{"id":"https://openalex.org/W4392904537","doi":"https://doi.org/10.1109/icassp48485.2024.10447329","title":"Tokenmotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection VIA Learnable Token Selection","display_name":"Tokenmotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection VIA Learnable Token Selection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904537","doi":"https://doi.org/10.1109/icassp48485.2024.10447329"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447329","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5000101472","display_name":"Zifan Yu","orcid":"https://orcid.org/0000-0002-5958-8123"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zifan Yu","raw_affiliation_strings":["Arizona State University,Tempe,AZ","Arizona State University, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"Arizona State University,Tempe,AZ","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078467314","display_name":"Erfan Bank Tavakoli","orcid":"https://orcid.org/0000-0002-3248-9301"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erfan Bank Tavakoli","raw_affiliation_strings":["Arizona State University,Tempe,AZ","Arizona State University, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"Arizona State University,Tempe,AZ","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068509275","display_name":"Meida Chen","orcid":"https://orcid.org/0000-0002-2436-3848"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meida Chen","raw_affiliation_strings":["U.S. DEVCOM Army Research Laboratory,Adelphi,MD","U.S. DEVCOM Army Research Laboratory, Adelphi, MD"],"affiliations":[{"raw_affiliation_string":"U.S. DEVCOM Army Research Laboratory,Adelphi,MD","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]},{"raw_affiliation_string":"U.S. DEVCOM Army Research Laboratory, Adelphi, MD","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072580786","display_name":"Suya You","orcid":"https://orcid.org/0000-0002-6387-7024"},"institutions":[{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]},{"id":"https://openalex.org/I4388482679","display_name":"USC Institute for Creative Technologies","ror":"https://ror.org/03hjhvn29","country_code":null,"type":"facility","lineage":["https://openalex.org/I1174212","https://openalex.org/I4388482679"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suya You","raw_affiliation_strings":["USC Institute for Creatives Technologies,Los Angeles,CA","USC Institute for Creatives Technologies, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"USC Institute for Creatives Technologies,Los Angeles,CA","institution_ids":["https://openalex.org/I4210087747"]},{"raw_affiliation_string":"USC Institute for Creatives Technologies, Los Angeles, CA","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I4388482679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075151572","display_name":"Raghuveer Rao","orcid":"https://orcid.org/0000-0001-6481-4175"},"institutions":[{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]},{"id":"https://openalex.org/I4388482679","display_name":"USC Institute for Creative Technologies","ror":"https://ror.org/03hjhvn29","country_code":null,"type":"facility","lineage":["https://openalex.org/I1174212","https://openalex.org/I4388482679"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghuveer Rao","raw_affiliation_strings":["USC Institute for Creatives Technologies,Los Angeles,CA","USC Institute for Creatives Technologies, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"USC Institute for Creatives Technologies,Los Angeles,CA","institution_ids":["https://openalex.org/I4210087747"]},{"raw_affiliation_string":"USC Institute for Creatives Technologies, Los Angeles, CA","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I4388482679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111575427","display_name":"Sanjeev Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I4388482736","display_name":"U.S. Army Command, Control, Communications, Computers, Cyber, Intelligence, Surveillance and Reconnaissance Center","ror":"https://ror.org/02h7kd997","country_code":null,"type":"facility","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437","https://openalex.org/I4388482736"]},{"id":"https://openalex.org/I106965489","display_name":"United States Army Medical Command","ror":"https://ror.org/04vrzee53","country_code":"US","type":"funder","lineage":["https://openalex.org/I106965489","https://openalex.org/I1304082316","https://openalex.org/I1330347796"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Agarwal","raw_affiliation_strings":["U.S. DEVCOM Army C5ISR Center,Fort Belvoir,VA","U.S. DEVCOM Army C5ISR Center, Fort Belvoir, VA"],"affiliations":[{"raw_affiliation_string":"U.S. DEVCOM Army C5ISR Center,Fort