{"id":"https://openalex.org/W4407185814","doi":"https://doi.org/10.1145/3708359.3712113","title":"EditIQ: Automated Cinematic Editing of Static Wide-Angle Videos via Dialogue Interpretation and Saliency Cues","display_name":"EditIQ: Automated Cinematic Editing of Static Wide-Angle Videos via Dialogue Interpretation and Saliency Cues","publication_year":2025,"publication_date":"2025-03-19","ids":{"openalex":"https://openalex.org/W4407185814","doi":"https://doi.org/10.1145/3708359.3712113"},"language":"en","primary_location":{"id":"doi:10.1145/3708359.3712113","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3708359.3712113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.02172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070477682","display_name":"Rohit Girmaji","orcid":"https://orcid.org/0009-0000-3361-5894"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rohit Girmaji","raw_affiliation_strings":["CVIT, International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India,"],"raw_orcid":"https://orcid.org/0009-0000-3361-5894","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India,","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116142049","display_name":"Bhav Beri","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bhav Beri","raw_affiliation_strings":["CVIT, International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India,"],"raw_orcid":"https://orcid.org/0009-0008-5064-8725","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India,","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089971631","display_name":"Ramanathan Subramanian","orcid":"https://orcid.org/0000-0001-9441-7074"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ramanathan Subramanian","raw_affiliation_strings":["University of Canberra, Canberra, ACT, Australia,"],"raw_orcid":"https://orcid.org/0000-0001-9441-7074","affiliations":[{"raw_affiliation_string":"University of Canberra, Canberra, ACT, Australia,","institution_ids":["https://openalex.org/I188329596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067298540","display_name":"Vineet Gandhi","orcid":"https://orcid.org/0000-0001-8861-7731"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vineet Gandhi","raw_affiliation_strings":["CVIT, International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India,"],"raw_orcid":"https://orcid.org/0000-0001-8861-7731","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India,","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070477682"],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":2.2665,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86086473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"609","last_page":"623"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9962000250816345,"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":0.9897000193595886,"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":0.8213258981704712},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7673944234848022},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.6013187766075134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.568047285079956},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.5277044177055359},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5203089714050293},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.49937009811401367},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48260247707366943},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4719257354736328},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4517858922481537},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4351390600204468},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4274151623249054},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4167449474334717},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.4148312509059906},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3483262062072754},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17818859219551086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213258981704712},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7673944234848022},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.6013187766075134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.568047285079956},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.5277044177055359},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5203089714050293},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.49937009811401367},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48260247707366943},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4719257354736328},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4517858922481537},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4351390600204468},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4274151623249054},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4167449474334717},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.4148312509059906},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3