[{"_1":2,"_3":-5,"_4":-5},"loaderData",{"_5":6,"_7":8,"_9":10},"actionData","errors","root",{"_274":275},"routes/_layout",{"_11":194},"routes/entity.$type.$id",{"_11":12,"_13":14,"_15":16,"_17":18,"_19":20,"_21":22,"_23":24,"_25":26,"_27":28},"dehydratedState",{"_73":74,"_75":76},"type","paper","id","paper_W4285310685","section","technologies","entity",{"_15":16,"_29":30,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":38,"_39":-5,"_40":41,"_42":43,"_44":45,"_46":47,"_48":-5,"_49":50,"_51":30,"_52":53,"_54":55,"_56":57,"_58":59,"_60":61,"_62":-5,"_63":64,"_65":-5,"_66":67,"_68":30,"_69":-5},"canonical","https://www.hugmap.com/entity/paper/paper_W4285310685/technologies","siteBaseUrl","https://www.hugmap.com","sectionCount",2,"jsonLd","{\"@context\":\"https://schema.org\",\"@graph\":[{\"name\":\"Camouflaged Object Detection via Context-Aware Cross-Level Fusion\",\"url\":\"https://www.hugmap.com/entity/paper/paper_W4285310685/technologies\",\"@type\":\"ScholarlyArticle\",\"headline\":\"Camouflaged Object Detection via Context-Aware Cross-Level Fusion\",\"datePublished\":\"2022-05-26\",\"isPartOf\":{\"@type\":\"Periodical\",\"name\":\"IEEE Transactions on Circuits and Systems for Video Technology\"}},{\"@type\":\"CollectionPage\",\"name\":\"Camouflaged Object Detection via Context-Aware Cross-Level Fusion 相关技术\",\"description\":\"Camouflaged Object Detection via Context-Aware Cross-Level Fusion 在 HugMap 中的相关技术，共 2 条，含结构化关联信息与详情链接。\",\"url\":\"https://www.hugmap.com/entity/paper/paper_W4285310685/technologies\",\"inLanguage\":\"zh-CN\"},{\"@type\":\"BreadcrumbList\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"首页\",\"item\":\"https://www.hugmap.com/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"论文\",\"item\":\"https://www.hugmap.com/search?type=paper\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Camouflaged Object Detection via Context-Aware Cross-Level Fusion\",\"item\":\"https://www.hugmap.com/entity/paper/paper_W4285310685\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"相关技术\",\"item\":\"https://www.hugmap.com/entity/paper/paper_W4285310685/technologies\"}]}]}","name","Camouflaged Object Detection via Context-Aware Cross-Level Fusion","nameZh","aliases","description","descriptionZh","status","active","externalIds","{\"openalex\":\"W4285310685\",\"doi\":\"10.1109/tcsvt.2022.3178173\"}","properties","source","openalex","createdAt","2026-05-22T15:21:00.441964402","updatedAt","2026-05-22T15:21:00.441967167","doi","10.1109/tcsvt.2022.3178173","arxivId","openalexId","W4285310685","title","abstractText","Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances, e.g., object size and shape. To address these challenges, we propose a novel Context-aware Cross-level Fusion Network (

$\\text{C}^{2}\\text{F}$

-Net), which fuses context-aware cross-level features for accurately identifying camouflaged objects. Specifically, we compute informative attention coefficients from multi-level features with our Attention-induced Cross-level Fusion Module (ACFM), which further integrates the features under the guidance of attention coefficients. We then propose a Dual-branch Global Context Module (DGCM) to refine the fused features for informative feature representations by exploiting rich global context information. Multiple ACFMs and DGCMs are integrated in a cascaded manner for generating a coarse prediction from high-level features. The coarse prediction acts as an attention map to refine the low-level features before passing them to our Camouflage Inference Module (CIM) to generate the final prediction. We perform extensive experiments on three widely used benchmark datasets and compare

$\\text{C}^{2}\\text{F}$

-Net with state-of-the-art (SOTA) models. The results show that

$\\text{C}^{2}\\text{F}$

-Net is an effective COD model and outperforms SOTA models remarkably. Further, an evaluation on polyp segmentation datasets demonstrates the promising potentials of our

