{"id":"https://openalex.org/W7131070082","doi":"https://doi.org/10.1109/iccvw69036.2025.00505","title":"Human-Inspired Summarization: Cluster Scene Videos into Diverse Frames","display_name":"Human-Inspired Summarization: Cluster Scene Videos into Diverse Frames","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131070082","doi":"https://doi.org/10.1109/iccvw69036.2025.00505"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00505","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 Workshops (ICCVW)","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/A5126624670","display_name":"Chao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chao Chen","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126623244","display_name":"Mingzhi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingzhi Zhu","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024767651","display_name":"Ankush Pratap Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankush Pratap Singh","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126605439","display_name":"Yu Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Yan","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034751153","display_name":"Felix Juefei-Xu","orcid":"https://orcid.org/0000-0002-0857-8611"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Juefei-Xu","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126602784","display_name":"Chen Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Feng","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5126624670"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74612582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4872","last_page":"4882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.15060000121593475,"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":0.15060000121593475,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.1145000010728836,"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/T10799","display_name":"Data Visualization and Analytics","score":0.0763000026345253,"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/automatic-summarization","display_name":"Automatic summarization","score":0.714900016784668},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5877000093460083},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5687999725341797},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5224999785423279},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5182999968528748},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38019999861717224},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.35260000824928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252000212669373},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.714900016784668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6707000136375427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5877000093460083},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5687999725341797},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5534999966621399},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5182999968528748},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2856000065803528}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00505","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 Workshops (ICCVW)","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":48,"referenced_works":["https://openalex.org/W1966872876","https://openalex.org/W1987366351","https://openalex.org/W1989863986","https://openalex.org/W2005854391","https://openalex.org/W2024501163","https://openalex.org/W2028613966","https://openalex.org/W2088252378","https://openalex.org/W2115579991","https://openalex.org/W2134577448","https://openalex.org/W2151385494","https://openalex.org/W2194345886","https://openalex.org/W2216883103","https://openalex.org/W2402341335","https://openalex.org/W2516142572","https://openalex.org/W2737677090","https://openalex.org/W2753434909","https://openalex.org/W2781922022","https://openalex.org/W2798970487","https://openalex.org/W2804318406","https://openalex.org/W2892074118","https://openalex.org/W2902616437","https://openalex.org/W2903758693","https://openalex.org/W2908469318","https://openalex.org/W2919365148","https://openalex.org/W2951019013","https://openalex.org/W2953127211","https://openalex.org/W2963026017","https://openalex.org/W2963558761","https://openalex.org/W2963919999","https://openalex.org/W2964167369","https://openalex.org/W2971202647","https://openalex.org/W2982672255","https://openalex.org/W2987654501","https://openalex.org/W2993980108","https://openalex.org/W3027431227","https://openalex.org/W3035524453","https://openalex.org/W3090254005","https://openalex.org/W3099156605","https://openalex.org/W3108154605","https://openalex.org/W3130420927","https://openalex.org/W3137393880","https://openalex.org/W3173736705","https://openalex.org/W3184847191","https://openalex.org/W3203187896","https://openalex.org/W4283363598","https://openalex.org/W4312748990","https://openalex.org/W4319300119","https://openalex.org/W4386076282"],"related_works":[],"abstract_inverted_index":{"Humans":[0],"are":[1,123],"remarkably":[2],"efficient":[3],"at":[4],"forming":[5],"spatial":[6,33,62,76,85,108],"understanding":[7],"from":[8,87,114],"just":[9],"a":[10,25,52,93,125],"few":[11],"visual":[12,103],"observations.":[13],"When":[14,120],"browsing":[15],"real":[16,136],"estate":[17],"or":[18],"navigating":[19],"unfamiliar":[20],"spaces,":[21],"they":[22],"intuitively":[23],"select":[24],"small":[26],"set":[27,54],"of":[28,45,55],"views":[29],"that":[30,59,97,142],"summarize":[31],"the":[32,43],"layout.":[34],"Inspired":[35],"by":[36],"this":[37],"ability,":[38],"we":[39],"introduce":[40],"scene":[41,49],"summarization,":[42],"task":[44],"condensing":[46],"long,":[47],"continuous":[48],"videos":[50],"into":[51],"compact":[53],"spatially":[56,146],"diverse":[57],"keyframes":[58,113],"facilitate":[60],"global":[61],"reasoning.":[63],"Unlike":[64],"conventional":[65],"video":[66,100,152],"summarization-which":[67],"focuses":[68],"on":[69,135],"user-edited,":[70],"fragmented":[71],"clips":[72],"and":[73,132,137,149],"often":[74],"ignores":[75],"continuity-our":[77],"goal":[78],"is":[79],"to":[80,106],"mimic":[81],"how":[82],"humans":[83],"abstract":[84],"layout":[86],"sparse":[88],"views.":[89],"We":[90],"propose":[91],"SceneSum,":[92],"two-stage":[94],"self-supervised":[95],"pipeline":[96],"first":[98],"clusters":[99],"frames":[101],"using":[102],"place":[104],"recognition":[105],"promote":[107],"diversity,":[109],"then":[110],"selects":[111],"representative":[112],"each":[115],"cluster":[116],"under":[117],"resource":[118],"constraints.":[119],"camera":[121],"trajectories":[122],"available,":[124],"lightweight":[126],"supervised":[127],"loss":[128],"further":[129],"refines":[130],"clustering":[131],"selection.":[133],"Experiments":[134],"simulated":[138],"indoor":[139],"datasets":[140],"show":[141],"SceneSum":[143],"produces":[144],"more":[145],"informative":[147],"summaries":[148],"outperforms":[150],"existing":[151],"summarization":[153],"baselines.":[154]},"counts_by_year":[],"updated_date":"2026-02-25T06:17:34.324206","created_date":"2026-02-24T00:00:00"}