{"id":"https://openalex.org/W4415707685","doi":"https://doi.org/10.1109/icme59968.2025.11209055","title":"Self-ReS: Self-Reflection in Large Vision-Language Models for Long Video Understanding","display_name":"Self-ReS: Self-Reflection in Large Vision-Language Models for Long Video Understanding","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707685","doi":"https://doi.org/10.1109/icme59968.2025.11209055"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5012600407","display_name":"Jo\u00e3o Pereira","orcid":"https://orcid.org/0000-0002-8120-7649"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Pereira","raw_affiliation_strings":["NOVA@FCT,NOVA LINCS,Caparica,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA@FCT,NOVA LINCS,Caparica,Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037622759","display_name":"Vasco Lopes","orcid":"https://orcid.org/0000-0002-5577-1094"},"institutions":[{"id":"https://openalex.org/I2802870671","display_name":"Energias de Portugal (Portugal)","ror":"https://ror.org/00praab34","country_code":"PT","type":"company","lineage":["https://openalex.org/I2802870671"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Vasco Lopes","raw_affiliation_strings":["DeepNeuronic,Covilhã,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepNeuronic,Covilhã,Portugal","institution_ids":["https://openalex.org/I2802870671"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044625394","display_name":"David Semedo","orcid":"https://orcid.org/0000-0002-2403-0058"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"David Semedo","raw_affiliation_strings":["NOVA@FCT,NOVA LINCS,Caparica,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA@FCT,NOVA LINCS,Caparica,Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002088416","display_name":"Jo\u00e3o C. Neves","orcid":"https://orcid.org/0000-0003-0139-2213"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Neves","raw_affiliation_strings":["University of Beira Interior,NOVA LINCS,Covilhã,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Beira Interior,NOVA LINCS,Covilhã,Portugal","institution_ids":["https://openalex.org/I161321875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.26970352,"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":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8571000099182129,"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":0.8571000099182129,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03830000013113022,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03779999911785126,"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/key","display_name":"Key (lock)","score":0.65829998254776},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6182000041007996},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5814999938011169},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.510200023651123},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.49000000953674316},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.45210000872612},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.43810001015663147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194000124931335},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.65829998254776},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6182000041007996},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.510200023651123},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4745999872684479},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.45210000872612},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.38370001316070557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3776000142097473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37059998512268066},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.36910000443458557},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3603000044822693},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3474999964237213},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":11,"referenced_works":["https://openalex.org/W2979826702","https://openalex.org/W4390873312","https://openalex.org/W4402669747","https://openalex.org/W4402671548","https://openalex.org/W4402702917","https://openalex.org/W4402754220","https://openalex.org/W4403002096","https://openalex.org/W4403939369","https://openalex.org/W4413146669","https://openalex.org/W4413147769","https://openalex.org/W4413156662"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"demonstrate":[4,111],"remarkable":[5],"performance":[6],"in":[7,17,39,48,58],"short-video":[8],"tasks":[9],"such":[10],"as":[11],"video":[12,40,77],"question":[13],"answering,":[14],"but":[15],"struggle":[16],"long-video":[18,123],"understanding.":[19],"The":[20,140],"linear":[21],"frame":[22],"sampling":[23,71],"strategy,":[24],"conventionally":[25],"used":[26],"by":[27],"LVLMs,":[28,121],"fails":[29],"to":[30,95,129],"account":[31],"for":[32],"the":[33,53,88,135],"non-linear":[34,68],"distribution":[35],"of":[36,55,93],"key":[37,76],"events":[38,57],"data,":[41],"often":[42],"introducing":[43],"redundant":[44],"or":[45,107],"irrelevant":[46],"information":[47],"longer":[49],"contexts":[50],"while":[51],"risking":[52],"omission":[54],"critical":[56],"shorter":[59],"ones.":[60],"To":[61],"address":[62],"this,":[63],"we":[64],"propose":[65],"Self-ReS,":[66],"a":[67],"spatiotemporal":[69],"self-reflective":[70],"method":[72],"that":[73,112],"dynamically":[74],"selects":[75],"fragments":[78],"based":[79],"on":[80],"user":[81],"prompts.":[82],"Unlike":[83],"prior":[84],"approaches,":[85],"Self-ReS":[86,113],"leverages":[87],"inherently":[89],"sparse":[90],"attention":[91],"maps":[92],"LVLMs":[94],"define":[96],"reflection":[97],"tokens,":[98],"enabling":[99],"relevance-aware":[100],"token":[101],"selection":[102],"without":[103],"requiring":[104],"additional":[105],"training":[106],"external":[108],"modules.":[109],"Experiments":[110],"can":[114,142],"be":[115,143],"seamlessly":[116],"integrated":[117],"into":[118],"strong":[119],"base":[120],"improving":[122],"task":[124],"accuracy":[125],"and":[126],"achieving":[127],"up":[128],"46%":[130],"faster":[131],"inference":[132],"speed":[133],"within":[134],"same":[136],"GPU":[137],"memory":[138],"budget.":[139],"code":[141],"found":[144],"here:":[145],"https://github.com/jaca-pereira/Self-ReS.":[146]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}