$\\text{C}^{2}\\text{F}$

-Net in COD downstream applications. Our code is publicly available at: https://github.com/Ben57882/C2FNet-TSCVT","publishedDate","2022-05-26","publishedYear",2022,"venue","IEEE Transactions on Circuits and Systems for Video Technology","citationCount",244,"authors","keywords",[70,71,72],"pdfUrl","topVenue",false,"displayName","displayDescription","Visual Attention and Saliency Detection","Advanced Image and Video Retrieval Techniques","Image Enhancement Techniques","mutations",[],"queries",[77],{"_78":79,"_80":81,"_82":83,"_84":85},"dehydratedAt",1781536997567,"state",{"_87":88,"_89":90,"_91":79,"_92":-5,"_93":94,"_95":94,"_96":94,"_97":-5,"_98":-5,"_99":67,"_35":100,"_101":102},"queryKey",[86,19,14,16],"queryHash","[\"portal\",\"entity\",\"paper\",\"paper_W4285310685\"]","portal","data",{"_19":20,"_103":104,"_105":106,"_107":108,"_109":110,"_18":111,"_62":112},"dataUpdateCount",1,"dataUpdatedAt","error","errorUpdateCount",0,"errorUpdatedAt","fetchFailureCount","fetchFailureReason","fetchMeta","isInvalidated","success","fetchStatus","idle","entityType","Paper","taxonomies",[163,164,165],"events",[],"articles",[],[143,144],[113,114,115],{"_15":137,"_29":138,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":139,"_39":-5,"_40":41,"_42":140,"_44":141,"_121":142,"_51":-5,"_123":-5,"_124":-5,"_125":-5,"_60":-5,"_126":-5,"_127":-5,"_128":-5,"_129":-5,"_130":-5,"_68":138,"_69":-5},{"_15":131,"_29":132,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":133,"_39":-5,"_40":41,"_42":134,"_44":135,"_121":136,"_51":-5,"_123":-5,"_124":-5,"_125":-5,"_60":-5,"_126":-5,"_127":-5,"_128":-5,"_129":-5,"_130":-5,"_68":132,"_69":-5},{"_15":116,"_29":117,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":118,"_39":-5,"_40":41,"_42":119,"_44":120,"_121":122,"_51":-5,"_123":-5,"_124":-5,"_125":-5,"_60":-5,"_126":-5,"_127":-5,"_128":-5,"_129":-5,"_130":-5,"_68":117,"_69":-5},"person_A5100765638","Geng Chen","{\"openalex\":\"A5100765638\",\"orcid\":\"0000-0001-8350-6581\"}","2026-05-14T08:07:08.186317663","2026-05-22T15:21:00.44982081","orcid","0000-0001-8350-6581","affiliation","researchArea","paperCount","homepage","linkedin","twitter","github","hindex","person_A5001285878","Ge-Peng Ji","{\"openalex\":\"A5001285878\",\"orcid\":\"0000-0001-7092-2877\"}","2026-05-14T08:07:07.381822875","2026-05-23T10:02:30.475768088","0000-0001-7092-2877","person_A5091678461","Yafeng Wu","{\"openalex\":\"A5091678461\",\"orcid\":\"0009-0007-3157-5340\"}","2026-05-19T14:32:58.179239973","2026-05-22T15:21:00.463411996","0009-0007-3157-5340",{"_15":159,"_29":70,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":160,"_39":-5,"_40":147,"_42":161,"_44":162,"_150":151,"_152":153,"_154":-5,"_155":156,"_157":-5,"_125":-5,"_158":-5,"_68":70,"_69":-5},{"_15":145,"_29":71,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":146,"_39":-5,"_40":147,"_42":148,"_44":149,"_150":151,"_152":153,"_154":-5,"_155":156,"_157":-5,"_125":-5,"_158":-5,"_68":71,"_69":-5},"tech_oa_T10627","{\"taxonomy_id\":\"tax_rd_T10627\"}","openalex_topics","2026-05-17T09:00:01.224003475","2026-05-17T09:00:01.22400541","techType","concept","domain","Physical Sciences","proposedYear","maturityLevel","growing","wikipediaUrl","patentCount","tech_oa_T11605","{\"taxonomy_id\":\"tax_rd_T11605\"}","2026-05-17T09:00:06.186961274","2026-05-17T09:00:06.186963469",{"_15":189,"_29":71,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":190,"_39":-5,"_40":41,"_42":191,"_44":192,"_170":171,"_172":-5,"_173":174,"_175":176,"_177":193,"_179":94,"_180":181,"_182":94,"_183":-5,"_68":71,"_69":-5},{"_15":184,"_29":70,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":185,"_39":-5,"_40":41,"_42":186,"_44":187,"_170":171,"_172":-5,"_173":174,"_175":176,"_177":188,"_179":94,"_180":181,"_182":94,"_183":-5,"_68":70,"_69":-5},{"_15":166,"_29":72,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":167,"_39":-5,"_40":41,"_42":168,"_44":169,"_170":171,"_172":-5,"_173":174,"_175":176,"_177":178,"_179":94,"_180":181,"_182":94,"_183":-5,"_68":72,"_69":-5},"tax_rd_T11019","{\"openalex_topic\":\"T11019\"}","2026-05-14T00:50:42.195596405","2026-05-23T12:38:54.270145284","taxonomyType","RESEARCH_DOMAIN","code","level",3,"parentId","tax_rd_1707","path","Physical