal-Sensitive Video Understanding","display_name":"Time-IC: Empowering MLLM with Interleaved Context for Temporal-Sensitive Video Understanding","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073151","doi":"https://doi.org/10.1145/3743093.3771066"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771066","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3771066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","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/A5083717898","display_name":"Henghao Zhao","orcid":"https://orcid.org/0000-0002-0970-021X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Henghao Zhao","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029702480","display_name":"Peng Huang","orcid":"https://orcid.org/0009-0003-4102-6506"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Huang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716371","display_name":"Rui Yan","orcid":"https://orcid.org/0000-0002-0694-9458"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yan","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017096005","display_name":"Zechao Li","orcid":"https://orcid.org/0000-0002-5341-5985"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zechao Li","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083717898"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4021941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9787999987602234,"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":0.9787999987602234,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.004000000189989805,"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":0.002400000113993883,"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":0.6841999888420105},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6565999984741211},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6256999969482422},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6126999855041504},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5916000008583069},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5644000172615051},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5514000058174133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847000002861023},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.6841999888420105},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6565999984741211},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6256999969482422},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6126999855041504},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5916000008583069},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5514000058174133},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4603999853134155},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4178999960422516},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41040000319480896},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3492000102996826},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2655999958515167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3771066","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3771066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W329267344","https://openalex.org/W2952132648","https://openalex.org/W2962799512","https://openalex.org/W2963351113","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W3025796084","https://openalex.org/W3035339529","https://openalex.org/W3104862079","https://openalex.org/W3174257385","https://openalex.org/W3207454933","https://openalex.org/W4214663214","https://openalex.org/W4306913475","https://openalex.org/W4312544061","https://openalex.org/W4386066385","https://openalex.org/W4386083094","https://openalex.org/W4390873341","https://openalex.org/W4390873423","https://openalex.org/W4390874338","https://openalex.org/W4393853176","https://openalex.org/W4402671548","https://openalex.org/W4402702917","https://openalex.org/W4402702962","https://openalex.org/W4402726946","https://openalex.org/W4402727142","https://openalex.org/W4402727272","https://openalex.org/W4402727693","https://openalex.org/W4402754238","https://openalex.org/W4404781975","https://openalex.org/W4404783405","https://openalex.org/W4404784276"],"related_works":[],"abstract_inverted_index":{"Temporal-sensitive":[0],"video":[1,6,57,90,131],"tasks,":[2],"such":[3],"as":[4],"dense":[5],"captioning,":[7,132],"require":[8],"models":[9],"to":[10,25,109],"describe":[11],"event":[12],"content":[13],"in":[14,42],"detail":[15],"and":[16,39,71,81,92,113,140],"generate":[17,114],"timestamps":[18],"marking":[19],"their":[20],"occurrence.":[21],"Existing":[22],"approaches":[23],"tend":[24],"over-rely":[26],"on":[27,122],"visuals":[28],"while":[29],"neglecting":[30],"the":[31,107,138,143],"role":[32],"of":[33,142],"rich":[34],"contexts,":[35],"limiting":[36],"temporal":[37,133],"reasoning":[38],"semantic":[40,79,83],"comprehension":[41],"videos.":[43],"To":[44],"this":[45,104],"end,":[46],"we":[47],"propose":[48],"Time-IC,":[49],"a":[50,96],"multimodal":[51],"large":[52],"language":[53],"model":[54,108],"that":[55],"incorporates":[56],"context":[58,67,73],"for":[59],"improved":[60],"understanding.":[61],"Specifically,":[62],"Time-IC":[63],"integrates":[64],"both":[65],"internal":[66],"(timestamps,":[68],"speech":[69],"transcripts)":[70],"external":[72],"(titles,":[74],"author":[75],"descriptions),":[76],"providing":[77],"complementary":[78],"cues":[80],"high-level":[82],"priors.":[84],"More":[85],"importantly,":[86],"it":[87],"unifies":[88],"context,":[89],"frames,":[91],"task":[93],"instructions":[94],"into":[95],"temporally":[97],"aligned,":[98],"interleaved":[99],"sequence.":[100],"With":[101],"instruction":[102],"tuning,":[103],"design":[105],"enables":[106],"associate":[110],"contextual":[111],"elements":[112],"comprehensive":[115],"responses":[116],"across":[117,127],"diverse":[118],"tasks.":[119],"Extensive":[120],"experiments":[121],"widely-used":[123],"benchmarks":[124],"(YouCookII,":[125],"QVHighlights)":[126],"three":[128],"tasks":[129],"(dense":[130],"grounding,":[134],"highlight":[135],"detection)":[136],"demonstrate":[137],"effectiveness":[139],"flexibility":[141],"proposed":[144],"Time-IC.":[145]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-06T00:00:00"}