{"id":"https://openalex.org/W7138054749","doi":"https://doi.org/10.1609/aaai.v40i15.38245","title":"Towards Explainable Video Camouflaged Object Detection: SAM2 with Eventstream-Inspired Data","display_name":"Towards Explainable Video Camouflaged Object Detection: SAM2 with Eventstream-Inspired Data","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138054749","doi":"https://doi.org/10.1609/aaai.v40i15.38245"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i15.38245","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38245","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i15.38245","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129650162","display_name":"Hong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hong Zhang","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085090465","display_name":"Yixuan Lyu","orcid":"https://orcid.org/0000-0001-7608-9150"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Lyu","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709858","display_name":"Hanyang Liu","orcid":"https://orcid.org/0009-0009-8956-1245"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyang Liu","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047559536","display_name":"Jianbo Song","orcid":"https://orcid.org/0000-0001-5847-9630"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbo Song","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014038368","display_name":"Ding Yuan","orcid":"https://orcid.org/0000-0002-6184-6371"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Yuan","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129710858","display_name":"Yifan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129650162"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31330472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"15","first_page":"12511","last_page":"12519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9409999847412109,"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":0.9409999847412109,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.00839999970048666,"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/T11094","display_name":"Face Recognition and Perception","score":0.006399999838322401,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6563000082969666},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.641700029373169},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.623199999332428},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5848000049591064},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5647000074386597},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5400999784469604},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5059999823570251},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.43529999256134033},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.41510000824928284}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8016999959945679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883999943733215},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7705000042915344},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6563000082969666},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.641700029373169},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.623199999332428},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5848000049591064},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5647000074386597},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.43529999256134033},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.37380000948905945},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3684000074863434},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.33059999346733093},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3154999911785126},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i15.38245","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38245","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i15.38245","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38245","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":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],"poses":[5],"significant":[6],"challenges":[7],"due":[8],"to":[9,81,130,176],"the":[10,48,58,132,166,173,181],"subtle":[11],"appearance":[12,120],"of":[13,51,60,106,117,168],"camouflaged":[14],"objects,":[15],"especially":[16],"under":[17],"dynamic":[18],"motion":[19,33,84,89,118,163],"and":[20,41,57,110,119,146,161],"occlusion.":[21],"Existing":[22],"methods":[23],"predominantly":[24],"rely":[25],"on":[26,144],"optical":[27],"flow":[28],"or":[29],"black-box":[30],"features":[31],"for":[32,71,134],"modeling,":[34],"which":[35],"often":[36],"entail":[37],"substantial":[38],"computational":[39],"costs":[40],"suffer":[42],"from":[43,90],"limited":[44],"interpretability.":[45],"Inspired":[46],"by":[47],"human":[49],"strategy":[50],"identifying":[52],"abnormal":[53],"movements":[54],"between":[55],"frames":[56],"principle":[59],"event":[61],"camera":[62],"image":[63],"formation,":[64],"we":[65,74,124],"propose":[66],"an":[67,76],"eventstream-inspired":[68,178],"dual-branch":[69,102],"framework":[70],"VCOD.":[72,141],"Specifically,":[73],"design":[75],"eventstream-like":[77],"data":[78],"extraction":[79],"module":[80],"capture":[82],"pixel-level":[83],"variations,":[85],"effectively":[86],"distinguishing":[87],"object":[88],"background":[91],"dynamics.":[92],"This":[93],"event-based":[94],"representation":[95],"is":[96,172],"integrated":[97],"into":[98,180],"SAM2":[99],"through":[100],"a":[101,126],"memory-augmented":[103],"framework,":[104],"consisting":[105],"Time":[107],"Bridge":[108,112],"Attention":[109],"Visual":[111],"Attention,":[113],"enabling":[114],"joint":[115],"modeling":[116],"cues.":[121],"In":[122],"addition,":[123],"introduce":[125],"Prompt":[127],"Embedding":[128],"Generator":[129],"eliminate":[131],"need":[133],"human-provided":[135],"interactive":[136],"prompts,":[137],"facilitating":[138],"fully":[139],"automatic":[140],"Extensive":[142],"experiments":[143],"MoCA-Mask":[145],"CAD2016":[147],"demonstrate":[148],"that":[149],"our":[150,169],"approach":[151],"significantly":[152],"outperforms":[153],"state-of-the-art":[154],"methods,":[155],"achieving":[156],"both":[157],"superior":[158],"segmentation":[159],"accuracy":[160],"interpretable":[162],"modeling.":[164],"To":[165],"best":[167],"knowledge,":[170],"this":[171],"first":[174],"work":[175],"incorporate":[177],"representations":[179],"VCOD":[182],"task.":[183]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}