{"id":"https://openalex.org/W7131274593","doi":"https://doi.org/10.1109/vcip67698.2025.11396791","title":"Parameter-Efficient Cross-Layer Feature Fusion via Chebyshev Polynomial Unit","display_name":"Parameter-Efficient Cross-Layer Feature Fusion via Chebyshev Polynomial Unit","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7131274593","doi":"https://doi.org/10.1109/vcip67698.2025.11396791"},"language":null,"primary_location":{"id":"doi:10.1109/vcip67698.2025.11396791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5126713937","display_name":"Yue Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Xin","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101603527","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0003-3064-7625"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarui Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073652872","display_name":"Ziyang Zheng","orcid":"https://orcid.org/0000-0001-9923-8016"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049554440","display_name":"Yaoming Wang","orcid":"https://orcid.org/0000-0002-0026-4247"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoming Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126709685","display_name":"Wenrui Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Dai","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007581833","display_name":"Chang Li","orcid":"https://orcid.org/0000-0002-3267-1859"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglin Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121765747","display_name":"Junni Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junni Zou","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002494284","display_name":"Hongkai Xiong","orcid":"https://orcid.org/0000-0003-4552-0029"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongkai Xiong","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.23160000145435333,"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/T10057","display_name":"Face and Expression Recognition","score":0.23160000145435333,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.09679999947547913,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.051500000059604645,"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/chebyshev-polynomials","display_name":"Chebyshev polynomials","score":0.5738000273704529},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5414999723434448},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5393000245094299},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.5203999876976013},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.49869999289512634},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4115999937057495},{"id":"https://openalex.org/keywords/fusion-rules","display_name":"Fusion rules","score":0.40790000557899475},{"id":"https://openalex.org/keywords/chebyshev-filter","display_name":"Chebyshev filter","score":0.37959998846054077}],"concepts":[{"id":"https://openalex.org/C129785596","wikidata":"https://www.wikidata.org/wiki/Q619511","display_name":"Chebyshev polynomials","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5414999723434448},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5393000245094299},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5202999711036682},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.49869999289512634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4643999934196472},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C2778971668","wikidata":"https://www.wikidata.org/wiki/Q5510284","display_name":"Fusion rules","level":4,"score":0.40790000557899475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.391400009393692},{"id":"https://openalex.org/C21424316","wikidata":"https://www.wikidata.org/wiki/Q718621","display_name":"Chebyshev filter","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3513000011444092},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2549000084400177},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip67698.2025.11396791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2163922914","https://openalex.org/W2194775991","https://openalex.org/W2752782242","https://openalex.org/W2804047627","https://openalex.org/W2892221324","https://openalex.org/W2922509574","https://openalex.org/W2963446712","https://openalex.org/W2998249317","https://openalex.org/W3016719260","https://openalex.org/W3094897602","https://openalex.org/W3136021864","https://openalex.org/W4254246953","https://openalex.org/W4372347372","https://openalex.org/W4385245566","https://openalex.org/W4390190649","https://openalex.org/W4410495386"],"related_works":[],"abstract_inverted_index":{"Cross-layer":[0],"feature":[1,44,48],"fusion":[2,16,31,45,78,104],"critically":[3],"influences":[4],"the":[5,68],"performance":[6],"of":[7,17,32,94,111],"deep":[8],"neural":[9],"networks,":[10],"where":[11],"mainstream":[12],"approaches":[13],"like":[14],"additive":[15],"residual":[18,88],"connections":[19,34],"struggle":[20,56],"to":[21,57],"model":[22],"high-order":[23,83],"nonlinear":[24],"interactions,":[25,53],"limiting":[26],"representational":[27],"capacity,":[28],"while":[29],"concatenative":[30],"dense":[33],"incurs":[35],"significant":[36],"memory":[37],"and":[38,50,60,90,133],"computational":[39],"overhead.":[40],"Although":[41],"recent":[42],"attention-based":[43],"methods":[46],"refine":[47],"representations":[49],"strengthen":[51],"hierarchical":[52],"they":[54],"often":[55],"balance":[58],"expressiveness":[59],"efficiency.":[61],"To":[62],"address":[63],"these":[64],"limitations,":[65],"we":[66],"propose":[67],"Chebyshev":[69,84],"Fusion":[70],"Unit":[71],"(CFU),":[72],"a":[73],"lightweight":[74],"yet":[75],"effective":[76],"cross-layer":[77,113],"mechanism.":[79],"Specifically,":[80],"CFU":[81],"computes":[82],"polynomial":[85],"terms":[86],"between":[87],"features":[89],"current-layer":[91],"features,":[92],"each":[93],"which":[95],"is":[96],"aggregated":[97],"through":[98],"learnable":[99],"scalar":[100],"weights,":[101],"forming":[102],"enhanced":[103],"features.":[105],"This":[106],"design":[107],"enables":[108],"explicit":[109],"modeling":[110],"complex":[112],"dependencies":[114],"with":[115],"minimal":[116],"additional":[117],"parameters.":[118],"Extensive":[119],"experiments":[120],"across":[121],"various":[122],"commonly":[123],"used":[124],"base":[125],"models":[126],"on":[127],"image":[128,131],"classification,":[129],"medical":[130],"segmentation,":[132],"physical":[134],"law":[135],"learning":[136],"tasks":[137],"demonstrate":[138],"its":[139],"superior":[140],"performance.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-25T00:00:00"}