Sciences/Computer Science/Computer Vision and Pattern Recognition/Image Enhancement Techniques","sortOrder","isLeaf",true,"entityCount","children","tax_rd_T11605","{\"openalex_topic\":\"T11605\"}","2026-05-14T00:27:59.275123602","2026-05-23T12:40:36.233811231","Physical Sciences/Computer Science/Computer Vision and Pattern Recognition/Visual Attention and Saliency Detection","tax_rd_T10627","{\"openalex_topic\":\"T10627\"}","2026-05-14T00:27:13.287760078","2026-05-23T12:38:54.232846671","Physical Sciences/Computer Science/Computer Vision and Pattern Recognition/Advanced Image and Video Retrieval Techniques",{"_73":195,"_75":196},[],[197],{"_78":198,"_80":199,"_82":200,"_84":201},1781536996010,{"_87":203,"_89":90,"_91":198,"_92":-5,"_93":94,"_95":94,"_96":94,"_97":-5,"_98":-5,"_99":67,"_35":100,"_101":102},[86,202],"[\"portal\",\"industries\"]","industries",[204,205,206,207,208,209,210,211,212,213,214,215],{"_15":267,"_29":268,"_31":-5,"_32":269,"_33":270,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":271,"_179":94,"_180":67,"_182":94,"_183":-5,"_68":268,"_69":270},{"_15":263,"_29":264,"_31":-5,"_32":-5,"_33":265,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":266,"_179":94,"_180":67,"_182":94,"_183":-5,"_68":264,"_69":265},{"_15":257,"_29":258,"_31":-5,"_32":259,"_33":260,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":261,"_179":94,"_180":67,"_182":94,"_183":-5,"_68":258,"_69":260},{"_15":253,"_29":254,"_31":-5,"_32":-5,"_33":255,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":256,"_179":94,"_180":67,"_182":94,"_183":-5,"_68":254,"_69":255},{"_15":249,"_29":250,"_31":-5,"_32":-5,"_33":251,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":252,"_179":94,"_180":67,"_182":94,"_183":-5,"_68":250,"_69":251},{"_15":243,"_29":244,"_31":-5,"_32":245,"_33":246,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":247,"_179":94,"_180":67,"_182":94,"_183":-5,"_68":244,"_69":246},{"_15":239,"_29":240,"_31":-5,"_32":-5,"_33":241,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":242,"_179":94,"_180":181,"_182":94,"_183":-5,"_68":240,"_69":241},{"_15":235,"_29":236,"_31":-5,"_32":-5,"_33":237,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":238,"_179":94,"_180":67,"_182":94,"_183":-5,"_68":236,"_69":237},{"_15":231,"_29":232,"_31":-5,"_32":-5,"_33":233,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":234,"_179":94,"_180":67,"_182":94,"_183":-5,"_68":232,"_69":233},{"_15":227,"_29":228,"_31":-5,"_32":-5,"_33":229,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":230,"_179":94,"_180":67,"_182":94,"_183":-5,"_68":228,"_69":229},{"_15":223,"_29":224,"_31":-5,"_32":-5,"_33":225,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":226,"_179":94,"_180":67,"_182":94,"_183":-5,"_68":224,"_69":225},{"_15":216,"_29":217,"_31":-5,"_32":-5,"_33":218,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":219,"_42":-5,"_44":-5,"_170":220,"_172":-5,"_173":90,"_175":221,"_177":222,"_179":94,"_180":67,"_182":94,"_183":-5,"_68":217,"_69":218},"tax_ind_smartphone","智能手机","Smartphone","manual","INDUSTRY","tax_ind_root","科技行业/智能手机","tax_ind_robot","机器人","Robotics","科技行业/机器人","tax_ind_wearable","智能穿戴","Smart Wearables","科技行业/智能穿戴","tax_ind_energy","新能源与智能制造","New Energy & Smart Manufacturing","科技行业/新能源与智能制造","tax_ind_biotech","生物科技","Biotech","科技行业/生物科技","tax_ind_quantum","量子计算","Quantum Computing","科技行业/量子计算","tax_ind_blockchain","区块链",[248],"Blockchain","科技行业/区块链","Web3","tax_ind_enterprise","企业软件","Enterprise Software","科技行业/企业软件","tax_ind_security","网络安全","Cybersecurity","科技行业/网络安全","tax_ind_semi","半导体",[262],"Semiconductor","科技行业/半导体","芯片","tax_ind_cloud","云计算","Cloud Computing","科技行业/云计算","tax_ind_ai","人工智能",[272,273],"Artificial Intelligence","科技行业/人工智能","AI","AI 技术","env",{"_276":24},"SITE_BASE_URL"]

Camouflaged Object Detection via Context-Aware Cross-Level Fusion 论文

Camouflaged Object Detection via Context-Aware Cross-Level Fusion · 相关技术

相关技术