{"id":"https://openalex.org/W4417155432","doi":"https://doi.org/10.1109/iccv51701.2025.01212","title":"Scoring, Remember, and Reference: Catching Camouflaged Objects in Videos","display_name":"Scoring, Remember, and Reference: Catching Camouflaged Objects in Videos","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417155432","doi":"https://doi.org/10.1109/iccv51701.2025.01212"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.17050","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102658990","display_name":"Yuang Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu'ang Feng","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048271189","display_name":"Shuyong Gao","orcid":"https://orcid.org/0000-0002-8992-0756"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyong Gao","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fuzhen Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuzhen Yan","raw_affiliation_strings":["School of Economics, Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics, Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035069538","display_name":"Yicheng Song","orcid":"https://orcid.org/0009-0008-7104-8630"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Song","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101804825","display_name":"Lingyi Hong","orcid":"https://orcid.org/0000-0002-2749-5133"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyi Hong","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101982146","display_name":"Junjie Hu","orcid":"https://orcid.org/0000-0002-5750-0511"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Hu","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087549682","display_name":"Wenqiang Zhang","orcid":"https://orcid.org/0000-0003-1568-1200"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqiang Zhang","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13043","last_page":"13052"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9315999746322632,"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":0.9315999746322632,"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/T13219","display_name":"Mind wandering and attention","score":0.005200000014156103,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.004100000020116568,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6675999760627747},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6524999737739563},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6281999945640564},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5934000015258789},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49900001287460327},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.426800012588501},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.41519999504089355},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.4032000005245209},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.39809998869895935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169000148773193},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6675999760627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6632000207901001},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6524999737739563},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6281999945640564},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.616599977016449},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5934000015258789},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49900001287460327},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41519999504089355},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.4032000005245209},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C74992021","wikidata":"https://www.wikidata.org/wiki/Q184876","display_name":"Frame of reference","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C22304111","wikidata":"https://www.wikidata.org/wiki/Q1417978","display_name":"Object permanence","level":4,"score":0.26409998536109924},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C150189527","wikidata":"https://www.wikidata.org/wiki/Q356674","display_name":"Reference model","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.17050","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17050","pdf_url":"https://arxiv.org/pdf/2503.17050","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.17050","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.17050","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.17050","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17050","pdf_url":"https://arxiv.org/pdf/2503.17050","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7143284523","display_name":"\u52a8\u6001\u573a\u666f\u4e2d\u673a\u5668\u4eba\u663e\u8457\u6027\u76ee\u6807\u8bc6\u522b\u4e0e\u8868\u8fbe\u6280\u672f\u7814\u7a76","funder_award_id":"62072112","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"Camouflaged":[1],"Object":[2],"Detection":[3],"(VCOD)":[4],"aims":[5],"to":[6,30,98,142,149],"segment":[7],"objects":[8,36],"whose":[9],"appearances":[10],"closely":[11],"resemble":[12],"their":[13],"surroundings,":[14],"posing":[15],"a":[16,77,105,185],"challenging":[17],"and":[18,37,85,134,145,158,183],"emerging":[19],"task.":[20],"Existing":[21],"vision":[22],"models":[23],"often":[24],"struggle":[25],"in":[26,44],"such":[27],"scenarios":[28],"due":[29],"the":[31,38,131,189],"indistinguishable":[32],"appearance":[33],"of":[34,41,161],"camouflaged":[35,71],"insufficient":[39],"exploitation":[40],"dynamic":[42],"information":[43,64,116,141],"videos.":[45],"To":[46],"address":[47],"these":[48,127],"challenges,":[49],"we":[50,75,129],"propose":[51],"an":[52],"end-to-end":[53],"VCOD":[54],"framework":[55],"inspired":[56],"by":[57,65,173],"human":[58],"memory-recognition,":[59],"which":[60,138],"leverages":[61],"historical":[62],"video":[63,162],"integrating":[66,113],"memory":[67,147],"reference":[68,88,115],"frames":[69],"for":[70,121],"sequence":[72],"processing.":[73,152],"Specifically,":[74],"design":[76,157],"dual-purpose":[78],"decoder":[79],"that":[80],"simultaneously":[81],"generates":[82],"predicted":[83],"masks":[84],"scores,":[86],"enabling":[87],"frame":[89],"selection":[90],"based":[91],"on":[92,175],"scores":[93],"while":[94,178],"introducing":[95],"auxiliary":[96],"supervision":[97],"enhance":[99],"feature":[100,123],"extraction.Furthermore,":[101],"this":[102],"study":[103],"introduces":[104],"novel":[106],"reference-guided":[107],"multilevel":[108],"asymmetric":[109],"attention":[110],"mechanism,":[111],"effectively":[112],"long-term":[114],"with":[117],"short-term":[118],"motion":[119],"cues":[120],"comprehensive":[122],"extraction.":[124],"By":[125],"combining":[126],"modules,":[128],"develop":[130],"Scoring,":[132],"Remember,":[133],"Reference":[135],"(SRR)":[136],"framework,":[137],"efficiently":[139],"extracts":[140],"locate":[143],"targets":[144],"employs":[146],"guidance":[148],"improve":[150],"subsequent":[151],"With":[153],"its":[154],"optimized":[155],"module":[156],"effective":[159],"utilization":[160],"data,":[163],"our":[164],"model":[165],"achieves":[166],"significant":[167],"performance":[168],"improvements,":[169],"surpassing":[170],"existing":[171],"approaches":[172],"10%":[174],"benchmark":[176],"datasets":[177],"requiring":[179],"fewer":[180],"parameters":[181],"(54M)":[182],"only":[184],"single":[186],"pass":[187],"through":[188],"video.":[190],"The":[191],"code":[192],"will":[193],"be":[194],"made":[195],"publicly":[196],"available.":[197]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}