{"id":"https://openalex.org/W4414767440","doi":"https://doi.org/10.1109/lsp.2025.3617294","title":"SODA: Structural Pre-Decoupling and Co-Aligning for Video Compositional Representation","display_name":"SODA: Structural Pre-Decoupling and Co-Aligning for Video Compositional Representation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414767440","doi":"https://doi.org/10.1109/lsp.2025.3617294"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3617294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3617294","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5029702480","display_name":"Peng Huang","orcid":"https://orcid.org/0009-0003-4102-6506"},"institutions":[{"id":"https://openalex.org/I167027274","display_name":"Nanjing Forestry University","ror":"https://ror.org/03m96p165","country_code":"CN","type":"education","lineage":["https://openalex.org/I167027274"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Huang","raw_affiliation_strings":["College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing, China","institution_ids":["https://openalex.org/I167027274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037778075","display_name":"Wenxuan Ge","orcid":"https://orcid.org/0000-0002-4186-8944"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Ge","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086967620","display_name":"He Yan","orcid":"https://orcid.org/0000-0002-6135-3809"},"institutions":[{"id":"https://openalex.org/I167027274","display_name":"Nanjing Forestry University","ror":"https://ror.org/03m96p165","country_code":"CN","type":"education","lineage":["https://openalex.org/I167027274"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Yan","raw_affiliation_strings":["College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing, China","institution_ids":["https://openalex.org/I167027274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083717898","display_name":"Henghao Zhao","orcid":"https://orcid.org/0000-0002-0970-021X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Henghao Zhao","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040437528","display_name":"Xiangbo Shu","orcid":"https://orcid.org/0000-0003-4902-4663"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangbo Shu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4902-4663","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.36988477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"4049","last_page":"4053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.965499997138977,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9273999929428101,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7240999937057495},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.626800000667572},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5873000025749207},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.4934999942779541},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.49309998750686646},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4708000123500824},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.462799996137619},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4480000138282776},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.41620001196861267},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3849000036716461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982000112533569},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7240999937057495},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.626800000667572},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5873000025749207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5688999891281128},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48330000042915344},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C11821877","wikidata":"https://www.wikidata.org/wiki/Q187959","display_name":"Distributive property","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C2777311342","wikidata":"https://www.wikidata.org/wiki/Q578801","display_name":"Shared space","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3617294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3617294","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1351919236","display_name":null,"funder_award_id":"62306142","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1861350651","display_name":null,"funder_award_id":"62427808","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5512729199","display_name":null,"funder_award_id":"62222207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1948251820","https://openalex.org/W2126579184","https://openalex.org/W2602311553","https://openalex.org/W2761860076","https://openalex.org/W2976669726","https://openalex.org/W3034257141","https://openalex.org/W3126721948","https://openalex.org/W3152380984","https://openalex.org/W3206930349","https://openalex.org/W3207758636","https://openalex.org/W3209504420","https://openalex.org/W3217102353","https://openalex.org/W4304092632","https://openalex.org/W4312560592","https://openalex.org/W4312769131","https://openalex.org/W4322746940","https://openalex.org/W4360993849","https://openalex.org/W4386072300","https://openalex.org/W4389815697","https://openalex.org/W4390874575","https://openalex.org/W4391215769","https://openalex.org/W4393853176","https://openalex.org/W4402350623","https://openalex.org/W4402997051","https://openalex.org/W4409152523","https://openalex.org/W4409152534","https://openalex.org/W4413155536"],"related_works":[],"abstract_inverted_index":{"The":[0],"core":[1,78],"challenge":[2],"in":[3,8,124,150],"video":[4],"compositional":[5,148,180],"representation":[6],"lies":[7],"jointly":[9],"identifying":[10],"atomic":[11,146],"actions":[12],"(verbs)":[13],"and":[14,39,57,69,74,107,113,147,178,187],"their":[15],"associated":[16],"objects":[17],"(nouns),":[18],"while":[19,165],"generalizing":[20],"to":[21,36],"unseen":[22],"verb-noun":[23,163],"combinations.":[24],"Existing":[25],"approaches":[26],"often":[27],"adopt":[28],"a":[29,52,136,151],"shared":[30,152],"backbone":[31],"with":[32],"multi-head":[33],"classifiers,":[34],"leading":[35],"semantic":[37,72,153],"entanglement":[38],"recognition":[40,75,182],"imbalance,":[41],"especially":[42],"under":[43],"ViT-based":[44],"paradigms.":[45],"To":[46],"tackle":[47],"these":[48],"issues,":[49],"we":[50],"propose":[51],"novel":[53],"framework,":[54],"Structural":[55],"Pre-Decoupling":[56],"Co-Aligning":[58],"(SODA),":[59],"which":[60],"structurally":[61],"decouples":[62],"the":[63,81,125,167,185],"early-stage":[64],"learning":[65],"paths":[66],"of":[67,127,134,162,170,189],"verbs":[68],"nouns,":[70],"mitigating":[71],"interference":[73],"imbalance.":[76],"A":[77],"component":[79],"is":[80,141],"Divide-and-Conquer":[82],"Disentanglement":[83],"(DCD)":[84],"module,":[85],"comprising":[86],"two":[87],"parallel":[88],"paths:":[89],"an":[90,114],"Object-Removed":[91],"Verb":[92],"(OR-V)":[93],"path":[94,118],"that":[95,119,144],"explicitly":[96],"suppresses":[97],"object":[98],"appearance":[99],"by":[100],"integrating":[101],"frame-difference":[102],"features":[103,129],"for":[104,110],"short-term":[105],"motion":[106],"trajectory":[108],"cues":[109],"long-term":[111],"dynamics,":[112],"Object-Centric":[115],"Noun":[116],"(OC-N)":[117],"constructs":[120],"adaptive":[121],"key-frame":[122],"representations":[123,149],"guidance":[126],"dynamic":[128],"from":[130],"OR-V.":[131],"On":[132],"top":[133],"these,":[135],"Compositional":[137],"Co-Alignment":[138],"(CCA)":[139],"strategy":[140],"further":[142],"introduced":[143],"aligns":[145],"space":[154],"through":[155],"contrastive":[156],"learning,":[157],"capturing":[158],"implicit":[159],"commonsense":[160],"associations":[161],"pairs":[164],"preserving":[166],"discriminative":[168],"power":[169],"each":[171],"stream.":[172],"Extensive":[173],"experiments":[174],"on":[175],"both":[176],"standard":[177],"zero-shot":[179],"action":[181],"benchmarks":[183],"validate":[184],"effectiveness":[186],"generalization":[188],"our":[190],"approach.":[191]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}