{"id":"https://openalex.org/W7125376029","doi":"https://doi.org/10.1007/978-981-95-5716-5_20","title":"Improve Visual Grounding with\u00a0Dynamic Gating and\u00a0Dual Stream Attention","display_name":"Improve Visual Grounding with\u00a0Dynamic Gating and\u00a0Dual Stream Attention","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125376029","doi":"https://doi.org/10.1007/978-981-95-5716-5_20"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-95-5716-5_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-5716-5_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5123548029","display_name":"Qianqian Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianqian Lin","raw_affiliation_strings":["Shenyang University of Technology, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Shenyang University of Technology, Shenyang, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123590666","display_name":"Xiaoxu Song","orcid":null},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoxu Song","raw_affiliation_strings":["Shenyang University of Technology, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Shenyang University of Technology, Shenyang, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123548618","display_name":"Jing Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Shan","raw_affiliation_strings":["Shenyang University of Technology, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Shenyang University of Technology, Shenyang, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123599666","display_name":"Jiaying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaying Wang","raw_affiliation_strings":["Shenyang University of Technology, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Shenyang University of Technology, Shenyang, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123616332","display_name":"Junyi Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123599","display_name":"Liaoning Jianzhu Vocational University","ror":"https://ror.org/03wtdg769","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210123599"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyi Jiang","raw_affiliation_strings":["Liaoning Vocational and Technical College of Economics, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Liaoning Vocational and Technical College of Economics, Shenyang, China","institution_ids":["https://openalex.org/I4210123599"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5123590666"],"corresponding_institution_ids":["https://openalex.org/I157507598"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51485536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"318","last_page":"332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8776000142097473,"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":0.8776000142097473,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.029200000688433647,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.02319999970495701,"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/encoder","display_name":"Encoder","score":0.5231000185012817},{"id":"https://openalex.org/keywords/visual-objects","display_name":"Visual Objects","score":0.4503999948501587},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.42910000681877136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42010000348091125},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.41110000014305115},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4041000008583069},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38960000872612},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.38940000534057617},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3650999963283539},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.35989999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.901199996471405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6420000195503235},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5231000185012817},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.4503999948501587},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4205000102519989},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.35989999771118164},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31610000133514404},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.3061000108718872},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C27362006","wikidata":"https://www.wikidata.org/wiki/Q272021","display_name":"Gestalt psychology","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2779668609","wikidata":"https://www.wikidata.org/wiki/Q623092","display_name":"Rapid serial visual presentation","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-95-5716-5_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-5716-5_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2770129969","https://openalex.org/W2799263800","https://openalex.org/W2904910963","https://openalex.org/W2946086442","https://openalex.org/W2963109634","https://openalex.org/W2964345792","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W3034772468","https://openalex.org/W3096609285","https://openalex.org/W3110435696","https://openalex.org/W3112077297","https://openalex.org/W3138516171","https://openalex.org/W3163747765","https://openalex.org/W3174965650","https://openalex.org/W3203354307","https://openalex.org/W4200631575","https://openalex.org/W4206706211","https://openalex.org/W4214490042","https://openalex.org/W4312956471","https://openalex.org/W4382458695","https://openalex.org/W4386066126","https://openalex.org/W4386076636","https://openalex.org/W4387986753","https://openalex.org/W4393145564","https://openalex.org/W4402706555","https://openalex.org/W4402979572"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-01-24T23:23:39.755997","created_date":"2026-01-23T00:00:00"}