{"id":"https://openalex.org/W4399257633","doi":"https://doi.org/10.1145/3653804.3656278","title":"LAtt-Yolov8-seg: Video Real-time Instance Segmentation for Urban Street Scenes Based on Focused Linear Attention Mechanism","display_name":"LAtt-Yolov8-seg: Video Real-time Instance Segmentation for Urban Street Scenes Based on Focused Linear Attention Mechanism","publication_year":2024,"publication_date":"2024-01-19","ids":{"openalex":"https://openalex.org/W4399257633","doi":"https://doi.org/10.1145/3653804.3656278"},"language":"en","primary_location":{"id":"doi:10.1145/3653804.3656278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653804.3656278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer Vision and Deep Learning","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/A5026978129","display_name":"Xinqi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinqi Zhang","raw_affiliation_strings":["HDU-ITMO Joint Institute, Hangzhou Dianzi University, China"],"raw_orcid":"https://orcid.org/0009-0006-0469-1277","affiliations":[{"raw_affiliation_string":"HDU-ITMO Joint Institute, Hangzhou Dianzi University, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111217861","display_name":"Tuo Dong","orcid":"https://orcid.org/0000-0002-1201-6355"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuo Dong","raw_affiliation_strings":["Comprehensive Command and Support Center of Grassroots Governance, China"],"raw_orcid":"https://orcid.org/0000-0002-1201-6355","affiliations":[{"raw_affiliation_string":"Comprehensive Command and Support Center of Grassroots Governance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051997091","display_name":"Liqi Yan","orcid":"https://orcid.org/0000-0002-7077-4947"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqi Yan","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University, China"],"raw_orcid":"https://orcid.org/0000-0002-7077-4947","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036549630","display_name":"Zhenglei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenglei Yang","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University, China"],"raw_orcid":"https://orcid.org/0009-0003-5087-2763","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100778354","display_name":"Jianhui Zhang","orcid":"https://orcid.org/0000-0002-0979-6514"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhui Zhang","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University, China"],"raw_orcid":"https://orcid.org/0000-0002-0979-6514","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University, China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026978129"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47709961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9991000294685364,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.8603532314300537},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6366629004478455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5356912612915039},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4762837290763855},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.4410867989063263},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3914509415626526},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34549054503440857},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.2087182104587555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8603532314300537},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6366629004478455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5356912612915039},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4762837290763855},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.4410867989063263},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3914509415626526},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34549054503440857},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2087182104587555}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3653804.3656278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653804.3656278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer Vision and Deep Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.7900000214576721,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2559655401","https://openalex.org/W2613718673","https://openalex.org/W2993182889","https://openalex.org/W3034573343","https://openalex.org/W3096609285","https://openalex.org/W3116489684","https://openalex.org/W4236965008","https://openalex.org/W4293732316","https://openalex.org/W4312815172","https://openalex.org/W6735463952","https://openalex.org/W6739901393","https://openalex.org/W6780816326"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3022820045","https://openalex.org/W2801655600","https://openalex.org/W3005627584","https://openalex.org/W2894954915"],"abstract_inverted_index":{"Abstract:":[0],"Recently,":[1],"instance":[2,31,158],"segmentation":[3,32,159],"models":[4],"with":[5],"complex":[6,39],"architectures":[7],"and":[8,25,35,95,103,143,148,156],"large":[9],"parameter":[10],"sets":[11],"have":[12],"shown":[13],"impressive":[14],"levels":[15],"of":[16,62,75,93,111,123],"precision.":[17],"Nonetheless,":[18],"considering":[19],"a":[20,49,63,86],"practical":[21,157],"perspective,":[22],"balancing":[23],"precision":[24],"speed":[26],"is":[27],"more":[28],"desirable.":[29],"Real-time":[30],"faces":[33],"efficiency":[34],"quality":[36,144],"challenges":[37],"in":[38,59],"urban":[40],"street":[41],"scenes.":[42],"In":[43],"the":[44,60,72,91,109,121,124,132,137],"present":[45],"research,":[46],"we":[47],"propose":[48],"YOLOv8-seg":[50],"based":[51],"model":[52],"named":[53],"LAtt-Yolov8-seg.":[54],"A":[55],"pivotal":[56],"advancement":[57],"lies":[58],"introduction":[61],"mechanism":[64,83],"called":[65],"Focused":[66],"Linear":[67],"Attention,":[68],"which":[69],"effectively":[70],"reduces":[71],"computational":[73],"complexity":[74],"traditional":[76],"attention":[77,126],"while":[78],"maintaining":[79],"representational":[80],"capacity.":[81],"This":[82,151],"first":[84],"designs":[85],"focusing":[87],"function":[88],"to":[89,98,119,146],"adjust":[90],"orientations":[92],"query":[94],"key":[96],"features":[97,101,105],"bring":[99],"similar":[100],"together":[102],"dissimilar":[104],"apart,":[106],"thereby":[107],"mimicking":[108],"distribution":[110],"Softmax":[112],"attention.":[113],"Secondly,":[114],"depthwise":[115],"convolutions":[116],"are":[117],"used":[118],"recover":[120],"rank":[122],"linear":[125],"matrix,":[127],"improving":[128],"feature":[129],"diversity.":[130],"On":[131],"Cityscapes":[133],"dataset,":[134],"LAtt-Yolov8-seg":[135],"achieves":[136],"optimal":[138],"balance":[139],"between":[140],"real-time":[141],"performance":[142],"compared":[145],"convolutional":[147],"transformer":[149],"models.":[150],"work":[152],"provides":[153],"an":[154],"effective":[155],"solution":[160],"for":[161],"resource-constrained":[162],"real-world":[163],"applications.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}