{"id":"https://openalex.org/W4387969348","doi":"https://doi.org/10.1145/3581783.3612017","title":"Temporally Efficient Gabor Transformer for Unsupervised Video Object Segmentation","display_name":"Temporally Efficient Gabor Transformer for Unsupervised Video Object Segmentation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969348","doi":"https://doi.org/10.1145/3581783.3612017"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612017","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5102866341","display_name":"Jiaqing Fan","orcid":"https://orcid.org/0000-0001-5659-7457"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqing Fan","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5659-7457","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007418071","display_name":"Tiankang Su","orcid":"https://orcid.org/0000-0002-6470-8230"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiankang Su","raw_affiliation_strings":["Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6470-8230","affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075412755","display_name":"Kaihua Zhang","orcid":"https://orcid.org/0000-0002-1613-3401"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaihua Zhang","raw_affiliation_strings":["Ministry of Education & Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1613-3401","affiliations":[{"raw_affiliation_string":"Ministry of Education & Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072705110","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-2113-7853"},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Walmart Global Tech, Sunnyvale, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2113-7853","affiliations":[{"raw_affiliation_string":"Walmart Global Tech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404959","display_name":"Qingshan Liu","orcid":"https://orcid.org/0000-0002-5512-6984"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingshan Liu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5512-6984","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3394","last_page":"3402"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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":0.8236008286476135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7332282066345215},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6495746970176697},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6494235992431641},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6043708324432373},{"id":"https://openalex.org/keywords/gabor-wavelet","display_name":"Gabor wavelet","score":0.5633474588394165},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47611531615257263},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4701072573661804},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.17752370238304138},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.11382859945297241},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08568981289863586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8236008286476135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7332282066345215},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6495746970176697},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6494235992431641},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6043708324432373},{"id":"https://openalex.org/C136902061","wikidata":"https://www.wikidata.org/wiki/Q16981559","display_name":"Gabor wavelet","level":5,"score":0.5633474588394165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47611531615257263},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4701072573661804},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.17752370238304138},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.11382859945297241},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08568981289863586},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612017","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2981342784","https://openalex.org/W2987391422","https://openalex.org/W2998449272","https://openalex.org/W3035422681","https://openalex.org/W3049318984","https://openalex.org/W3107944836","https://openalex.org/W3108043693","https://openalex.org/W3175890016","https://openalex.org/W3182236906","https://openalex.org/W3202858245","https://openalex.org/W3203605797","https://openalex.org/W3204640376","https://openalex.org/W3204643350","https://openalex.org/W3210096385","https://openalex.org/W3212881378","https://openalex.org/W3215899623","https://openalex.org/W4312732475","https://openalex.org/W6814250579"],"related_works":["https://openalex.org/W2155558857","https://openalex.org/W2045241287","https://openalex.org/W2509068507","https://openalex.org/W2148452471","https://openalex.org/W1586656922","https://openalex.org/W3140675663","https://openalex.org/W2137598809","https://openalex.org/W2145421296","https://openalex.org/W2031483260","https://openalex.org/W1585032044"],"abstract_inverted_index":{"Spatial-temporal":[0],"structural":[1,87,105],"details":[2,88,107],"of":[3,108,195],"targets":[4],"in":[5,26],"video":[6],"(e.g.":[7,39],"varying":[8],"edges,":[9],"textures":[10],"over":[11],"time)":[12],"are":[13],"essential":[14],"to":[15,49,102,115,132,199],"accurate":[16,90,112],"Unsupervised":[17],"Video":[18],"Object":[19],"Segmentation":[20],"(UVOS).":[21],"The":[22,68],"vanilla":[23],"multi-head":[24],"self-attention":[25],"the":[27,35,44,72,85,104,109,118,135,142,147,153,163,193,196],"Transformer-based":[28],"UVOS":[29,154,184],"methods":[30],"usually":[31],"concentrates":[32],"on":[33,181],"learning":[34],"general":[36],"low-frequency":[37],"information":[38,164],"illumination,":[40],"color),":[41],"while":[42],"neglecting":[43],"high-frequency":[45],"texture":[46,106],"details,":[47],"leading":[48],"unsatisfying":[50],"segmentation":[51],"results.":[52],"To":[53],"address":[54],"this":[55,57],"issue,":[56],"paper":[58],"presents":[59],"a":[60,157,172],"Temporally":[61],"efficient":[62,126],"Gabor":[63,99,167],"Transformer":[64,101,159],"(TGFormer)":[65],"for":[66,89,111],"UVOS.":[67,91,113],"TGFormer":[69],"jointly":[70],"models":[71],"spatial":[73],"dependencies":[74],"and":[75,79,145,168,190],"temporal":[76,137],"coherence":[77],"intra-":[78],"inter-frames,":[80],"which":[81,139],"can":[82],"fully":[83,158],"capture":[84],"rich":[86,176],"Concretely,":[92],"we":[93,123,151],"first":[94],"propose":[95],"an":[96,125],"effective":[97],"learnable":[98],"filtering":[100],"mine":[103],"object":[110],"Then,":[114],"adaptively":[116],"store":[117],"redundant":[119],"neighboring":[120,128],"historical":[121],"information,":[122,138],"present":[124],"dynamic":[127],"frame":[129,144],"selection":[130],"module":[131],"automatically":[133],"choose":[134],"useful":[136],"simultaneously":[140],"relieves":[141],"blurry":[143],"reduces":[146],"computation":[148],"burden.":[149],"Finally,":[150],"make":[152],"model":[155],"be":[156],"architecture,":[160],"meanwhile":[161],"aggregating":[162],"from":[165],"space,":[166],"time":[169],"domains,":[170],"yielding":[171],"strong":[173],"representation":[174],"with":[175],"structure":[177],"details.":[178],"Extensive":[179],"experiments":[180],"five":[182],"mainstream":[183],"benchmarks":[185],"(DAVIS2016,":[186],"FBMS,":[187],"DAVSOD,":[188],"ViSal,":[189],"MCL)":[191],"demonstrate":[192],"superiority":[194],"presented":[197],"solution":[198],"sate-of-the-art":[200],"methods.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}