Belvoir,VA","institution_ids":["https://openalex.org/I106965489","https://openalex.org/I2802705668","https://openalex.org/I4388482736"]},{"raw_affiliation_string":"U.S. DEVCOM Army C5ISR Center, Fort Belvoir, VA","institution_ids":["https://openalex.org/I106965489","https://openalex.org/I2802705668","https://openalex.org/I4388482736"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083744126","display_name":"Fengbo Ren","orcid":"https://orcid.org/0000-0002-6509-8753"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengbo Ren","raw_affiliation_strings":["Arizona State University,Tempe,AZ","Arizona State University, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"Arizona State University,Tempe,AZ","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5000101472"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46934556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2875","last_page":"2879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9966999888420105,"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/security-token","display_name":"Security token","score":0.8113706111907959},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7673195600509644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7301356196403503},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6974499225616455},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6160783767700195},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.43797045946121216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3530057668685913},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13561782240867615},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12293732166290283}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8113706111907959},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673195600509644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7301356196403503},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6974499225616455},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6160783767700195},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.43797045946121216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3530057668685913},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13561782240867615},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12293732166290283},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447329","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":18,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2547875792","https://openalex.org/W2998449272","https://openalex.org/W3034684132","https://openalex.org/W3034771037","https://openalex.org/W3108460979","https://openalex.org/W3164098653","https://openalex.org/W3203092180","https://openalex.org/W3211490618","https://openalex.org/W4212774754","https://openalex.org/W4221151441","https://openalex.org/W4312258849","https://openalex.org/W4313142416","https://openalex.org/W4389665722","https://openalex.org/W4389666156","https://openalex.org/W6729448088","https://openalex.org/W6730091202","https://openalex.org/W6796494063"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4387768015","https://openalex.org/W4304700937"],"abstract_inverted_index":{"The":[0,101,125],"area":[1],"of":[2,14,106,123,127],"Video":[3],"Camouflaged":[4],"Object":[5],"Detection":[6],"(VCOD)":[7],"presents":[8],"unique":[9],"challenges":[10],"in":[11,74,86,92,98],"the":[12,66,78,104,120,134],"field":[13],"computer":[15],"vision":[16],"due":[17],"to":[18,52,118],"texture":[19],"similarities":[20],"between":[21],"target":[22],"objects":[23,36],"and":[24,37,94],"their":[25],"surroundings,":[26],"as":[27,29],"well":[28],"irregular":[30],"motion":[31],"patterns":[32],"caused":[33],"by":[34,55,82],"both":[35],"camera":[38],"movement.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"introduce":[44],"TokenMotion":[45],"(TMNet),":[46],"which":[47],"employs":[48],"a":[49,60,83,95,115],"transformer-based":[50,116],"model":[51],"enhance":[53],"VCOD":[54],"extracting":[56],"motion-guided":[57,108],"features":[58,109],"using":[59],"learnable":[61,111],"token":[62,112],"selection.":[63],"Evaluated":[64],"on":[65],"challenging":[67],"MoCA-Mask":[68],"dataset,":[69],"TMNet":[70],"achieves":[71],"state-of-the-art":[72,80],"performance":[73],"VCOD.":[75,124],"It":[76],"outperforms":[77],"existing":[79],"method":[81],"12.8%":[84],"improvement":[85],"weighted":[87],"F-measure,":[88],"an":[89],"8.4%":[90],"enhancement":[91],"S-measure,":[93],"10.7%":[96],"boost":[97],"mean":[99],"IoU.":[100],"results":[102],"demonstrate":[103],"benefits":[105],"utilizing":[107],"via":[110],"selection":[113],"within":[114],"framework":[117],"tackle":[119],"intricate":[121],"task":[122],"code":[126],"our":[128],"work":[129],"will":[130],"be":[131],"available":[132],"when":[133],"paper":[135],"is":[136],"accepted.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
