{"id":"https://openalex.org/W4408355900","doi":"https://doi.org/10.1109/icassp49660.2025.10888596","title":"Joint Feature and Kernel Fusion for Improved Depth-Aware Panoptic Segmentation","display_name":"Joint Feature and Kernel Fusion for Improved Depth-Aware Panoptic Segmentation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355900","doi":"https://doi.org/10.1109/icassp49660.2025.10888596"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5028664833","display_name":"Yulong Bai","orcid":"https://orcid.org/0000-0001-9765-1229"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yulong Bai","raw_affiliation_strings":["University of Science and Technology Beijing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012986058","display_name":"Shu Tian","orcid":"https://orcid.org/0000-0002-4910-6071"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Tian","raw_affiliation_strings":["University of Science and Technology Beijing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101821628","display_name":"Xin Zhao","orcid":"https://orcid.org/0000-0002-8567-3575"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhao","raw_affiliation_strings":["University of Science and Technology Beijing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074514262","display_name":"Xu-Cheng Yin","orcid":"https://orcid.org/0000-0003-0023-0220"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu-Cheng Yin","raw_affiliation_strings":["University of Science and Technology Beijing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028664833"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0587082,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.8927000164985657,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.8927000164985657,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/T10057","display_name":"Face and Expression Recognition","score":0.8878999948501587,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.8406999707221985,"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/joint","display_name":"Joint (building)","score":0.7428187131881714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.656711995601654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.654854416847229},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.643302321434021},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6238861083984375},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5225024819374084},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46507784724235535},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.462564080953598},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.42702099680900574},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0985724925994873},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08530056476593018}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7428187131881714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.656711995601654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.654854416847229},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.643302321434021},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6238861083984375},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5225024819374084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46507784724235535},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.462564080953598},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.42702099680900574},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0985724925994873},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08530056476593018},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2910628332","https://openalex.org/W2913340405","https://openalex.org/W2963488291","https://openalex.org/W2963877604","https://openalex.org/W2981537222","https://openalex.org/W2999219213","https://openalex.org/W3014758606","https://openalex.org/W3085046840","https://openalex.org/W3088976275","https://openalex.org/W3106546328","https://openalex.org/W3170410843","https://openalex.org/W3176027594","https://openalex.org/W3204819834","https://openalex.org/W4312258332","https://openalex.org/W4385804929","https://openalex.org/W4399504874","https://openalex.org/W4401417093","https://openalex.org/W4402702938","https://openalex.org/W6784930956","https://openalex.org/W6848927509"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2888483922","https://openalex.org/W4396737233","https://openalex.org/W4379231730","https://openalex.org/W2367747139","https://openalex.org/W3147584709","https://openalex.org/W4389858081","https://openalex.org/W2099421762","https://openalex.org/W4292523377"],"abstract_inverted_index":{"Depth-aware":[0,86,127],"Panoptic":[1,87,128],"Segmentation,":[2],"which":[3],"combines":[4],"panoptic":[5],"segmentation":[6],"and":[7,24,48,65,80,96,103],"monocular":[8],"depth":[9,64],"estimation,":[10],"is":[11],"a":[12,17,73,120],"challenging":[13],"task":[14,53],"that":[15,110],"requires":[16],"comprehensive":[18],"understanding":[19],"of":[20,94,119],"both":[21],"scene":[22],"geometry":[23],"object":[25],"semantics.":[26],"Recent":[27],"multi-task":[28,123],"learning":[29,124],"approaches":[30],"have":[31],"leveraged":[32],"dynamic":[33],"kernel":[34,49],"methods":[35,43],"to":[36,57,84],"tackle":[37],"these":[38,42],"tasks":[39],"simultaneously.":[40],"However,":[41],"often":[44],"treat":[45],"feature":[46],"extraction":[47],"generation":[50],"for":[51,126],"each":[52],"in":[54],"isolation,":[55],"failing":[56],"fully":[58],"exploit":[59],"the":[60,117],"rich":[61],"interdependencies":[62],"between":[63,106],"semantic":[66],"information.":[67],"To":[68],"address":[69],"this,":[70],"we":[71],"propose":[72],"novel":[74],"framework":[75],"with":[76],"Cross-Task":[77],"Feature":[78],"Fusion":[79,82],"Kernel":[81],"mechanisms":[83],"enhance":[85],"Segmentation.":[88,129],"Our":[89],"approach":[90],"enables":[91],"deeper":[92],"integration":[93],"features":[95],"kernels,":[97],"promoting":[98],"more":[99,121],"effective":[100],"information":[101],"exchange":[102],"mutual":[104],"reinforcement":[105],"tasks.":[107],"Experiments":[108],"show":[109],"our":[111],"method":[112],"brings":[113],"significant":[114],"improvements,":[115],"demonstrating":[116],"potential":[118],"integrated":[122],"strategy":[125]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}