483262062072754},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17818859219551086},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3708359.3712113","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3708359.3712113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.02172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.02172","pdf_url":"https://arxiv.org/pdf/2502.02172","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.02172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.02172","pdf_url":"https://arxiv.org/pdf/2502.02172","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","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":55,"referenced_works":["https://openalex.org/W3906825","https://openalex.org/W181644151","https://openalex.org/W1974846296","https://openalex.org/W1980852932","https://openalex.org/W1996577481","https://openalex.org/W2000224299","https://openalex.org/W2012210378","https://openalex.org/W2021486453","https://openalex.org/W2025302737","https://openalex.org/W2038053759","https://openalex.org/W2048097911","https://openalex.org/W2054769378","https://openalex.org/W2068277723","https://openalex.org/W2074520446","https://openalex.org/W2113018061","https://openalex.org/W2213100575","https://openalex.org/W2249980490","https://openalex.org/W2271886155","https://openalex.org/W2294706300","https://openalex.org/W2325697621","https://openalex.org/W2400429454","https://openalex.org/W2604272474","https://openalex.org/W2618799552","https://openalex.org/W2738077708","https://openalex.org/W2799306936","https://openalex.org/W2807186921","https://openalex.org/W2883429621","https://openalex.org/W2955060956","https://openalex.org/W2963125010","https://openalex.org/W2963504571","https://openalex.org/W2963758538","https://openalex.org/W2986131415","https://openalex.org/W2990503944","https://openalex.org/W3030831740","https://openalex.org/W3034287518","https://openalex.org/W3100302033","https://openalex.org/W3138095408","https://openalex.org/W3149149291","https://openalex.org/W3173407577","https://openalex.org/W3206008172","https://openalex.org/W3211461682","https://openalex.org/W4232838367","https://openalex.org/W4241425637","https://openalex.org/W4376851255","https://openalex.org/W4385822293","https://openalex.org/W4386076204","https://openalex.org/W4386076558","https://openalex.org/W4387983481","https://openalex.org/W4390395706","https://openalex.org/W4392904756","https://openalex.org/W4394598041","https://openalex.org/W4398756379","https://openalex.org/W4402670448","https://openalex.org/W4402683943","https://openalex.org/W4404792998"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"We":[0,106],"present":[1,54],"EditIQ,":[2],"a":[3,13,32,75,79,146,159],"completely":[4],"automated":[5,47],"framework":[6],"for":[7],"cinematically":[8],"editing":[9,48,71,111],"scenes":[10],"captured":[11],"via":[12,158],"stationary,":[14],"large":[15,80],"field-of-view":[16],"and":[17,68,102,127,133,145],"high-resolution":[18],"camera.":[19],"From":[20],"the":[21,55,58,70,138,166],"static":[22],"camera":[23,38,103],"feed,":[24],"EditIQ":[25,129,152,179],"initially":[26],"generates":[27],"multiple":[28],"virtual":[29,37],"feeds,":[30],"emulating":[31],"team":[33],"of":[34,137,151],"cameramen.":[35],"These":[36],"shots":[39,104],"termed":[40],"rushes":[41],"are":[42],"subsequently":[43],"assembled":[44],"using":[45],"an":[46,113,131],"algorithm,":[49],"whose":[50],"objective":[51],"is":[52,156],"to":[53,87,97],"viewer":[56],"with":[57,92],"most":[59],"vivid":[60],"scene":[61,66,100],"content.":[62],"To":[63],"understand":[64],"key":[65],"elements":[67,101],"guide":[69],"process,":[72],"we":[73],"employ":[74],"two-pronged":[76],"approach:":[77],"(1)":[78],"language":[81],"model":[82],"(LLM)-based":[83],"dialogue":[84],"understanding":[85],"module":[86],"analyze":[88],"conversational":[89],"flow,":[90],"coupled":[91],"(2)":[93],"visual":[94],"saliency":[95],"prediction":[96],"identify":[98],"meaningful":[99],"therefrom.":[105],"then":[107],"formulate":[108],"cinematic":[109,121,143],"video":[110],"as":[112],"energy":[114],"minimization":[115],"problem":[116],"over":[117],"shot":[118,124],"selection,":[119],"where":[120],"constraints":[122],"determine":[123],"choices,":[125],"transitions,":[126],"continuity.":[128],"synthesizes":[130],"aesthetically":[132],"visually":[134],"compelling":[135],"representation":[136],"original":[139],"narrative":[140],"while":[141],"maintaining":[142],"coherence":[144],"smooth":[147],"viewing":[148],"experience.":[149],"Efficacy":[150],"against":[153],"competing":[154],"baselines":[155],"demonstrated":[157],"psychophysical":[160],"study":[161],"involving":[162],"twenty":[163],"participants":[164],"on":[165],"BBC":[167],"Old":[168],"School":[169],"dataset":[170],"plus":[171],"eleven":[172],"theatre":[173],"performance":[174],"videos.":[175],"Video":[176],"samples":[177],"from":[178],"can":[180],"be":[181],"found":[182],"at":[183],"https://editiq-ave.github.io/.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
