{"id":"https://openalex.org/W4417099862","doi":"https://doi.org/10.1109/iccv51701.2025.02251","title":"Timeexpert: an Expert-Guided Video Llm for Video Temporal Grounding","display_name":"Timeexpert: an Expert-Guided Video Llm for Video Temporal Grounding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417099862","doi":"https://doi.org/10.1109/iccv51701.2025.02251"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.01699","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088457247","display_name":"Zuhao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zuhao Yang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090126397","display_name":"Yingchen Yu","orcid":"https://orcid.org/0000-0002-7893-0764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingchen Yu","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060204146","display_name":"Yunqing Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunqing Zhao","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023507910","display_name":"Shijian Lu","orcid":"https://orcid.org/0000-0002-6766-2506"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shijian Lu","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101562162","display_name":"Song Bai","orcid":"https://orcid.org/0000-0002-2570-9118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Bai","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45052749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24286","last_page":"24296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9726999998092651,"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":0.9726999998092651,"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":0.007699999958276749,"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":0.004600000102072954,"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/task","display_name":"Task (project management)","score":0.6553000211715698},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6141999959945679},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5823000073432922},{"id":"https://openalex.org/keywords/unexpected-events","display_name":"Unexpected events","score":0.31769999861717224},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.31619998812675476},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3021000027656555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137999773025513},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6553000211715698},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6141999959945679},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5594000220298767},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4041000008583069},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3021000027656555},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2524999976158142},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.251800000667572},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.01699","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01699","pdf_url":"https://arxiv.org/pdf/2508.01699","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.01699","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.01699","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.01699","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01699","pdf_url":"https://arxiv.org/pdf/2508.01699","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0,45,143,148],"Temporal":[1],"Grounding":[2],"(VTG)":[3],"aims":[4],"to":[5,13,61,102,119],"precisely":[6],"identify":[7],"video":[8],"event":[9,121],"segments":[10],"in":[11,43],"response":[12],"textual":[14,34,69],"queries.":[15],"The":[16],"outputs":[17],"of":[18,24,115],"VTG":[19,91,125,138],"tasks":[20,74,92,139],"manifest":[21],"as":[22,141],"sequences":[23],"events,":[25],"each":[26,116],"defined":[27],"by":[28,93],"precise":[29,113],"timestamps,":[30,99],"saliency":[31,66,100],"scores,":[32],"and":[33,57,68,147],"descriptions.":[35],"Despite":[36],"recent":[37],"advances,":[38],"a":[39,84],"fundamental":[40],"limitation":[41],"persists":[42],"existing":[44],"Large":[46],"Language":[47],"Models":[48],"(Video-LLMs):":[49],"they":[50],"process":[51],"all":[52],"task":[53],"tokens":[54,97],"through":[55],"identical":[56],"static":[58],"pathways,":[59],"failing":[60],"recognize":[62],"that":[63,88,130],"temporal":[64],"localization,":[65],"assessment,":[67],"generation":[70],"represent":[71],"fundamentally":[72],"distinct":[73],"requiring":[75],"specialized":[76,103],"processing.":[77],"To":[78],"address":[79],"this,":[80],"we":[81],"introduce":[82],"TimeExpert,":[83],"Mixture-of-Experts":[85],"(MoE)-based":[86],"Video-LLM":[87],"effectively":[89],"decomposes":[90],"dynamically":[94],"routing":[95],"task-specific":[96],"(e.g.,":[98],"scores)":[101],"experts,":[104],"with":[105],"increased":[106],"computational":[107],"efficiency.":[108],"Our":[109],"design":[110],"choices":[111],"enable":[112],"handling":[114],"subtask,":[117],"leading":[118],"improved":[120],"modeling":[122],"across":[123],"diverse":[124],"applications.":[126],"Extensive":[127],"experiments":[128],"demonstrate":[129],"TimeExpert":[131],"consistently":[132],"achieves":[133],"state-of-the-art":[134],"performance":[135],"on":[136],"various":[137],"such":[140],"Dense":[142],"Captioning,":[144],"Moment":[145],"Retrieval,":[146],"Highlight":[149],"Detection.":[150]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}