{"id":"https://openalex.org/W4415708458","doi":"https://doi.org/10.1109/icme59968.2025.11210151","title":"GiVE: Guiding Visual Encoder to Perceive Overlooked Information","display_name":"GiVE: Guiding Visual Encoder to Perceive Overlooked Information","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708458","doi":"https://doi.org/10.1109/icme59968.2025.11210151"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210151","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/A5100367638","display_name":"Junjie Li","orcid":"https://orcid.org/0000-0001-7973-0310"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junjie Li","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049838944","display_name":"Jianghong Ma","orcid":"https://orcid.org/0000-0002-0524-3584"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianghong Ma","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455661","display_name":"Xiaofeng Zhang","orcid":"https://orcid.org/0000-0002-2780-9315"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Zhang","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443272","display_name":"Yuhang Li","orcid":"https://orcid.org/0000-0002-3273-5218"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Li","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101997806","display_name":"Jianyang Shi","orcid":"https://orcid.org/0000-0002-9151-6058"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyang Shi","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100367638"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31088451,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.975600004196167,"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":0.975600004196167,"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":0.004600000102072954,"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/T10028","display_name":"Topic Modeling","score":0.00430000014603138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7279999852180481},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5268999934196472},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4569000005722046},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4535999894142151},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4514999985694885},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.40139999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875000238418579},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7279999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6359999775886536},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5268999934196472},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4668000042438507},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4514999985694885},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.40139999985694885},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3684000074863434},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.32179999351501465},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210151","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2017814585","https://openalex.org/W2277195237","https://openalex.org/W2948672349","https://openalex.org/W2979382951","https://openalex.org/W4307844773","https://openalex.org/W4312933868","https://openalex.org/W4312980231","https://openalex.org/W4386071957","https://openalex.org/W4386952103","https://openalex.org/W4387967975","https://openalex.org/W4390873312","https://openalex.org/W4404356490","https://openalex.org/W4408287837","https://openalex.org/W4410659598"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"have":[4],"advanced":[5],"AI":[6],"in":[7],"applications":[8],"like":[9],"text-to-video":[10],"generation":[11],"and":[12,61,84,95,111],"visual":[13,20,53,101],"question":[14],"answering.":[15],"These":[16,68],"models":[17],"rely":[18],"on":[19],"encoders":[21,30],"to":[22,45,107],"convert":[23],"non-text":[24],"data":[25],"into":[26],"vectors,":[27],"but":[28],"current":[29],"either":[31],"lack":[32],"semantic":[33],"alignment":[34],"or":[35],"overlook":[36],"non-salient":[37],"objects.":[38],"We":[39],"propose":[40],"the":[41,112],"Guiding":[42],"Visual":[43,64],"Encoder":[44],"Perceive":[46],"Overlooked":[47],"Information":[48],"(GiVE)":[49],"approach.":[50],"GiVE":[51],"enhances":[52],"representation":[54],"with":[55],"an":[56,62],"Attention-Guided":[57],"Adapter":[58],"(AG-Adapter)":[59],"module":[60],"Object-focused":[63,74,79,85],"Semantic":[65],"Learning":[66],"module.":[67],"incorporate":[69],"three":[70],"novel":[71,104],"loss":[72,105],"terms:":[73],"Image-Text":[75],"Contrast":[76,81],"(OITC)":[77],"loss,":[78,83,89],"Image-Image":[80],"(OIIC)":[82],"Image":[86],"Discrimination":[87],"(OID)":[88],"improving":[90],"object":[91,109],"consideration,":[92],"retrieval":[93],"accuracy,":[94],"comprehensiveness.":[96],"Our":[97],"contributions":[98],"include":[99],"dynamic":[100],"focus":[102],"adjustment,":[103],"functions":[106],"enhance":[108],"retrieval,":[110],"Multi-Object":[113],"Instruction":[114],"(MOInst)":[115],"dataset.":[116],"Experiments":[117],"show":[118],"our":[119],"approach":[120],"achieves":[121],"state-of-the-art":[122],"performance.":[123]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}