{"id":"https://openalex.org/W4412889823","doi":"https://doi.org/10.18653/v1/2025.acl-long.1347","title":"Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains","display_name":"Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889823","doi":"https://doi.org/10.18653/v1/2025.acl-long.1347"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1347","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1347","pdf_url":"https://aclanthology.org/2025.acl-long.1347.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1347.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088517105","display_name":"Juntian Zhang","orcid":"https://orcid.org/0000-0003-3793-714X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juntian Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069312764","display_name":"Chuanqi Cheng","orcid":"https://orcid.org/0000-0002-3366-8395"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuanqi Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350532","display_name":"Yuhan Liu","orcid":"https://orcid.org/0000-0003-2912-750X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109602711","display_name":"Wei Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102950341","display_name":"Jing Luan","orcid":"https://orcid.org/0000-0003-2234-2426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Luan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046836420","display_name":"Rui Yan","orcid":"https://orcid.org/0000-0003-0048-3092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27782","last_page":"27798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7548999786376953,"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":0.7548999786376953,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.6972000002861023,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13071","display_name":"Digital Storytelling and Education","score":0.6672999858856201,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/weaving","display_name":"Weaving","score":0.8146334290504456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7331511974334717},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6858925223350525},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6177605986595154},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.46718886494636536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4487329423427582},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4215444028377533},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40581777691841125},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.13022750616073608},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09360954165458679},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06090924143791199}],"concepts":[{"id":"https://openalex.org/C54525549","wikidata":"https://www.wikidata.org/wiki/Q2553445","display_name":"Weaving","level":2,"score":0.8146334290504456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7331511974334717},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6858925223350525},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6177605986595154},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.46718886494636536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4487329423427582},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4215444028377533},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40581777691841125},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.13022750616073608},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09360954165458679},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06090924143791199},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1347","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1347","pdf_url":"https://aclanthology.org/2025.acl-long.1347.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1347","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1347","pdf_url":"https://aclanthology.org/2025.acl-long.1347.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318846","display_name":"Yuhan","ror":"https://ror.org/00bv1jr75"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889823.pdf","grobid_xml":"https://content.openalex.org/works/W4412889823.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2952092742","https://openalex.org/W2068981955","https://openalex.org/W67774003","https://openalex.org/W2368396969","https://openalex.org/W4231951841","https://openalex.org/W2027559301","https://openalex.org/W2188987414","https://openalex.org/W2365680989","https://openalex.org/W153134268","https://openalex.org/W2141293686"],"abstract_inverted_index":{"Vision-language":[0],"models":[1,23],"(VLMs)":[2],"achieve":[3],"remarkable":[4],"success":[5],"in":[6,52,86],"single-image":[7],"tasks.However,":[8],"real-world":[9],"scenarios":[10],"often":[11],"involve":[12],"intricate":[13],"multi-image":[14,53,96,101],"inputs,":[15],"leading":[16],"to":[17,25],"a":[18,41,63,80,128],"notable":[19],"performance":[20,109],"decline":[21],"as":[22],"struggle":[24],"disentangle":[26],"critical":[27],"information":[28],"scattered":[29],"across":[30,115],"complex":[31,141],"visual":[32,142],"features.In":[33],"this":[34,56,75],"work,":[35],"we":[36,58],"propose":[37,59],"Focus-Centric":[38,60,90],"Visual":[39,91],"Chain,":[40,92],"novel":[42],"paradigm":[43],"that":[44,104,138],"enhances":[45],"VLMs'":[46],"perception,":[47],"comprehension,":[48],"and":[49,113,134],"reasoning":[50,73,84],"abilities":[51],"scenarios.To":[54],"facilitate":[55],"paradigm,":[57],"Data":[61],"Synthesis,":[62],"scalable":[64],"bottom-up":[65],"approach":[66],"for":[67,95],"synthesizing":[68],"high-quality":[69],"data":[70,85],"with":[71,83],"elaborate":[72],"paths.Through":[74],"approach,":[76],"We":[77],"construct":[78],"VISC-150K,":[79],"large-scale":[81],"dataset":[82],"the":[87,122],"form":[88],"of":[89,111],"specifically":[93],"designed":[94],"tasks.Experimental":[97],"results":[98],"on":[99],"seven":[100],"benchmarks":[102],"demonstrate":[103],"our":[105],"method":[106],"achieves":[107],"average":[108],"gains":[110],"3.16%":[112],"2.24%":[114],"two":[116],"distinct":[117],"model":[118],"architectures,":[119],"without":[120],"compromising":[121],"general":[123],"vision-language":[124,136],"capabilities.Our":[125],"study":[126],"represents":[127],"significant":[129],"step":[130],"toward":[131],"more":[132],"robust":[133],"capable":[135],"systems":[137],"can":[139],"handle":[140],"scenarios:":[143],"VISC.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}